information

Article
Enhancing E-Learning Adaptability with Automated Learning
Style Identification and Sentiment Analysis: A Hybrid Deep
Learning Approach for Smart Education
Tahir Hussain 1 , Lasheng Yu 1, * , Muhammad Asim 2,3, * , Afaq Ahmed 1 and Mudasir Ahmad Wani 2

1 Department of Computer Science and Technology, Central South University, 932 South Lushan Rd,
Changsha 410083, China; [email protected] (T.H.); [email protected] (A.A.)
2 EIAS Data Science Lab, College of Computer and Information Sciences, Prince Sultan University,
Riyadh 11586, Saudi Arabia; [email protected]
3 School of Computer Science and Technology, Guangdong University of Technology,
Guangzhou 510006, China
* Correspondence: [email protected] (L.Y.); [email protected] (M.A.)

Abstract: In smart education, adaptive e-learning systems personalize the educational process by
tailoring it to individual learning styles. Traditionally, identifying these styles relies on learners
completing surveys and questionnaires, which can be tedious and may not reflect their true pref-
erences. Additionally, this approach assumes that learning styles are fixed, leading to a cold-start
problem when automatically identifying styles based on e-learning platform behaviors. To address
these challenges, we propose a novel approach that annotates unlabeled student feedback using
multi-layer topic modeling and implements the Felder–Silverman Learning Style Model (FSLSM) to
identify learning styles automatically. Our method involves learners answering four FSLSM-based
questions upon logging into the e-learning platform and providing personal information like age,
gender, and cognitive characteristics, which are weighted using fuzzy logic. We then analyze learners’
behaviors and activities using web usage mining techniques, classifying their learning sequences into
specific styles with an advanced deep learning model. Additionally, we analyze textual feedback
Citation: Hussain, T.; Yu, L.; Asim, M.;
using latent Dirichlet allocation (LDA) for sentiment analysis to enhance the learning experience
Ahmed, A.; Wani, M.A. Enhancing
further. The experimental results demonstrate that our approach outperforms existing models in
E-Learning Adaptability with
Automated Learning Style
accurately detecting learning styles and improves the overall quality of personalized content delivery.
Identification and Sentiment Analysis:
A Hybrid Deep Learning Approach Keywords: e-learning system; smart education; sentiment analysis; fuzzy weights; FSLSM model;
for Smart Education. Information 2024, deep learning; LSTM; LDA
15, 277. https://doi.org/10.3390/
info15050277

Academic Editors: Arkaitz Zubiaga

1. Introduction
and Luis Borges Gouveia
In recent years, electronic learning (e-learning) systems have emerged as a transfor-
Received: 28 March 2024 mative force, reshaping the landscape of smart education. Online learning systems offer
Revised: 24 April 2024
significant advantages, making education more accessible, flexible, and personalized. By
Accepted: 9 May 2024
eliminating geographical and socioeconomic barriers, these platforms enable individuals
Published: 13 May 2024
from diverse backgrounds to access educational resources from anywhere in the world [1].
This accessibility is especially beneficial for those who might not be able to attend traditional
classroom settings due to work or family commitments [2]. Additionally, online systems
Copyright: © 2024 by the authors.
allow for a high degree of customization, catering to different learning styles and paces,
Licensee MDPI, Basel, Switzerland. which can enhance student engagement and improve learning outcomes. Moreover, online
This article is an open access article courses tend to be more cost-effective than their traditional counterparts, reducing financial
distributed under the terms and barriers for learners and institutions alike. These platforms also provide students with an
conditions of the Creative Commons abundance of resources, including videos, interactive content, and extensive databases,
Attribution (CC BY) license (https:// further enriching the learning experience.
creativecommons.org/licenses/by/ Developing a successful adaptive e-learning system is contingent upon the creation
4.0/). of a detailed student model, incorporating various attributes of the student. Students

Information 2024, 15, 277. https://doi.org/10.3390/info15050277 https://www.mdpi.com/journal/information

Information 2024, 15, 277 2 of 30

have unique ways of engaging with learning materials that shape their individual learning
styles [3]. These styles reflect their preferred methods for processing and understanding
information. Recognizing these styles is crucial for e-learning systems to tailor content that
enhances learning effectively. Traditionally, identifying learning styles involved having
students complete questionnaires. However, this method has several drawbacks: it is
often a boring and time-consuming task, students may not fully understand or be aware
of their learning styles, leading to arbitrary responses, and the results are static, failing to
account for changes in learning styles over time, such a type of learning style identification
approach is known as an explicit approach [4]. These issues highlight the need for a more
dynamic and engaging approach to accurately ascertain students’ learning preferences.
Various automated methods have been developed to identify students’ learning styles
by analyzing their interactions with e-learning systems to address these limitations. These
automatic identification techniques offer several advantages over traditional methods.
Firstly, they eliminate the need for time-consuming questionnaires by gathering data
directly from students’ activities within the system [5]. Additionally, unlike static results
from questionnaires, the learning styles identified through these automated approaches are
dynamic; they can adapt and change in response to shifts in students’ behaviors, ensuring
a more accurate and personalized learning experience; such a type of approach is known as
an implicit approach [6]. The implicit approach is much better than the explicit approach,
but it may face a cold-start problem when new users log into the system. To overcome
these issues, this paper combined both approaches as we collected a minimal number of
input characteristics such as learners’ previous score (categorized by fuzzy weight logic),
age, gender, and lastly, filling our four questions which represented the FSLSM dimension.
Implementing automatic identification of learning styles requires using a learning style
(LS) model, which classifies students based on their preferred learning methods [7]. Various
learning style models have been discussed in this paper. However, the Felder–Silverman
Learning Style Model (FSLSM) is identified as particularly effective for adaptive e-learning
systems according to recent studies [8]. In this paper, the FSLSM model was chosen for the
reasons described in the next section.
This paper proposes a hybrid approach to improve the e-learning system by integrating
automatic learning style identification and simultaneously conducting sentiment analysis
to improve the learning object quality further. To identify automatic learning styles, using
web usage mining techniques, we analyze student behavior and obtain minimal attributes
from learners when they log into the e-learning platform. The collected data on student
activities from the e-learning platform’s log files organizes this information into sequences.
Each sequence consists of the learning objects that a student accessed during a session.
These learning objects are then aligned with the learning style combinations outlined in the
FSLSM. These sequences of student activities, their input attributes, and their corresponding
learning objects are used as input for long short-term memory (LSTM), a recurrent neural
network (RNN) architecture capable of learning long-term dependencies in data sequences.
This algorithm maps the sequences to various learning style categories.
Additionally, this paper analyzes textual feedback to improve the learning objects
further by using LDA for sentiment analysis to examine textual feedback from learners.
This paper proposes a novel approach to annotating unlabeled student feedback using
multi-layer topic modeling and also introduces and implements a novel algorithm for
sentiment extraction and mapping. Our proposed approach combines both implicit and
explicit approaches of learning style identification methods, which removes the limitations
of both approaches that exist individually. The experimental results of this paper not only
outperform existing models in accurately detecting learning styles but also enhance the
quality of learning objects, improving the overall adaptive e-learning systems.
This paper contributes the following points:
1. By using minimal learner inputs and learning sequences of learners, this paper de-
signs LSTM positional encoding to classify learners; our novel approach improves
the accuracy of learning style identification compared to other traditional machine
Information 2024, 15, 277 3 of 30

learning algorithms. This novel approach addresses the limitations of traditional

questionnaire-based methods, such as learners’ time consumption while filling in
forms, lack of self-awareness, and static learning style results.
2. This paper proposes a novel approach to annotating unlabeled student feedback using
multi-layer topic modeling.
3. This paper also introduces and implements a novel rule-based algorithm for sentiment
extraction and mapping. Incorporating LDA to analyze textual feedback from learners,
this research paper offers a nuanced understanding of learners’ perspectives on the
educational content and the overall e-learning experience. This sentiment analysis
allows for the continuous refinement of e-learning content to better align with learner
needs and preferences.
The structure of this paper is outlined as follows: Section 2 describes the literature
review of related work. Section 3 provides prerequisites and introduces the proposed
methodology of this paper. Section 4 presents the experiments conducted and the results.
Section 5 discusses and compares with other models. Section 6 concludes the paper and
discusses the limitations and future work.

2. Related Works
In academic research, a range of classification methods have been applied to automati-
cally determine learning styles and sentiment across different models. Researchers have
utilized these techniques to better understand and cater to individual learning preferences,
enhancing the personalization of educational content.
According to Graf [9], a data-driven approach utilizing artificial intelligence algorithms
has been developed to automatically detect learning styles from learner interactions within
a system. This method uses real behavioral data as input, with the algorithm outputting
the learner’s style preferences, thereby enhancing accuracy. To ensure meaningful data
for classification, web mining techniques are employed to extract detailed behavioral
information, as detailed by Mahmood [10], making the system both effective and efficient
in adapting to individual learning needs.
In [11], a novel method was introduced to identify each learner’s style using the
FSLSM by extracting behaviors from Moodle logs. Decision trees were utilized for dynamic
classification based on these styles, with the method’s accuracy evaluated by comparing
behaviors to quiz results provided at the end of a course. This approach, however, was
tested with a limited sample of 35 learners in a single Moodle-based online course.
In [12], the authors integrated fuzzy logic with neural networks to train an algorithm
capable of recognizing various learning styles. However, the algorithm’s effectiveness was
limited to classifying just three dimensions of the FSLSM model: perception, input, and
understanding.
In [13], the authors employed Bayesian networks to analyze learner data from logs
of chats, forums, and processing activities, detecting only three Felder–Silverman learn-
ing styles: perception, processing, and understanding. Their study illustrates the use
of predictive modeling to discern specific educational traits based on interactive online
behaviors.
Fuzzy logic has been utilized to automatically determine learners’ styles, as demon-
strated by Troussas [14]. Expanding on this, Crockett [15] developed a fuzzy classification
tree within a predictive model that employs independent variables captured through
natural language dialogue, enhancing the precision of style assessments.
In [16], the authors applied the Fuzzy C-Means (FCM) algorithm to categorize learning
behavioral data into FSLSM categories. This clustering approach enabled a structured
analysis of behavioral patterns, aligning them with defined learning styles to enhance
personalized education strategies.
In [17], a model named adaptive e-learning recommender model using learning style
and knowledge-level modeling (AERM-KLLS) was developed to enhance student engage-
ment and performance through personalized materials using questionnaires and adaptive
Information 2024, 15, 277 4 of 30

feedback, focusing on personalized learning experiences. Another study [18] designed an

adaptive learning system based on artificial intelligence model (ALSAI model)for personal-
ized learning environments utilizing artificial intelligence, modeling, adaptive learning,
machine learning, natural language processing, and deep learning, aimed at enhancing
online teaching.
Additionally, a framework was proposed in [19] for the automatic recognition of learn-
ing styles using machine learning, FSLSM, decision tree–hidden Markov model (decision
tree MM) and Bayesian model, specifically targeting the automatic identification of learning
styles. Another contribution [20] included the development of an auto-detection model for
learning styles in learning management systems (LMSs), based on a literature review and
machine learning algorithms.
A systematic review of machine learning techniques for identifying learning styles
was conducted in [21], highlighting the use of neural networks, deep learning, FSLSM,
and visual aural read/write and kinesthetic (VARK), primarily focused on e-learning
enhancement. Furthermore, a convolutional neural network learning feature descriptor
(CNN-LFD) model for predicting learning styles was developed in [22], using convolutional
neural networks (CNNs), Levy flight distribution, and machine learning, aimed at e-
learning environments.
There was also a survey on the automatic prediction of learning styles through a
literature review, FSLSM, classification, clustering, and hybrid methods, emphasizing the
prediction of learning styles [23]. Improvement in the identification of learning styles was
achieved using deep multi-target prediction and artificial neural networks in adaptive
e-learning systems [24]. Lastly, the automatic modeling of learning styles and affective
states in web-based learning management systems was demonstrated in [25] to be more
appropriate than traditional questionnaires for detecting learning styles and affective states.
The literature indicates that learners’ learning styles can be automatically identified
using models such as the FSLSM, which is prominently featured in these studies. Despite
this, most of these investigations rely on behavioral data from just one course, limiting
the robustness of their classifications. There is a noted deficiency in validating these
classification processes across multiple courses, which would provide a more accurate and
reliable identification of learning styles according to the FSLSM.

3. Materials and Methods

3.1. Preliminaries
This subsection explores the core concepts behind adaptive learning: web usage
mining (WUM) for pattern analysis, learning style models (LSM) for categorizing infor-
mation processing preferences, the Felder–Silverman Learning Style Model (FSLSM) for
personalized education, and long short-term memory (LSTM) networks for sequential
data handling.

3.1.1. Learning Style

The term learning styles (LSs) has several definitions in the modern literature.
Pashler [26] defines learning styles as distinctive modes of perception, memory, thought
processes, problem-solving, and decision-making. According to [27], learning styles are the
combination of typical affective, cognitive, and physiological variables that serve as gener-
ally stable markers of how a learner sees, interacts with, and responds to an instructional
environment. Several learning style models have been developed to categorize learners
into certain groups to improve their learning potential by adapting educational content
to their preferences. Some of the most famous learning style models are the Honey and
Mumford learning style model, the Kolb learning style model, the Myers–Briggs Type
Indicator learning style model, the VARK learning style model, and lastly the FSLSM [28].
Information 2024, 15, 277 5 of 30

3.1.2. Web Usage Mining Techniques

Finding and automatically extracting usage patterns from web data is known as web
usage mining (WUM) [29]. Its main focus is on identifying learners’ online behaviors by
looking at how they interact with websites. Log files, which document learners’ activities
as they access material on web servers, are the main source of data for WUM. These web
log files are plain text documents containing data on user activity when interacting with
the e-learning platform. According to [30], the usage mining process consists of three
steps. It starts with data preprocessing, which involves the essential tasks of data cleaning
and transformation to prepare it for analysis. In pattern discovery’s second phase, we
uncover concealed insights and patterns within the processed data. Data mining and
machine learning approaches are used to accomplish this; in the final stage, known as
pattern analysis [31], our attention is directed toward extracting noteworthy and compelling
patterns from the outcomes of the pattern discovery phase. Finally, the learning sequences
of learners are generated; learning sequences refer to learners’ way of learning. This
ensures that only the most pertinent patterns are preserved for further investigation and
practical use.

3.1.3. Felder–Silverman Learning Style Model

Richard Felder and Linda Silverman initially studied the Felder–Silverman learning
style to assist instructors in their instruction of engineering students. However, it has since
gained popularity as a learning style paradigm and is progressively being incorporated
into numerous online learning platforms. In this work, we employed the FSLSM [32]
primarily because of its comprehensive nature compared to other models that categorize
learners into fewer styles [33]. The FSLSM offers an in-depth exploration of learner styles,
making it a suitable choice [34]. It defines four key dimensions: perception of informa-
tion, preferred input type, information processing, and comprehension of information.
Within the perception dimension, there are two variants: sensing (concrete) and intuitive
(abstract/imaginative) [20]. Input preferences can fall into two categories: visual or verbal.
Information processing occurs in two distinct ways: actively through experimentation
and reflectively through observation [35]. Understanding information is also categorized
into two approaches: sequential (following a specific order) and global (working without
a fixed sequence) [36]. These dimensions and their respective values in the FSLSM are
depicted in Figure 1. By selecting one value from each of the four dimensions within the
model, a total of 16 unique combinations of learning styles can be formed [37], as shown
in Table 1. Additionally, the FSLSM’s emphasis on learning inclinations is noteworthy. It ac-
knowledges that even when a learner strongly prefers a certain style, they may occasionally
display actions consistent with a different learning style [38].

Figure 1. Overview of the FSLSM: its four key dimensions, and their associated values [39].
Information 2024, 15, 277 6 of 30

Table 1. FSLSM learning styles: 16 combinations [40].

Group 1 (Active Styles) Group 2 (Reflective Styles)

Active, Sensing, Visual, Sequential Reflective, Sensing, Visual, Sequential
Active, Sensing, Visual, Global Reflective, Sensing, Visual, Global
Active, Sensing, Verbal, Sequential Reflective, Sensing, Verbal, Sequential
Active, Sensing, Verbal, Global Reflective, Sensing, Verbal, Global
Active, Intuitive, Visual, Sequential Reflective, Intuitive, Visual, Sequential
Active, Intuitive, Visual, Global Reflective, Intuitive, Visual, Global
Active, Intuitive, Verbal, Sequential Reflective, Intuitive, Verbal, Sequential
Active, Intuitive, Verbal, Global Reflective, Intuitive, Verbal, Global

3.1.4. Long Short-Term Memory

Long short-term memory (LSTM) networks, a specialized subset of recurrent neural
networks (RNNs), excel in learning long-term dependencies, setting them apart from con-
ventional neural networks, which primarily handle short-term data [41]. These networks
utilize a sequence-to-sequence architecture, particularly beneficial when the input and out-
put sizes vary, encompassing an encoder that summarizes input information over specific
time frames and a decoder that interprets this condensed data to generate outputs [42]. In
the context described, LSTMs process inputs of 4098 units per time step, with the encoder
designed for 24-time steps and the decoder producing outputs of 10 units [43]. This LSTM
configuration is devised to align with the Felder-Shilman learning style model, categorizing
learning styles into five distinct dimensions: perception, input, organization, processing,
and understanding. In this way, the LSTM algorithm classifies and offers a nuanced under-
standing of individual learning preferences, contributing to the enhancement of tailored
educational approaches.

3.2. Methodology
This paper’s aim is to improve adaptability in e-learning systems through learning
style identification and sentiment analysis. It aims to address critical issues such as the
inefficient identification of learning styles through traditional questionnaire-based meth-
ods, which are time-consuming and lack dynamic responsiveness to individual learner
preferences [44]. Additionally, it seeks to address the lack of incorporation of learners’
sentiments and feedback, which are vital for refining e-learning content and improving
learner experiences. To tackle these challenges, this paper introduces a novel hybrid
approach that integrates automatic learning style identification and sentiment analysis.
This approach aims to dynamically identify learners’ preferences and sentiments towards
educational content, thus facilitating a more personalized and engaging learning experi-
ence. By overcoming the limitations of traditional methods and incorporating sentiment
analysis, the proposed system seeks to enhance the effectiveness of e-learning platforms,
ultimately aiming to improve learner engagement, satisfaction, and educational outcomes.
The workflow starts when learners access the e-learning platform; initially, they have to
answer the four questions which are based on the FSLSM dimension [45], and additionally
provide their personal information such as age, gender, and prior academic performance.
Considering the uncertainty in grade classification, fuzzy weights are used to evaluate
prior academic performance. For example, a score of 75% might be seen as both somewhat
good and somewhat excellent. When the learners interact with learning objects in the
e-learning platform, the learners’ behaviors are extracted using web usage mining and
stored in the database, and their learning sequences are captured to identify their learning
style dynamically. To use a supervised learning algorithm, it is essential to convert the
sequences of learner interactions extracted from log files into a suitable input format for
the algorithm. A learner’s interaction sequence is characterized by the different learning
objects they engage with during a session. Each of these sequences is detailed with iden-
tifiers for the sequence, session, and learner, along with a list of the learning objects the
learner interacted with within that session. Following the extraction of these interaction
Information 2024, 15, 277 7 of 30

sequences, they are categorized based on the FSLSM, where each sequence is associated
with a distinct combination of learning styles. This paper used advanced deep learning
techniques, such as a Transformer model with LSTM positional encoding, to automatically
classify learners based on their learning styles because of its ability to handle sequential
data, leveraging its ability to remember long-term dependencies for tasks as compared to
other algorithms. This classifier takes into account various learner attributes, including
age, previous academic performance, gender, and learning sequences. This method enables
an automated process to determine the learning styles of students, aligning them with
specific dimensions without the necessity of completing the entire 44-question FSLSM
questionnaire, is a process known for being long and tedious. Additionally, this approach
utilizes the powerful LDA algorithm to extract key topics from student feedback, enabling
it to unearth valuable insights. As students engage with the e-learning platform, feedback
is collected through surveys and questionnaires. This feedback undergoes thorough pre-
processing to ensure accuracy and meaningful analysis. Using LDA, we identify prominent
aspects within the feedback, shedding light on student preferences, concerns, and senti-
ments. Furthermore, the extracted aspects and sentiments are subjected to aspect-based
sentiment analysis (ABSA), which assesses the sentiment associated with each aspect and
develops a novel algorithm for analyzing aspect-oriented feedback to determine each
piece of feedback’s sentiment orientation (positive, negative, or neutral). Its purpose is to
automatically categorize user feedback based on sentiment, helping to understand overall
user sentiment towards different aspects of feedback. This multifaceted analysis provides
critical insights that guide improvements in the overall e-learning experience. By employ-
ing a sentiment classification algorithm such as the convolutional neural network (CNN),
sentiment labels are assigned to learner feedback, categorizing it as positive, negative, or
neutral based on sentiment scores calculated using a sentiment lexicon. In the final stages of
the workflow, this approach summarizes the results of the aspect-based sentiment analysis
(ABSA) and sends them to educational institutions and instructors. This summary drives
the process of updating course materials and resources in alignment with the feedback
and sentiments expressed by learners. Ultimately, this comprehensive approach paves the
way for more engaging, adaptable, and satisfying e-learning experiences for students. The
overall framework is shown in Figure 2.

Figure 2. Overall proposed framework.

3.3. Learning Style Identification

This study integrates an automatic identification of learning styles (AILS) module
into our system, drawing upon the FSLSM framework, utilizing minimal input attributes,
and extracting learning sequences from learners’ behavior activities. The AILS system
Information 2024, 15, 277 8 of 30

makes use of a tailored Transformer model, incorporating LSTM-based positional encoding

and GloVe word vectors. Its purpose is to efficiently classify students into their specific
learning styles [46]. The process begins with training the Transformer model using a
designated dataset, and subsequently, it predicts the learning style category for each
instance. To ascertain students’ learning styles, Learnenglish considers specific student
attributes, including:
• Age: This significantly influences learning styles, younger students prefer visual learn-
ing while older students engage in detail-oriented competitive, listening, and reading
activities [47]. Younger students also favor peer collaboration, list-making, and direct
communication [48]. Learnenglish treats learning styles as dynamic traits, recognizing
that they can change with age and other characteristics. When students first interact,
they have to select their age from four age groups: prepubescent (6–12 years old),
younger (13–18 years old), average (19–45 years old), and elder (46+ years old).
• Gender: This is a significant factor affecting the recognition of learning styles, as
indicated in previous studies [49]. Both male and female students can benefit from
individualized instruction that aligns with their learning preferences to improve their
acquisition of knowledge and development of skills [50]. For instance, male learners
tend to favor auditory and reading activities, while female learners are more inclined
toward composition activities. Learnenglish collects gender information during the
learner’s initial interaction with options for “female” and “male”.
• Before the first interaction with Learnenglish, students are prompted to answer four
questions, each aligned with one of the FSLSM dimensions [32]: understanding,
perception, input, and processing. These questions, chosen for their relevance and
representativeness, play a crucial role in identifying students’ learning styles. The four
questions are as follows:
• When approaching a new subject, do you prefer (a) Learning the material in
clear steps and maintaining focus? (b) Developing a broad understanding of the
connections between the topic and related subjects? This question is about the
understanding dimension.
• In instructional settings, do you prefer an emphasis on (a) Specific data or factual
material? (b) Theoretical concepts and overarching principles? These questions
show the perception dimension.
• When presented with data and information, do you tend to focus on (a) figures,
charts, and graphs? (b) Oral or written explanations summarizing the findings?
This question represents the input dimension.
• Regarding learning preferences, do you prefer: (a) Collaborative study in a
group setting? (b) Independent study alone? This last question demonstrates the
processing dimension.
• Previous academic performance: This plays a crucial role in identifying learning
styles [51]. It is linked to students’ preferred teaching methods based on their prior aca-
demic achievements. High-achieving students tend to favor more complex knowledge
delivery methods like diagrams and mathematical equations while lower-achieving
students lean towards examples and images [52]. Determining prior academic perfor-
mance occurs during the learner’s initial interaction with Learnenglish, where they
respond to preliminary questions related to English language domain knowledge.
However, assessing academic performance is not straightforward; it is fraught with
uncertainty. For instance, when a student scores 70/100, it cannot be definitively
categorized as either good or advanced. Three fuzzy weights—beginner ( B), interme-
diate ( I ), and advanced ( A)—are used in fuzzy logic to solve this problem [53]. These
weights are represented by membership functions based on the student’s score. The
membership functions, illustrated in Figure 3, are defined with respect to the student’s
score (represented as x). The “X” values indicate the score obtained by a student
in a subject. The membership functions determine how well this score aligns with
Information 2024, 15, 277 9 of 30

the predefined categories of “beginner”, “intermediate”, and “advanced” based on

fuzzy logic. The µ B ( x ) categorizes learner scores into advanced, intermediate, and
beginner [54]. The µ1 ( x ) second case offers detailed classification from intermediate to
advanced and beginner, and the µ A ( x ) case further refines the classification, providing
intermediate, intermediate to advanced, and beginner categories.

Figure 3. Fuzzy weighting for a student’s prior academic performance. (a) Mathematical Definitions
for Membership Functions (b) Graphical Representation of Membership Functions.

The membership functions described above assign values to the three fuzzy sets
(µb , µ I , µ A ) representing each student’s prior academic performance (Figure 3). These
numbers go from 0 to 1, where 1 denotes a total understanding of the subject matter being
taught. As a result, the equation µ B ( x ) + µ I ( x ) + µ A ( x ) = 1 states that the total of the
partition values for these fuzzy sets for the domain notion is always 1. These fuzzy sets
and their membership function thresholds were determined by a panel of 16 experts from
various domains. Among them, 10 were computer science experts from public universities’
computer science departments, and 6 were pedagogical experts from public universities’
education departments. These experts, each with over 10 years of experience, provided
descriptive assessments of student progress and performance levels along with defining
success intervals for each knowledge level.

3.4. Learning Style Classification

A modified Transformer design is used to classify students’ learning styles, as Figure 4
illustrates. Global Vectors (GloVe), an unsupervised technique, offers a solution to the limi-
tations of traditional word-to-vector (Word2Vec) approaches [55]. In contrast to Word2Vec,
which depends on a one-to-one correspondence between words and vectors and encounters
difficulties with synonyms and polysemous terms, GloVe capitalizes on global statistics,
historical data, and the benefits of co-occurrence windows to adeptly handle these syn-
onyms and polysemous words [56]. This approach enhances grammatical and semantic
information richness in word feature representation, making it a valuable alternative to
traditional Word2Vec techniques.
The total number of unique terms in our domain-specific knowledge is represented by
the symbol V. We have a word vector representation wi , and an associated bias term (b) for
every word bi . When we refer to the occurrence of word j within the context of word i, it is
represented as xij , and xi represents the total count of words that co-occur with word i. We
use Equation (1) to compute the probability Pij of word j appearing in the context of word i.

xij
Pij = (1)
xi

The co-occurrence probabilities receive weight assignments through the application of

x
the weighting function, denoted as f ( x ). This function is often selected as f ( x ) = xmax ,
where xmax represents the maximum count of co-occurrences in the corpus [57]. xmax is
Information 2024, 15, 277 10 of 30

a hyperparameter responsible for governing the weighting process and holds significant
importance in the context of GloVe. GloVe’s primary optimization objective lies in the
minimization of the loss function illustrated in Equation (2). This optimization is conducted
under the constraint outlined in Equation (3).
v v
J= ∑ ∑ f ( pij ) · (wiT · w j + bi + bj − log (Xij ))2 (2)
i =1 j =1

wiT · w j + bi + b j − log( xij ) = 0 for all (i, j) word pairs. (3)

A widely
 adopted selection for the weighting function, denoted as f ( x ), is expressed
 α
x
as f ( x ) = xmax . Here, xmax represents the maximum co-occurrence count within the
corpus, while α acts as the hyperparameter responsible for controlling the probability
weighting process [58]. Additionally, we enhance our input sentence representation by
introducing positional encoding through the utilization of (LSTM), as shown in Figure 4.
This allows our model to take into account the order of words and their positions, which
is a crucial task in text classification. The “[batch_size, pad_size, Embad_size]” describes
the structure of our input data. “batch_size” is the number of sequences processed in each
batch, “pad_size” is the sequence length after padding to ensure uniformity, and “Em-
bad_size” is the dimension of our word embeddings. PE( pos,2i) and PE( pos,2i+1) represent
positional encodings for words in the input sentences. These encodings are used to provide
information
 about theposition 
 of words in the sequence. The mathematical functions
pos pos
sin 1000002i/d and cos 1000002i/d calculate the positional encodings. They are based on
the position (pos) of words in the sequence and the embeddings’ dimension (d).

Figure 4. Design of the LSTM positional encoding architecture in our research.

LSTM Positional Encoding

The Transformer has trouble effectively utilizing both front and back data because it
lacks temporal information [59]. LSTM frequently exhibits a superior capacity for address-
ing temporally sensitive matters through the utilization of dedicated implicit units designed
for the extended storage of input information [60]. Consequently, LSTM is implemented as
a preceding layer before obtaining the location data. The specific procedure is illustrated
in Figure 5. To enhance the efficiency of dot products, it becomes imperative that the
distribution of attention probabilities for pertinent queries be non-uniform [61]. Leveraging
KL divergence, we identify the most critical queries and disregard the remaining ones
while assessing query sparsity. Equation (4) represents the probability formulation for the
maximal average measurement.
Information 2024, 15, 277 11 of 30

qi K jT qi K jT
! !
Lk
1
M̂(qi , K ) = max √
j d
−
LK ∑ √
d
(4)
j =1

The proposed approach makes use of “Log-Sum-Exp” to ascertain the qi average and
peak levels. When a relatively high M(qi , k) value is chosen, it amplifies the importance
of the attention probability P(k j |qi ). This querying technique effectively filters out less
critical information, creating a novel probabilistic sparse matrix, denoted as Q, which
encapsulates the most relevant specifics from M(qi , K ). By employing the sample sampling
factor u = c ln Q in the dot product calculation, we manage to reduce the complexity to
O( LK ln LQ). When calculating the dot product, the sample sampling factor u = cInQ
decreases in complexity to O( LK InLQ ). The dot product is then used to generate the
confidence score P, which highlights the factor that is being given the most attention.
Higher confidence scores indicate stronger associations. Equation (5) displays the formula
for P.
Q̂ · K
P= √ (5)
d
This approach uses the top-k(n) method to extract relevant information from P based
on the confidence score P. For each row in P, we isolate the top n scores, forming a pool
of key indices, where n is adjusted to c. This strategy maintains the intended meaning
while emphasizing the most important information. The final values are set to zero. This
strategy streamlines the model by selecting the most important scores while preserving
important data. The conversion of P into a sparse matrix P is achieved by utilizing the
softmax function, and this process is an integral part of the regularization procedure.
Finally, Equation (6) shows the ultimate result, S.

S = softmax( P̂)V (6)

By leveraging a mask, our model utilizes Kullback–Leibler (KL) divergence to filter

and assess attention points, allowing for the extraction and refinement of attention. A
diagram of this is shown in Figure 5.

Figure 5. The proposed framework for classifying learning styles.

Information 2024, 15, 277 12 of 30

3.5. Final Output Layer

Using the feature vector from the previous layer as input, we run the text through
a softmax classifier to classify it. The probability of the classifier for class j indicates the
chance of the text being placed in that specific category, as per Equation (7).

(θ jT xi )
e
P ( yi = j | x i ; θ ) = T i
(7)
∑kn=1 e(θn x )

3.6. Aspect-Based Sentiment Analysis

After identifying learners’ learning styles, learning materials were provided to each
learner according to their individual preferences; simultaneously, feedback was collected
from each learner to improve the quality of the materials further. We have developed
an automated and resilient system for analyzing textual data from student feedback col-
lected during teaching-learning. This system efficiently tags and processes the textual
data, providing detailed insights. The proposed framework generates concise annotated
results, including aspect terms and sentiments, which are then presented to the institute’s
management and study board. Subsequently, these results are forwarded to the relevant
authorities for analysis and decision-making. To ensure prompt results, the system accepts
offline data for training. Our proposed system transforms student feedback into meaningful
information, facilitating a deeper understanding of the situation. The framework of our
approach is illustrated in Figure 6.

Figure 6. Proposed framework for aspect-based sentiment classification.

3.7. Dataset
The dataset used in this paper is publicly available, originates from a prominent
northern Indian university, and serves as the foundation for generating the institutional
report through the analysis of student feedback data [62]. It encompasses six essential
categories: teaching quality, course content, lab experiences, library facilities, and the
environment of the institute. Each category in the dataset is represented by two columns,
allowing for sentiment labels—0 (neutral), 1 (positive), or −1 (negative)—to be assigned.
This dataset provides a comprehensive view of student opinions, making it a valuable
resource for evaluating various facets of the university experience, and the sample dataset
is shown in Figure 7.
Information 2024, 15, 277 13 of 30

Figure 7. Dataset sample used in our research.

3.8. Preprocessing
The data were cleaned during the preprocessing procedure [63] to enable efficient
computation. In the initial stages of text data preprocessing, our approach incorporates a
series of essential steps to ensure the consistency and quality of textual data for subsequent
analysis. These steps include the following.
• Word Tokenization: Word tokenization involves the task of segmenting the text into
individual words or tokens. It divides the text into discrete units where each unit is
typically a word [64]. For example, the sentence “The quick brown fox” would be
transformed into tokens as follows: [“The” “quick” “brown” “fox”]. Tokenization is
essential because it transforms unstructured text into a structured format that com-
puters can process. It enables subsequent analysis, such as counting word frequency,
determining sentence structure, and identifying significant terms.
• Lowercase Conversion: Lowercase conversion involves changing all the tokens in
the text to lowercase [65]. For instance, “Word” becomes “word”. This step ensures
uniformity in text analysis by treating words with different letter cases as identical.
Lowercasing simplifies text analysis by reducing the influence of letter case variations,
allowing for more accurate word matching and counting.
• Removal of Numbers and Punctuation: This step focuses on removing numerical
characters and punctuation marks from the text [66]. For example, When we transform
“The price is $100” into “The price is”, we eliminate the numbers and punctuation. This
simplification process streamlines the text, removing non-textual elements, and thus,
making it more amenable to the extraction of meaningful information from the text.
• Exclusion of Symbols and Hyphens: Symbols like “@” or “#” and hyphens are excluded
from the text. These characters often do not carry significant linguistic meaning and can
interfere with text analysis [67]. Excluding symbols and hyphens maintains the focus on
the textual content, reducing noise and distractions from non-textual elements.
• Stop Word Removal: Stop words consist of common, uninformative words such as “of”
“they” “is” “on”, etc. In this step, these words are removed from the text. Removing
stop words is critical for improving feature extraction because it reduces the influence
of frequently occurring but less meaningful words [68]. This enhances the quality of
text analysis and gives more attention to content-rich terms.
• Stemming and Lemmatization: Stemming and lemmatization are techniques to reduce
words to their base forms. Stemming typically removes suffixes, resulting in a root
form (e.g., “running” → “run”) [69]. Lemmatization focuses on semantic relevance,
ensuring that words are reduced to their dictionary form (e.g., “better” → “good”).

3.9. Aspect Extraction and Mapping

This approach implements a two-layered approach in the aspect modeling framework,
as shown in Figure 8. The initial layer focuses on the extraction of aspects, employing both
LDA in its various forms [70] and co-occurrence analysis techniques. These methods are
Information 2024, 15, 277 14 of 30

instrumental in identifying relevant topics and associated terms. A rule-based algorithm

is then applied to scrutinize each aspect derived from topics and terms, ensuring their
validity as suggested by both LDA and co-occurrence analysis. The subsequent layer
of the proposed methodology is dedicated to extracting and labeling sentiments within
each comment and assigning appropriate labels by correlating comments with predefined
polarities, thereby mapping sentiments to the extracted aspects.

Figure 8. Multi-level framework for aspect extraction and labeling.

Using the LDA technique extracts aspect terms from unlabeled data for students’
textual feedback. These hidden aspects in student feedback were discovered using an
unsupervised LDA model similar to the latent topics represented by documents. The
generative workflow of LDA involves documents as mixtures over latent topics with words
characterized by topic-specific word probabilities. This approach allowed us to uncover
hidden aspects of student feedback effectively [71].
The generative process of LDA is shown in Figure 9, presenting an overview of its
key elements. In this context, ‘D’ symbolizes the corpus containing many documents, ‘z’
denotes topics, and ‘w’ represents the words present within these documents. Additionally,
within this visual representation, ‘α’ and ‘β’ are utilized to signify Dirichlet distributions,
while ‘θ’ and ‘ϕ’ are indicative of multinomial distributions.

j =1 i =1
P(W, Z, θ, ϕ, α, β) = ∏ P(θ j ; α) ∏ P(ϕi ; β)
M K
(8)
t =1
∏ P(Zj,t |θ j ) P(Wj,t |ϕzj,t )
N

Equation (8) depicts the LDA probability model, which consists of two sides. On the
left-hand side, the document’s probability is a mixture of latent topics, while the right-hand
side involves four distinct factors. The first two factors serve as the foundation of LDA,
while the latter two act as its driving mechanisms. Each factor calculates probabilities
and multiplies them to determine the final document probability. To be more specific,
the first term on the right-hand side corresponds to topics and is characterized by a
Dirichlet distribution, while the second factor represents words, also following a Dirichlet
distribution. In the same way, the third element of the equation is linked with topics, while
the fourth is associated with words. Both elements are defined by multinomial distributions.
Information 2024, 15, 277 15 of 30

Figure 9. The architectural illustration of the LDA topic modeling approach.

This approach involved implementing LDA through Gensim and customizing it to

suit our dataset. We conducted extensive fine-tuning of the hyperparameters α and β and
carefully optimized the number of topics T to ensure alignment with the characteristics
of the student feedback A detailed outline of the hyperparameter settings tailored to our
dataset can be found in Table 2.

Table 2. LDA hyperparameters.

Hyperparameter Value
Number of Topics 3
Number of Passes 10
Document–Topic Prior Alpha 0.01
Beta (Previous Topic–Word) 0.1
Random State 42
Maximum Iterations 500
Minimum Token Frequency 10
Maximum Features 5000
Chunk Size 2000
Learning Decay 0.7
Learning Offset 10
Perplexity Score Tolerance 0.1
Mean Change Tolerance 0.001
Learning Method ‘batch’
Evaluate Every 1

3.10. Aspects Mapping

Our approach to validate the aspects extracted through LDA analysis involved the
development and execution of Algorithm 1. This algorithm systematically reviews each
student’s feedback, matching terms, and their synonymous equivalents. The synonymous
terms were manually collected and organized into separate files [72,73]. Additionally,
part-of-speech (POS) tagging was employed to link specific aspect terms with the related
comments, as exemplified in Table 3. The relevant terms are associated with their corre-
sponding feedback and recorded in the “extracted aspects” column.
Information 2024, 15, 277 16 of 30

When combined with feature modification techniques, the approach demonstrates

significant accuracy improvements, indicating the algorithm’s strong performance in han-
dling real-world data. Moreover, the use of multi-core parallel processing techniques, as
mentioned, enhances efficiency and reduces processing time, further underscoring the
algorithm’s robust performance in practical applications.

Algorithm 1 Sentiment Extraction and Mapping

1: function S ENTIMENT E XTRACTOR(File)
2: Input: Aspect Oriented Feedback’s File
3: Output: Sentiment Orientation
4: total_positive, total_negative, total_neutral ← 0, 0, 0
5: positive_score ← CALCULATE.POSITIVESCORE(feedback[i])
6: negative_score ← CALCULATE.NEGATIVESCORE(feedback[i])
7: if feedback[i] is in NegationWordList then
8: SWAP(positive_score, negative_score)
9: end if
10: sentiment_score ← CALCULATE.OVERALLSENTIMENTSCORE
11: if sentiment_score > 0 then
12: feedback[i] ← Positive
13: total_positive ← total_positive + 1
14: else if sentiment_score < 0 then
15: feedback[i] ← Negative
16: total_negative ← total_negative + 1
17: else
18: feedback[i] ← Neutral
19: total_neutral ← total_neutral + 1
20: end if
21: end function

Table 3. Part-of-Speech( POS) Tagging.

No. Feedback POS Tagging

1 The classrooms at my university are small and not DT | NNS | IN | PRP | NN | VBP | JJ | CC | RB | RB
well-ventilated... | VBN
2 This course give us limited knowledge DT | NN | VB | PRP | JJ | NN
3 University arranging very less Events for Students NNP | VBG | RB | JJR | NNS | IN | NNS
4 Some course becomes difficult to understand be- DT | NN | VBZ | JJ | TO | VB | IN | IN | NNS
cause of technical issues...
5 There is need an improvements in courses EX | VBZ | MD | DT | NNS | IN | NNS
6 Sometimes teachers discourage students from asking RB | NNS | JJ | NNS | IN | VBG | DT | NN
the tough questions

3.11. Extracting and Mapping of Sentiments

This paper designed and assessed a sentiment classification algorithm (Algorithm 1) ,
which is employed to assign sentiment labels based on sentiment orientation by utilizing a
sentiment lexicon [74] containing 2006 positive expressions and 4783 negative expressions.
We calculated sentiment scores for each feedback with the aid of this sentiment lexicon.
Based on these scores, we classified each feedback into positive, negative, or neutral
sentiment categories.

3.12. Sentiment Classification

This study used a two-layer convolutional neural network to review sentiment classi-
fication. CNNs operate exclusively with fixed-length inputs, necessitating the standardiza-
tion of input lengths to ‘l’ by either truncating longer sentences or padding shorter ones
Information 2024, 15, 277 17 of 30

with zeros. Here, ‘Xi ’ represents an input instance while ‘xi ’ denotes the ith word within
that instance.
Layer 0: This initial layer incorporates word embeddings using Word2Vec representing
words as low-dimensional vectors ‘vi ∈ Rk’ where ‘k’ denotes the dimension of the word
vectors. These word vectors are concatenated to form the input instance ‘X ∈ Rl × k’.
Layer 1: In this layer, a one-dimensional convolution operation is applied with filter
weights ‘m’ of width ‘n’. For each word vector ‘vi ’, feature vectors are generated by
capturing contextual information within a window of size ‘n’. The output is calculated
using the ReLU activation function:

f j = m T v j:j+n−1
(9)
O = σ( f j + b)

Layer 2: Similar to layer 1, this layer includes a one-dimensional convolution operation

followed by max pooling.
Layer 3: The output from layer 2 is passed through a fully connected layer with ReLU
activation and dropout regularization.
Layer 4: The final layer is another fully connected layer with sigmoid activation for
classification.
This structure is a convolutional neural network (CNN) with two layers. The model
trains on source domain data and subsequently fine-tunes with target domain data to
enhance its performance and adapt to the specific domain.

4. Experiments and Results Analysis

This results section presents the experimental results, their interpretation, comparison
with other existing models, and conclusions from our experiments.

4.1. Evaluation Metrics

Loss metrics and a confusion matrix approach were used to evaluate the effectiveness
of the proposed methodology and the accuracy of the classification algorithm utilized in
this study. This approach involves a structured representation of the actual versus predicted
classifications, facilitating the analysis of the model’s performance across various categories.
Let us assume our analysis involves a confusion matrix designed for ‘n’ distinct classes, the
confusion matrix allows us to determine the counts of true positives (TTPs), true negatives
(TTNs), false positives (TFPs), and false negatives (TFNs) within each category.
False negatives (FNs) represent the count of instances that the classifier incorrectly
labels as negative when they are actually positive. False positives (FPs) indicate the
instances that the classifier mistakenly predicts as positive, though they are, in reality,
negative. True negatives (TNs) denote the instances that are negative and are accurately
classified by the classifier as such. True positives (TPs) are the positive instances that the
classifier rightly identifies as positive.
To assess the effectiveness of a classification model, specific metrics can be calculated,
including accuracy (A), precision (P), recall (R), and the F1 score (F1), each serving as critical
indicators of validation performance.
Precision (P): Measures the proportion of correctly predicted positive observations to
the total predicted positives.
TP
P=
TP + FP
Recall (R): Captures the ratio of correctly predicted positive observations to all actual
positives.
TP
R=
TP + FN
Information 2024, 15, 277 18 of 30

Accuracy (A): Accuracy reflects the proportion of total predictions that a model has
classified correctly.
TP + TN
A=
TP + TN + FP + FN
F1 score: Harmonic mean of precision and recall, balancing both metrics.

P×R
F1 = 2 ×
P+R

4.2. Experiment and Results

In this paper, the experimental section describes the effectiveness of the proposed
hybrid deep learning approach in enhancing e-learning systems. This involves two key
components: automatic learning style identification and sentiment analysis. To assess
the effectiveness of the proposed learning style identification methods, a comprehensive
experiment was conducted with 126 students. Initially, when students log into an LMS
such as Sup’Management Group, a free and open-source platform created to assist students
and educators in advancing their learning experiences, they fill in four questions aligned
with the dimensions of the FSLSM and the entirety of the 44-question Index of Learning
Styles (ILS) based on FSLSM, as well as basic information such as age and gender. We
administered a preliminary test as part of this tailored approach to evaluate the student’s
prior academic achievements. Using fuzzy weight logic, we analyzed the test scores, which
helped to accurately determine each student’s knowledge level. Secondly, from the e-
learning platform, we gathered 1235 sequences that reflect the behaviors of learners, with
each student contributing between 1 and 35 sequences. This dataset includes students’
demographic information (such as age and gender), their prior academic performance, and
their responses to four key questions aligned with the FSLSM dimensions and 1235 learning
sequences. These elements serve as inputs for our algorithm to predict individual learning
styles. The experiments demonstrate how the proposed model accurately categorizes
students into various learning styles based on (FSLSM) and is validated through a series of
tests for accuracy, precision, recall, and F1 score. Our novel approach achieved a learning
style prediction accuracy of 95.54%, precision of 95.54%, recall of 95.55%, and an F1 score
of 95.54%. Sentiment analysis further explores student feedback using LDA for topic
modeling. This approach effectively uncovers key aspects and sentiments within the
feedback, providing a nuanced understanding of student opinions on different facets of the
e-learning system. The performance of sentiment analysis was evaluated using a two-layer
convolutional neural network (CNN), which achieved a peak accuracy of 93.81%.

4.3. Learning Style Identification

The first experiment was carried out to demonstrate the reliability of the proposed work
when using learning behaviors that are relevant to various courses to determine the learning
type by randomly selecting a course and 126 students to gather the data to find the learning
style according to FSLSM dimensions. The test sequences are categorized into eight FSLSM
categories: verbal sequential, visual, active, reflective, sensing, intuitive, and global. After
210 iterations, the final clusters are obtained. The clustering outcome is shown in Table 4.

Table 4. The number of sequences generated by algorithms for each cluster.

Models C1 C2 C3 C4 C5 C6 C7 C8 C9 C10 C11 C12 C13 C14 C15 C16

LSTM Algorithm 75 82 72 75 91 98 87 80 74 76 71 74 90 95 86 72

MCQ Method 73 84 69 77 93 97 85 83 78 72 69 78 89 93 88 70

K-Means Algorithm 65 70 72 67 94 88 76 84 65 77 74 61 87 95 86 74
Information 2024, 15, 277 19 of 30

The 16 FSLSM categories are used to label the sequences. Since some sequences, based
on feature values, belong to more than one cluster, the total number of sequences clustered
using the LSTM algorithm is 1298, which is greater than the 1235 input sequences. In our
paper, i = 60, 100, and 200, and c = 4, n = 1235, d = 16, c = 4 correspond to the number of
data points, k to the number of clusters, c to the number of dimensions, and i to the number
of iterations. The results of our computation and a comparison of the temporal complexity
of both techniques are shown in Table 5.

Table 5. The time complexity of the proposed approach and FCM (Fuzzy C-Means) based on the
number of iterations.

1 Time Complexity of Proposed FCM Algorithm’s Time Complexity

Algorithms O(ndc2 i ) O(ndc2 i )
60 300 s 758 s
100 689 s 1264 s
200 1389 s 2529 s

The cross-validation outcomes for every dimension and algorithm are shown in
Table 6. Even though the proposed method has the highest precision, recall, and accuracy
scores in terms of size, as can be shown, the cross-validation score is just 78%. Other
algorithms with high cross-validation ratings are logistic regression random forest and
linear discriminant analysis. How will this help researchers and practitioners? Discussing
two significant aspects of this research will help to address this query. One is the distinction
and resemblance between hand marking and machine prediction in terms of consistency,
as can be seen in Table 7.

Table 6. Results of each dimension’s cross-validation and different algorithms.

Algorithms Dimensions
Input Processing Understanding Perception
Proposed Approach 78% 83% 83% 89%
Random Forest 79% 77% 77% 91%
Classifier Using Decision Tree 73% 74% 74% 90%
Naive Bayes 77% 76% 76% 86%
Logistic Regression 79% 80% 80% 87%
K-Nearest Neighbor 76% 78% 78% 90%
Analyzing Linear Discriminant 79% 79% 79% 86%
Cross-Validation Scores

Table 7. The degree of consistency between machine prediction and manual marking about Gardner’s
multiple intelligence theory.

Number of Students Who Have

Number of Students Who, Accord- (Number of Students from Manual
Dominant Intelligence as Deter-
Dominant Intelligence ing to the Machine Learning Method, Marking /Correct Predictions Made
mined by Manually Marking the
Have Dominant Intelligence by Machine) * 100
E-Questionnaire
Verbal–Linguistic 39 32 82.05%
Bodily–Kinesthetic 27 16 59.26%
Mathematical–Logical 43 36 83.72%
Visual–Spatial 57 52 91.23%
Interpersonal–Intrapersonal 34 26 76.47%
Total 200 162 81.00%
Information 2024, 15, 277 20 of 30

4.4. Learning Style Classification

Understanding students’ diverse learning styles is fundamental to creating tailored ed-
ucational experiences. To achieve this, we used capabilities of the Transformer architecture
in combination with GloVe (Global Vectors for Word Representation) word embeddings.
The amalgamation of these cutting-edge technologies allowed us to navigate the complexi-
ties of student learning styles with precision and efficiency by assessing the performance
of the designed Transformer architecture using accuracy and loss metrics. The model
achieved an outstanding accuracy of 95.54%, as demonstrated in Figure 10. Confusion
matrices (Table 8) provided detailed insights into classification accuracy for each learning
style cluster. These results affirm the effectiveness of the proposed approach, showcasing
its potential for personalized education delivery.

Figure 10. Performance evaluation based on accuracy and loss metrics: (a) accuracy and validation
accuracy; (b) training and validation loss.

Additionally, we evaluated the proposed model’s performance for each learning style,
as shown in Table 9. This detailed analysis offers precise insights into the model’s accuracy
within specific learning style categories, affirming its effectiveness in personalized learning
assessments.

Table 8. Confusion matrices for the classification of student learning styles.

C1 C2 C3 C4 C5 C6 C7 C8 C9 C10 C11 C12 C13 C14 C15 C16

Class 1 424 2 4 3 3 1 0 4 3 2 3 1 1 0 1 1
Class 2 2 428 2 2 0 1 1 2 1 2 3 1 2 1 1 1
Class 3 0 1 446 0 0 1 0 0 1 0 0 1 0 0 0 0
Class 4 1 0 0 437 0 2 0 3 1 1 3 0 0 1 0 1
Class 5 0 2 1 0 441 1 0 1 0 1 1 1 0 1 0 0
Class 6 2 0 0 0 0 443 0 0 1 0 0 1 1 1 1 0
Class 7 2 0 0 1 0 0 442 0 1 1 0 1 0 0 1 1
Class 8 2 0 2 0 3 0 0 434 0 3 1 2 3 2 3 0
Class 9 4 0 2 0 2 0 0 1 430 2 0 2 0 1 1 1
Class 10 5 0 0 3 0 4 0 3 0 425 3 0 3 2 2 0
Class 11 2 5 3 5 2 0 3 0 2 0 420 2 2 3 0 1
Class 12 1 1 2 2 1 1 2 1 1 0 0 427 5 3 2 1
Class 13 0 1 1 0 1 0 2 0 1 0 1 0 435 4 2 2
Class 14 2 3 2 2 4 2 2 4 0 3 0 0 2 418 2 4
Class 15 4 0 0 0 2 0 0 7 0 6 0 5 0 5 410 11
Class 16 3 2 2 1 0 0 0 2 3 0 2 3 0 3 6 423
Information 2024, 15, 277 21 of 30

Table 9. Evaluation of performance for each learning style classification.

Class Accuracy Precision Recall F1 Score

1 0.9918 0.94 0.93 0.93
2 0.9946 0.95 0.96 0.96
3 0.9965 0.99 0.96 0.97
4 0.9956 0.97 0.96 0.96
5 0.9963 0.98 0.96 0.97
6 0.9972 0.98 0.97 0.98
7 0.9975 0.98 0.98 0.98
8 0.9932 0.95 0.94 0.95
9 0.9957 0.96 0.97 0.97
10 0.9936 0.94 0.95 0.95
11 0.9935 0.93 0.96 0.95
12 0.994 0.95 0.96 0.95
13 0.9953 0.97 0.96 0.96
14 0.9918 0.93 0.94 0.93
15 0.9914 0.91 0.95 0.93
16 0.9929 0.94 0.95 0.94

4.5. Aspect-Based Sentiment Analysis

In this paper, we used LDA topic modeling to identify topics in the feedback provided
by learners. The results are shown in Table 10, with the first column dedicated to student
feedback while the second column displays aspect terms organized into three categories:
teacher, course, and university. These categories were determined through LDA analysis
using the id2word vocabulary sourced from our corpus. In addition, Table 11 presents the
results of applying Algorithm 1 for sentiment orientation and mapping, showcasing its
effectiveness in sentiment classification. It displays the sentiment labeling results, where
two subject matter experts examined each label. One is a specialist in English linguistics,
while the other is in text mining. To determine the sentiment scores for each feedback, we
used the sentiment dictionary “citephu2004mining”, which includes 2006 terms associated
with positivity and 4783 terms conveying negativity [75]. We calculated the sentiment score
employing the previously mentioned sentiment lexicon, subsequently assigning labels
of either positive, negative, or neutral to each feedback based on the obtained sentiment
score. Furthermore, Table 12 presents the extracted topics, inclusive of their corresponding
keywords, subject contribution percentages, and illustrative text. It also serves as a visual
aid in understanding the topics extracted with accompanying relevant terms and coherence
scores, all achieved through LDA Gensim [76]. In the same way, it graphically illustrates
the extracted topics, the associated terms, and the coherence scores obtained using LDA
Gensim. Furthermore, our sentiment analysis approach leveraged a tailor-made rule-based
classifier. This led to the categorization of each comment into positive, negative, or neutral
sentiments depending on the polarity detected. It also illustrates the topics that were
extracted using LDA Gensim, along with relevant terms and coherence scores.

Table 10. Student feedback and aspect extraction.

Feedback Extracted Aspects

1 Teacher have enough knowledge and know how to deliver lecture. Teacher
2 Teacher gives helpful examples to make the course easier. Course, teacher
3 Teacher’s behavior isn’t great for everyone. Teacher
4 There have lack of lab facility therefore its not good to study here. University
Information 2024, 15, 277 22 of 30

Table 10. Cont.

Feedback Extracted Aspects

5 The university should have more fun and extra extracurricular activities, not only study. University
Environment of the university is so bad, environment should be clean, I don’t want to stay
6 University
here because of poor environment.
7 I don’t quite get what this course is about. Course
8 I’m not happy with what we’re learning in this course. Course
9 I like the programming part of the course. Course
10 Teacher needs to explain things better with more details. Teacher
11 Teacher do not have enough knowledge about practical studies. Teacher
12 The teacher does not have good teaching experience and needs more experience. Teacher
13 Some teacher could not arrive classroom on time, teacher must arrive on class. Teacher
14 The cafeteria is not good need more improvement to provide better facilities for students. University
I think the university administrative is so good they know how to manage resources
15 University
for students.
16 There is a lack of labs in the university, and more labs should be performed practically. University
The university internet server is so bad, it should be improved and check their
17 University
quality regularly.
18 The course selection policy is bad, I don’t like it as I have to learn irrelevant subjects. Course
Each course provide us excellent knowledge which boosts our skill, I happy to after complet-
19 Course
ing this course.
20 I did not understand course content because of lack of teacher knowledge. Course, teacher
21 The materials we learned are not up to date its too old materials. Course

Table 11. The outcomes of proposed Algorithm 1 for sentiment analysis.

Extracted Sentiment
Feedback
Aspect Orientation
1 Teacher’s behavior isn’t great for everyone. Teacher Negative
2 University should have more fun stuff, not just studying. University Neutral
The environment of the university is so bad, the environment should be clean,
3 University Negative
I don’t want to stay here because of poor environment.
4 I like the programming part of the course. Course Positive
Course,
5 The materials are not up to date, the teacher must have to provide latest materials. Negative
teacher
6 The materials we learned are not up to date; they are too old. Course Negative
7 The course selection procedure is so bad. Course Negative
8 University has less teaching staff, if increase teaching staff it will be good. University General
9 This course is interesting. Course Positive
10 University’s new library resources are very poor. University Negative
11 University providing more facilities. University Positive
12 Teacher well prepared lecture. Teacher Positive

Table 12. Extracted topics and their corresponding terms obtained through LDA.

Topic_Perc
Topic_Num Keywords Representative Text
_Contrib
Course, learn, study, teach, program,
[learn, research, based, course, dip, machine
0.0 0.9251 interesting, achieve, skill, understand,
learning, vision]
help
Teacher, empower, overlook, often, bad, [teacher, bad habit, tell, teacher, thing, tell,
1.0 0.9390
due, love, give, job, time parent, exact, opposite]
University, provide, experience, big, op-
[educational, institution, play, key, role, city,
2.0 0.9209 portunity, develop, game, offer, staff,
region, operate]
library
Information 2024, 15, 277 23 of 30

Figure 11 indicates the sentiment orientation concerning feedback aspects.

Figure 11. Sentiment orientation based on extracted aspects.

4.6. Sentiment Classification

We harnessed a two-layer convolutional neural network to enhance sentiment clas-
sification for student feedback within the realm of e-learning systems. After meticulous
fine-tuning of hyperparameters tailored to our specific classification task, our novel ap-
proach achieved peak accuracy, reaching an impressive 93.81%. Figure 12 visually depicts
the accuracy and loss graphs, which we employed to assess the performance of our senti-
ment classification models.

Figure 12. Performance evaluation of the model by analyzing accuracy and loss graphs based on our
specific dataset.

When conducting sentiment classification, a confusion matrix serves as a valuable tool

for understanding the algorithm’s accuracy in predicting different classes. It helps iden-
tify which classes are correctly predicted and any potential shortcomings in the classifier.
Figure 13 illustrates the confusion matrix generated through a two-layer convolutional neu-
ral network for classifying student feedback into positive, negative, and neutral categories.
Information 2024, 15, 277 24 of 30

Figure 13. Illustrating the performance of our trained models using a confusion matrix.

5. Discussion and Comparison

In this section, the proposed models are compared with other existing models in
terms of overall accuracy of learning style identification and sentiment classification. To
comprehensively assess the efficacy of the proposed model, firstly it is compared with two
established methodologies: convolutional neural network (CNN) and genetic algorithm.
The results, visualized in Figure 14 using bar plots, highlight the significant advantages of
the proposed model over the alternatives.

Figure 14. Comparative evaluation of the proposed model with other existing models. In this context,
(a–c) signify the performance metrics concerning accuracy, precision, and recall, respectively.

Secondly, the proposed approach’s accuracy is compared to other existing studies’

accuracy outcomes. Figure 15 demonstrates that the proposed model achieves a 95.12%
accuracy in identifying learning styles and it leads the pack by a significant margin, in-
dicating a nuanced understanding of individual learner preferences. The other models,
like the “Robust Fuzzy C-Means algorithm (RFCM)” [77], “Category Boosting (Catboost)”,
and “Extreme Gradient Boosting (XGBoost) [78]”, show commendable accuracies, all above
92%, but they are not quite as precise as the proposed model. Models with lower accura-
cies, like the “K-modes Naive Bayes Learning Styles (KM-NB-LS)” [79], “Adaptive Fuzzy
C-Mean model (AFCM)” [80], and “Self-Taught Semi-Supervised Learning (ST-SSL)” [81],
hover around 88–89%, which might suggest a less sensitive approach to the subtleties of
learning styles.
Information 2024, 15, 277 25 of 30

Figure 15. Proposed model vs. other models for learning style identification.

In the bar chart for sentiment analysis of learner feedback shown in Figure 16, the
proposed model’s top performance is consistent, registering an accuracy of 93.81%. This
suggests that the model is not only good at identifying patterns in data for categorization
but is also adept at interpreting the nuances of language—a key feature for analyzing
feedback. The “Weakly Supervised Long Short-Term Memory (WS-LSTM)” [82], which
is only slightly less accurate, also demonstrates strong sentiment analysis capabilities.
However, as we move down the list to models like the “Recommendation System Based on
Sentiment Analysis (RSBSA)” [83], “Enhanced e-Learning Hybrid Recommender System
(ELHRS)” [84], and “Bidirectional Long Short-Term Memory (BiLSTM)” [85], the drop in
accuracy becomes more pronounced, indicating potential challenges in fully capturing
learner sentiments, especially when dealing with subtle or complex expressions.
The time complexity graph shown in Figure 17 compares the proposed algorithm
against the FCM (Fuzzy C-Means) algorithm over different iteration counts. Although the
proposed algorithm takes longer to execute than the FCM algorithm, the time increase is
not as pronounced as the iteration count grows. For instance, at 200 iterations, the proposed
algorithm takes 1389 s compared to 2529 s for the FCM algorithm, demonstrating better
scalability. This demonstrates that the proposed algorithm is more efficient at handling
large-scale data, a desirable trait for e-learning systems that need to process information
from many users simultaneously.

Figure 16. Proposed model vs. other models for sentiment classification performance.
Information 2024, 15, 277 26 of 30

The time complexity graph shown in Figure 17 compares the proposed algorithm
against the FCM (Fuzzy C-Means) algorithm over different iteration counts.

Figure 17. Proposed model and FCM algorithm time complexity comparison.

Although the proposed algorithm takes longer to execute than the FCM algorithm,
the time increase is not as pronounced as the iteration count grows. For instance, at
200 iterations, the proposed algorithm takes 1389 s compared to 2529 s for the FCM
algorithm, demonstrating better scalability. This demonstrates that the proposed algorithm
is more efficient at handling large-scale data, a desirable trait for e-learning systems that
need to process information from many users simultaneously.

6. Conclusions and Future Work

This paper proposed a hybrid deep-learning approach to improve e-learning systems.
This involves two key components: automatic learning style identification and sentiment
analysis. The first experiment was carried out to demonstrate the reliability of the proposed
approach in determining the learning style. This approach selected an English course and
126 students to gather the data to find the learning style according to FSLSM dimensions
and the response data from students were categorized into eight FSLSM categories: verbal
sequential, visual, active, reflective, sensing, intuitive, and global. After 210 iterations,
the final clusters were obtained. Initially when student logged into to an LMS such as
Sup’Management Group, a free and open-source platform created to assist students and
educators in advancing their learning experiences, they filled in four questions aligned with
the dimensions of the FSLSM and the entirety of the 44-question Index of Learning Styles
(ILS) based on FSLSM, as well as basic information such as age and gender. We administered
a preliminary test as part of a tailored proposed approach to evaluate the students’ prior
academic achievements. Implementing fuzzy weights logic to analyze the test scores
helped in accurately determining each student’s level of knowledge. Secondly, from the
e-learning platform, we collected 1235 sequences that reflect the behaviors of learners,
with each student contributing between 1 and 35 sequences. This dataset includes the
demographic information of students and their prior academic scores, and their responses to
four key questions aligned with the FSLSM dimensions and 1235 learning sequences. These
elements serve as inputs for our designed Transformer architecture in combination with
GloVe (Global Vectors for Word Representation) word embeddings. The amalgamation of
these cutting-edge technologies allowed us to navigate the complexities of student learning
styles with precision and efficiency. The experiments demonstrate how the proposed
model accurately categorizes students into various learning styles based on (FSLSM) and
it is validated through a series of tests for accuracy, precision, recall, and F1 score. The
proposed novel approach achieved a learning style prediction accuracy of 95.54%, precision
Information 2024, 15, 277 27 of 30

of 95.54%, recall of 95.55%, and F1 score of 95.54%. The sentiment analysis further explores
student feedback using LDA for topic modeling. This approach effectively uncovers
key aspects and sentiments within the feedback, providing a nuanced understanding of
student opinions on different facets of the e-learning system. The performance of the
sentiment analysis was evaluated using a two-layer convolutional neural network (CNN),
which achieved a peak accuracy of 93.81%. In conclusion, the proposed hybrid deep
learning method revolutionizes e-learning by precisely tailoring content to individual
learning styles, enhancing student engagement and success. By analyzing sentiments, it
also offers valuable insights into student feedback, enabling continuous improvement. This
approach significantly boosts the effectiveness and accessibility of online education, directly
impacting students’ learning outcomes. In practice, it empowers educators to deliver more
personalized, responsive, and impactful e-learning experiences.
In the future, we aim to apply the proposed learning style identification across various
domains and among diverse age groups, including tertiary education students. Addition-
ally, we plan to develop an integrated LS model, combining the FSLSM model with other
cognitive frameworks. This will allow for a more comprehensive understanding of factors
influencing e-learning. The identification of these hybrid learning styles will be automated
through the use of advanced intelligent techniques. The proposed aspect sentiment anal-
ysis approach deals only with English language comments. However, in Pakistan, most
students use Roman Urdu in their feedback, so there is a significant opportunity to enhance
the system’s inclusivity and effectiveness. By incorporating the ability to process Roman
Urdu, future iterations of the proposed approach could delve deeper into understanding
the nuances of student feedback. Furthermore, students often employ a range of symbols
and emoticons to express their opinions in online feedback systems. Therefore, a critical
area of future research will involve examining how these visual elements correlate with the
sentiments being expressed. By systematically analyzing the weight and sentiment of each
attribute, future research aims to refine sentiment analysis techniques, thereby achieving
greater precision in classifying sentiments.

Author Contributions: Conceptualization, T.H., L.Y., M.A. and A.A.; methodology, T.H., L.Y., M.A.
and A.A.; software, T.H., L.Y. and M.A.; validation, L.Y., M.A. and M.A.W.; formal analysis, L.Y., M.A.
and M.A.W.; investigation, M.A. and M.A.W.; resources, L.Y. and M.A.W.; writing—original draft,
T.H.; writing—review and editing, L.Y., M.A., A.A. and M.A.W.; supervision, L.Y.; funding acquisition,
M.A. and M.A.W. All authors have read and agreed to the published version of the manuscript.
Funding: The authors would like to thank Prince Sultan University for paying the APC of this article.
Institutional Review Board Statement: Not applicable.
Informed Consent Statement: Not applicable.
Data Availability Statement: The data presented in this study are available on request from the
corresponding author.
Acknowledgments: This work was supported by EIAS Data Science Lab, College of Computer and
Information Sciences, Prince Sultan University. The authors would like to thanks Prince Sultan University
for their support.
Conflicts of Interest: The authors declare no conflicts of interest.

References
1. Imran, M.; Almusharraf, N.; Abdellatif, M.S.; Ghaffar, A. Teachers’ perspectives on effective English language teaching practices
at the elementary level: A phenomenological study. Heliyon 2024, 10, e29175. [CrossRef] [PubMed]
2. Farooq, U.; Naseem, S.; Mahmood, T.; Li, J.; Rehman, A.; Saba, T.; Mustafa, L. Transforming educational insights: Strategic
integration of federated learning for enhanced prediction of student learning outcomes. J. Supercomput. 2024, 1–34. [CrossRef]
3. Sivarajah, R.T.; Curci, N.E.; Johnson, E.M.; Lam, D.L.; Lee, J.T.; Richardson, M.L. A review of innovative teaching methods. Acad.
Radiol. 2019, 26, 101–113. [CrossRef] [PubMed]
4. Karagiannis, I.; Satratzemi, M. An adaptive mechanism for Moodle based on automatic detection of learning styles. Educ. Inf.
Technol. 2018, 23, 1331–1357. [CrossRef]
Information 2024, 15, 277 28 of 30

5. Granić, A. Educational technology adoption: A systematic review. Educ. Inf. Technol. 2022, 27, 9725–9744. [CrossRef] [PubMed]
6. Shoeibi, A.; Khodatars, M.; Jafari, M.; Ghassemi, N.; Sadeghi, D.; Moridian, P.; Khadem, A.; Alizadehsani, R.; Hussain, S.; Zare,
A.; et al. Automated detection and forecasting of COVID-19 using deep learning techniques: A review. Neurocomputing 2024,
577, 127317. [CrossRef]
7. Zhang, H.; Huang, T.; Liu, S.; Yin, H.; Li, J.; Yang, H.; Xia, Y. A learning style classification approach based on deep belief network
for large-scale online education. J. Cloud Comput. 2020, 9, 1–17. [CrossRef]
8. Muhammad, B.A.; Qi, C.; Wu, Z.; Ahmad, H.K. An evolving learning style detection approach for online education using
bipartite graph embedding. Appl. Soft Comput. 2024, 152, 111230. [CrossRef]
9. Graf, S. Adaptivity in Learning Management Systems Focussing on Learning Styles. Ph.D. Thesis, Technische Universität Wien,
Vienna , Austria, 2007. Available online: http://hdl.handle.net/20.500.12708/10843 (accessed on 27 March 2024).
10. Jalal, A.; Mahmood, M. Students’ behavior mining in e-learning environment using cognitive processes with information
technologies. Educ. Inf. Technol. 2019, 24, 2797–2821. [CrossRef]
11. Abdullah, M.A. Learning style classification based on student’s behavior in moodle learning management system. Trans. Mach.
Learn. Artif. Intell. 2015, 3, 28. [CrossRef]
12. Zatarain-Cabada, R.; Barrón-Estrada, M.L.; Angulo, V.P.; García, A.J.; García, C.A.R. A learning social network with recognition of
learning styles using neural networks. In Proceedings of the Advances in Pattern Recognition: Second Mexican Conference on Pattern
Recognition, MCPR 2010, Puebla, Mexico, 27–29 September 2010; Springer: Berlin/Heidelberg, Germany, 2010; pp. 199–209. [CrossRef]
13. García, P.; Amandi, A.; Schiaffino, S.; Campo, M. Evaluating Bayesian networks’ precision for detecting students’ learning styles.
Comput. Educ. 2007, 49, 794–808. [CrossRef]
14. Troussas, C.; Chrysafiadi, K.; Virvou, M. An intelligent adaptive fuzzy-based inference system for computer-assisted language
learning. Expert Syst. Appl. 2019, 127, 85–96. [CrossRef]
15. Crockett, K.; Latham, A.; Mclean, D.; O’Shea, J. A fuzzy model for predicting learning styles using behavioral cues in an
conversational intelligent tutoring system. In Proceedings of the 2013 IEEE International Conference on Fuzzy Systems
(FUZZ-IEEE), Hyderabad, India, 7–10 July 2013; IEEE: New York, NY, USA, 2013; pp. 1–8. [CrossRef]
16. Kolekar, S.V.; Pai, R.M.; MM, M.P. Prediction of Learner’s Profile Based on Learning Styles in Adaptive E-learning System. Int. J.
Emerg. Technol. Learn. 2017, 12, 31–51. [CrossRef]
17. Aziz, A.S.; El-Khoribi, R.A.; Taie, S.A. Adaptive E-learning recommendation model based on the knowledge level and learning
style. J. Theor. Appl. Inf. Technol. 2021, 99, 5241–5256.
18. Kaouni, M.; Lakrami, F.; Labouidya, O. The design of an adaptive E-learning model based on Artificial Intelligence for enhancing
online teaching. Int. J. Emerg. Technol. Learn. 2023, 18, 202. [CrossRef]
19. Madhavi, A.; Nagesh, A.; Govardhan, A. A framework for automatic detection of learning styles in e-learning. AIP Conf. Proc.
2024, 2802, 120012. [CrossRef]
20. Rashid, A.B.; Ikram, R.R.R.; Thamilarasan, Y.; Salahuddin, L.; Abd Yusof, N.F.; Rashid, Z.B. A Student Learning Style Auto-
Detection Model in a Learning Management System. Eng. Technol. Appl. Sci. Res. 2023, 13, 11000–11005. [CrossRef]
21. Essa, S.G.; Celik, T.; Human-Hendricks, N. Personalised adaptive learning technologies based on machine learning techniques to
identify learning styles: A systematic literature review. IEEE Access 2023, 11, 48392–48409. [CrossRef]
22. Alshmrany, S. Adaptive learning style prediction in e-learning environment using levy flight distribution based CNN model.
Clust. Comput. 2022, 25, 523–536. [CrossRef]
23. Raleiras, M.; Nabizadeh, A.H.; Costa, F.A. Automatic learning styles prediction: A survey of the State-of-the-Art (2006–2021).
J. Comput. Educ. 2022, 9, 587–679. [CrossRef]
24. Gomede, E.; Miranda de Barros, R.; de Souza Mendes, L. Use of deep multi-target prediction to identify learning styles. Appl. Sci.
2020, 10, 1756. [CrossRef]
25. Khan, F.A.; Akbar, A.; Altaf, M.; Tanoli, S.A.K.; Ahmad, A. Automatic student modelling for detection of learning styles and
affective states in web based learning management systems. IEEE Access 2019, 7, 128242–128262. [CrossRef]
26. Pashler, H.; McDaniel, M.; Rohrer, D.; Bjork, R. Learning styles: Concepts and evidence. Psychol. Sci. Public Interest 2008,
9, 105–119. [CrossRef] [PubMed]
27. Hauptman, H.; Cohen, A. The synergetic effect of learning styles on the interaction between virtual environments and the
enhancement of spatial thinking. Comput. Educ. 2011, 57, 2106–2117. [CrossRef]
28. Jegatha Deborah, L.; Baskaran, R.; Kannan, A. Learning styles assessment and theoretical origin in an E-learning scenario: A
survey. Artif. Intell. Rev. 2014, 42, 801–819. [CrossRef]
29. Choudhary, L.; Swami, S. Exploring the Landscape of Web Data Mining: An In-depth Research Analysis. Curr. J. Appl. Sci.
Technol. 2023, 42, 32–42. [CrossRef]
30. Roy, R.; Giduturi, A. Survey on pre-processing web log files in web usage mining. Int. J. Adv. Sci. Technol. 2019, 29, 682–691.
31. Fawzia Omer, A.; Mohammed, H.A.; Awadallah, M.A.; Khan, Z.; Abrar, S.U.; Shah, M.D. Big Data Mining Using K-Means and
DBSCAN Clustering Techniques. In Big Data Analytics and Computational Intelligence for Cybersecurity; Springer: Berlin/Heidelberg,
Germany, 2022; pp. 231–246. [CrossRef]
32. Nafea, S.M.; Siewe, F.; He, Y. On recommendation of learning objects using felder-silverman learning style model. IEEE Access
2019, 7, 163034–163048. [CrossRef]
Information 2024, 15, 277 29 of 30

33. Deng, Y.; Lu, D.; Chung, C.J.; Huang, D.; Zeng, Z. Personalized learning in a virtual hands-on lab platform for computer science
education. In Proceedings of the 2018 IEEE Frontiers in Education Conference (FIE), San Jose, CA, USA, 3–6 October 2018; IEEE:
New York, NY, USA, 2018; pp. 1–8. [CrossRef]
34. Hu, J.; Peng, Y.; Chen, X.; Yu, H. Differentiating the learning styles of college students in different disciplines in a college English
blended learning setting. PLoS ONE 2021, 16, e0251545. [CrossRef]
35. Hmedna, B.; El Mezouary, A.; Baz, O. How does learners’ prefer to process information in MOOCs? A data-driven study. Procedia
Comput. Sci. 2019, 148, 371–379. [CrossRef]
36. Reardon, M.; Derner, S. Strategies for Great Teaching: Maximize Learning Moments; Taylor & Francis: Abingdon, UK, 2023. [CrossRef]
37. Seghroucheni, Y.Z.; Chekour, M. How Learning Styles Can Withstand the Demands of Mobile Learning Environments? Int. J.
Interact. Mob. Technol. 2023, 17, 84–99. [CrossRef]
38. Othmane, Z.; Derouich, A.; Talbi, A. A comparative study of the Most influential learning styles used in adaptive educational
environments. Int. J. Adv. Comput. Sci. Appl. 2019, 10, 520–528.
39. Sihombing, J.H.; Laksitowening, K.A.; Darwiyanto, E. Personalized e-learning content based on felder-silverman learning style
model. In Proceedings of the 2020 8th International Conference on Information and Communication Technology (ICoICT),
Yogyakarta, Indonesia, 24–26 June 2020; IEEE: New York, NY, USA, 2020; pp. 1–6. [CrossRef]
40. Hidayat, N.; Wardoyo, R.; Sn, A.; Surjono, H.D. Enhanced performance of the automatic learning style detection model using a
combination of modified K-means algorithm and Naive Bayesian. Int. J. Adv. Comput. Sci. Appl. 2020, 11, 638–648. [CrossRef]
41. Staudemeyer, R.C. Applying long short-term memory recurrent neural networks to intrusion detection. S. Afr. Comput. J. 2015,
56, 136–154. [CrossRef]
42. Kumaravel, G.; Sankaranarayanan, S. PQPS: Prior-Art Query-Based Patent Summarizer Using RBM and Bi-LSTM. Mob. Inf. Syst.
2021, 2021, 1–19. [CrossRef]
43. Pamir; Javaid, N.; Javaid, S.; Asif, M.; Javed, M.U.; Yahaya, A.S.; Aslam, S. Synthetic theft attacks and long short term
memory-based preprocessing for electricity theft detection using gated recurrent unit. Energies 2022, 15, 2778. [CrossRef]
44. Saberi, N.; Montazer, G.A. A new approach for learners’ modeling in e-learning environment using LMS logs analysis. In
Proceedings of the 6th National and 3rd International Conference of E-Learning and E-Teaching, Tehran, Iran, 3–4 March 2012;
IEEE: New York, NY, USA, 2012; pp. 25–33. [CrossRef]
45. Graf, S.; Viola, S.R.; Leo, T.; Kinshuk. In-depth analysis of the Felder-Silverman learning style dimensions. J. Res. Technol. Educ.
2007, 40, 79–93. [CrossRef]
46. Prottasha, N.J.; Sami, A.A.; Kowsher, M.; Murad, S.A.; Bairagi, A.K.; Masud, M.; Baz, M. Transfer learning for sentiment analysis
using BERT based supervised fine-tuning. Sensors 2022, 22, 4157. [CrossRef] [PubMed]
47. Stevens-Smith, D.A. Brain-based teaching: Differentiation in teaching, learning, and motor skills. J. Phys. Educ. Recreat. Danc.
2020, 91, 34–42. [CrossRef]
48. Hall, A.H.; Gao, Q.; Guo, Y.; Xie, Y. Examining the effects of kindergarten writing instruction on emergent literacy skills: A
systematic review of the literature. Early Child Dev. Care 2023, 193, 334–346. [CrossRef]
49. Al-Maroof, R.S.; Alahbabi, N.M.N.; Akour, I.; Alhumaid, K.; Ayoubi, K.; Alnnaimi, M.; Thabit, S.; Alfaisal, R.; Aburayya, A.;
Salloum, S. Students’ perception towards behavioral intention of audio and video teaching styles: An acceptance study. Int. J.
Data Netw. Sci. 2022, 6, 603. [CrossRef]
50. Hakami, Z. Comparison between virtual and traditional learning methods for orthodontic knowledge and skills in dental
students: A Quasi-Experimental Study. Healthcare 2021, 9, 1092. [CrossRef] [PubMed]
51. Ariastuti, M.D.; Wahyudin, A.Y. Exploring academic performance and learning style of undergraduate students in English
Education program. J. Engl. Lang. Teach. Learn. 2022, 3, 67–73. [CrossRef]
52. Chen, J.; Zhang, Y.; Wei, Y.; Hu, J. Discrimination of the contextual features of top performers in scientific literacy using a machine
learning approach. Res. Sci. Educ. 2021, 51, 129–158. [CrossRef]
53. Saadat, M.; Bayat, M. Prediction of the unconfined compressive strength of stabilised soil by Adaptive Neuro Fuzzy Inference
System (ANFIS) and Non-Linear Regression (NLR). Geomech. Geoengin. 2022, 17, 80–91. [CrossRef]
54. Venkatesh, V.; Zhang, A.; Deakins, E.; Luthra, S.; Mangla, S. A fuzzy AHP-TOPSIS approach to supply partner selection in
continuous aid humanitarian supply chains. Ann. Oper. Res. 2019, 283, 1517–1550. [CrossRef]
55. Selva Birunda, S.; Kanniga Devi, R. A review on word embedding techniques for text classification. In Innovative Data
Communication Technologies and Application: Proceedings of ICIDCA 2020; Springer: Singapore, 2021; pp. 267–281. [CrossRef]
56. Yang, L.; Zhou, G. Dissecting The Analects: An NLP-based exploration of semantic similarities and differences across English
translations. Humanit. Soc. Sci. Commun. 2024, 11, 50. [CrossRef]
57. Pan, M.; Huang, J.X.; He, T.; Mao, Z.; Ying, Z.; Tu, X. A simple kernel co-occurrence-based enhancement for pseudo-relevance
feedback. J. Assoc. Inf. Sci. Technol. 2020, 71, 264–281. [CrossRef]
58. Vilar, E. Word embedding, neural networks and text classification: What is the state-of-the-art? J. Manag. Sci. 2019, 4, 35–62.
[CrossRef]
59. Ma, K.; Tan, Y.; Tian, M.; Xie, X.; Qiu, Q.; Li, S.; Wang, X. Extraction of temporal information from social media messages using
the BERT model. Earth Sci. Informatics 2022, 15, 573–584. [CrossRef]
60. Le, T.H.; Chen, H.; Babar, M.A. Deep learning for source code modeling and generation: Models, applications, and challenges.
ACM Comput. Surv. (CSUR) 2020, 53, 1–38. [CrossRef]
Information 2024, 15, 277 30 of 30

61. Garg, S.; Roy, D. A Birds Eye View on Knowledge Graph Embeddings, Software Libraries, Applications and Challenges. arXiv
2022, arXiv:2205.09088. [CrossRef].
62. Khaiser, F.K.; Saad, A.; Mason, C. Sentiment analysis of students’ feedback on institutional facilities using text-based classification
and natural language processing (NLP). J. Lang. Commun. 2023, 10, 101–111. [CrossRef]
63. Tabassum, A.; Patil, R.R. A survey on text pre-processing & feature extraction techniques in natural language processing. Int. Res.
J. Eng. Technol. 2020, 7, 4864–4867.
64. Dogra, V.; Verma, S.; Chatterjee, P.; Shafi, J.; Choi, J.; Ijaz, M.F. A complete process of text classification system using state-of-the-art
NLP models. Comput. Intell. Neurosci. 2022, 2022, 1883698. [CrossRef] [PubMed]
65. Bhattacharjee, A.; Karami, M.; Liu, H. Text transformations in contrastive self-supervised learning: A review. arXiv 2022,
arXiv:2203.12000. [CrossRef].
66. Egger, R.; Gokce, E. Natural Language Processing (NLP): An Introduction: Making Sense of Textual Data. In Applied Data Science in
Tourism: Interdisciplinary Approaches, Methodologies, and Applications; Springer: Berlin/Heidelberg, Germany, 2022; pp. 307–334. [CrossRef]
67. Altrabsheh, N.; Cocea, M.; Fallahkhair, S. Sentiment analysis: Towards a tool for analysing real-time students feedback. In Proceedings
of the 2014 IEEE 26th International Conference on Tools with Artificial Intelligence, Limassol, Cyprus, 10–12 November 2014; IEEE:
New York, NY, USA, 2014; pp. 419–423. [CrossRef]
68. Kalaivani, E.R.; Marivendan, E.R. The effect of stop word removal and stemming in datapreprocessing. Ann. Rom. Soc. Cell Biol.
2021, 25, 739–746.
69. Pramana, R.; Subroto, J.J.; Gunawan, A.A.S.; Anderies. Systematic literature review of stemming and lemmatization performance
for sentence similarity. In Proceedings of the 2022 IEEE 7th International Conference on Information Technology and Digital
Applications (ICITDA), Yogyakarta, Indonesia, 4–5 November 2022; IEEE: New York, NY, USA , 2022; pp. 1–6. [CrossRef]
70. Zhou, F.; Ayoub, J.; Xu, Q.; Jessie Yang, X. A machine learning approach to customer needs analysis for product ecosystems.
J. Mech. Des. 2020, 142, 011101. [CrossRef]
71. Xuan, T.Y.; Yahya, N.; Khan, Z.; Badruddin, N.; Yusoff, M.Z. EEG Motor Classification Using Multi-band Signal and Common Spa-
tial Filter. In Proceedings of the International Conference on Intelligent Human Computer Interaction, Daegu, Republic of Korea,
24–26 November 2020; Springer: Berlin/Heidelberg, Germany, 2020; pp. 120–131. [CrossRef]
72. Shams, H.; Jan, T.; Khalil, A.A.; Ahmad, N.; Munir, A.; Khalil, R.A. Fingerprint image enhancement using multiple filters. PeerJ
Comput. Sci. 2023, 9, e1183. [CrossRef]
73. Kumar, A.; Malik, A.; Batra, I.; Ahmad, N.; Johar, S. Digital society social interactions and trust analysis model. PeerJ Comput. Sci.
2022, 8, e1129. [CrossRef]
74. Novera, C.N.; Ahmed, Z.; Kushol, R.; Wanke, P.; Azad, M.A.K. Internet of Things (IoT) in smart tourism: A literature review.
Span. J. Mark. ESIC 2022, 26, 325–344. [CrossRef]
75. Khoo, C.S.; Johnkhan, S.B. Lexicon-based sentiment analysis: Comparative evaluation of six sentiment lexicons. J. Inf. Sci. 2018,
44, 491–511. [CrossRef]
76. Syed, S.; Spruit, M. Exploring symmetrical and asymmetrical Dirichlet priors for latent Dirichlet allocation. Int. J. Semant. Comput.
2018, 12, 399–423. [CrossRef]
77. Azzi, I.; Jeghal, A.; Radouane, A.; Yahyaouy, A.; Tairi, H. A robust classification to predict learning styles in adaptive E-learning
systems. Educ. Inf. Technol. 2020, 25, 437–448. [CrossRef]
78. Alruwais, N.; Zakariah, M. Student-Engagement Detection in Classroom Using Machine Learning Algorithm. Electronics 2023,
12, 731. [CrossRef]
79. El Aissaoui, O.; El Madani, Y.E.A.; Oughdir, L.; El Allioui, Y. Combining supervised and unsupervised machine learning
algorithms to predict the learners’ learning styles. Procedia Comput. Sci. 2019, 148, 87–96. [CrossRef]
80. Aziz, A.S.; El-Khoribi, R.A.; Taie, S.A. AFCM model to predict the learner style based on questionnaire and fuzzy C mean
algorithm. J. Theor. Appl. Inf. Technol. 2021, 99, 343–356.
81. Ayyoub, H.Y.; Al-Kadi, O.S. Learning Style Identification Using Semi-Supervised Self-Taught Labeling. IEEE Trans. Learn. Technol.
2024, 17, 1093–1106. [CrossRef]
82. Kastrati, Z.; Imran, A.S.; Kurti, A. Weakly supervised framework for aspect-based sentiment analysis on students’ reviews of
MOOCs. IEEE Access 2020, 8, 106799–106810. [CrossRef]
83. Alatrash, R.; Priyadarshini, R.; Ezaldeen, H.; Alhinnawi, A. Augmented language model with deep learning adaptation on
sentiment analysis for E-learning recommendation. Cogn. Syst. Res. 2022, 75, 53–69. [CrossRef]
84. Ezaldeen, H.; Misra, R.; Bisoy, S.K.; Alatrash, R.; Priyadarshini, R. A hybrid E-learning recommendation integrating adaptive
profiling and sentiment analysis. J. Web Semant. 2022, 72, 100700. [CrossRef]
85. Alzaid, M.; Fkih, F. Sentiment Analysis of Students’ Feedback on E-Learning Using a Hybrid Fuzzy Model. Appl. Sci. 2023,
13, 12956. [CrossRef]

Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual
author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to
people or property resulting from any ideas, methods, instructions or products referred to in the content.