Applied Artificial Intelligence

An International Journal

ISSN: (Print) (Online) Journal homepage: www.tandfonline.com/journals/uaai20

Dynamic Educational Recommender System Based

on Improved Recurrent Neural Networks Using
Attention Technique

Hadis Ahmadian Yazdi, Seyyed Javad Seyyed Mahdavi Chabok & Maryam
Kheirabadi

To cite this article: Hadis Ahmadian Yazdi, Seyyed Javad Seyyed Mahdavi Chabok & Maryam
Kheirabadi (2022) Dynamic Educational Recommender System Based on Improved Recurrent
Neural Networks Using Attention Technique, Applied Artificial Intelligence, 36:1, 2005298, DOI:
10.1080/08839514.2021.2005298

To link to this article: https://doi.org/10.1080/08839514.2021.2005298

© 2021 The Author(s). Published with

license by Taylor & Francis Group, LLC.

Published online: 11 Dec 2021.

Submit your article to this journal

Article views: 2330

View related articles

View Crossmark data

Citing articles: 5 View citing articles

Full Terms & Conditions of access and use can be found at

https://www.tandfonline.com/action/journalInformation?journalCode=uaai20
APPLIED ARTIFICIAL INTELLIGENCE
2022, VOL. 36, NO. 1, e2005298 (491 pages)
https://doi.org/10.1080/08839514.2021.2005298

Dynamic Educational Recommender System Based on

Improved Recurrent Neural Networks Using Attention
Technique
Hadis Ahmadian Yazdia, Seyyed Javad Seyyed Mahdavi Chabok b
,
and Maryam Kheirabadia
a
Department of Computer Engineering, Neyshabur Branch, Islamic Azad University, Neyshabur, Iran;
b
Department of Electrical Engineering, Mashhad Branch, Islamic Azad University, Mashhad, Iran

ABSTRACT ARTICLE HISTORY

Most web-based educational systems contain some draw­ Received 30 March 2021
backs, as compared to traditional classrooms. Particularly, it Revised 3 November 2021
becomes difficult for teachers to guide students to choose an Accepted 8 November 2021
appropriate learning resource due to the large number of
online learning resources. Meanwhile, student decisions
make it more difficult to choose educational resources accord­
ing to their circumstances. In this matter, the resource recom­
mender system can be employed as an educational
environment to recommend the educational resource advice
for students, so that these recommendations can be coordi­
nated to each student’s preferences and needs. This paper
presents the resource recommender system as a combination
of MLP, BiLSTM, and LSTM improved deep learning networks
using the attention method. Compared to similar studies
conducted using DBN networks and focus only on the near
past interests and preferences of users, the proposed system
provides higher accuracy and more appropriate recommenda­
tions considering current interests, in addition to the user’s
long-term past interests. The proposed recommender system
with accuracy of 0.96 and a loss of 0.0822 contains a better
performance to recommend resources to students compared
to other methods.

Introduction
Many years ago, the book was well known as the primary tool for education.
Today’s, however, the development of computers and the World Wide Web
and the increase in heterogeneous information has created a sense of the need
to design systems to generate the most meaningful recommendations, which
simplifies selection and activity processes. Recommender systems have
evolved over the past two decades (Adomavicius and Tuzhilin 2005;
Cremonesi et al. 2011). By becoming the Internet to a comprehensive medium
and the rapid growth of e-learning, users’ expectations of these systems have

CONTACT Seyyed Javad Seyyed Mahdavi Chabok [email protected] Department of Electrical

Engineering, Mashhad Branch, Islamic Azad University, Mashhad, Iran
© 2021 The Author(s). Published with license by Taylor & Francis Group, LLC.
This is an Open Access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/
licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly
cited.
 APPLIED ARTIFICIAL INTELLIGENCE e2005298-469

risen. In this regard, one of the advantages of these systems is the lack of space
and time constraints on educating. Traditional education systems are time-
consuming, as compared to modern education (Shishehchi et al. 2011).
Nevertheless, web-based systems also have some significant drawbacks, as
compared to traditional classrooms. For instance, there is no interaction
between the learner and the educator. Meanwhile, the presentation of content
and feedback is not personalized (Romero, Ventura, and García 2008). Besides, a
large number of resources in e-learning environments makes it difficult to make
the proper choice. Another point is that the student has individual differences
such as educational background, study method, age, etc. This requires us to get
feedback from students to better guide them in the educating process (Lu 2004).
Concerning such limitations, students in e-learning systems are eager for perso­
nalized services to monitor, support automatically, and evaluate student learn­
ing. Student loyalty also increases with personalized service (Huimin, Ming, and
Mingming 2010; Muthukumar and Bhalaji 2020).
So far, counseling systems, especially educational counseling, have been
studied with different techniques and methods. Most of these researches,
especially in the issue of educational recommenders, have tried to solve the
problem with linear forms and models and data mining such as ontology to
recommend scientific resources. (Bourkoukou and Achbarou 2018;
Bourkoukou and El Bachari 2018; Gulzar, Leema, and Deepak 2018; Qiao
and Hu 2018; Yago et al. 2018) One of the problems and limitations of these
methods is not accepting a large amount of information. Only a framework for
recommendation is introduced; there has not been much discussion about
a training advisor who automatically offers helpful advice. One of the newest
and most complete ways to solve the problem is to use deep learning networks.
Due to a large amount of problem data, neural network integration, learning
techniques, and structural dynamics informing several hidden layers, these
networks can solve problems with high accuracy and not encounter overfit
errors. (Alashkar et al. 2017; Chen et al. 2017b, 2017a; Hu et al. 2018; Wang
et al. 2018, 2017; Xu et al. 2017; Zheng, Noroozi, and Ph 2017) On the other
hand, in issues such as our problem that we are faced with a variety of areas
and parameters influencing decision-making, Deep learning networks are
more powerful than traditional methods.
Educational Recommender Systems (ERS) is utilized to assist students and
teachers during the learning process. Here, it is worth mentioning that the main
difference between ERS and their business counterparts is the appropriate
educational principles for both the learning and teaching process. This differ­
ence in the educational methods used in different academic conditions deter­
mines the primary guidelines for the ERS design. Based on this analysis, along
with educating and upgrading of existing algorithms, five specific areas are
introduced, in which the future research and development can be expected:
construction of universal ERS, ERS intended primarily for teachers, ERS that
e2005298-470 H. AHMADIAN YAZDI ET AL.

links student achievements across different courses, ERS which take into account
physical distance between students and use of ERS to motivate students to work
continuously. (Muthukumar and Bhalaji 2020; Zhang et al. 2018) The use of
recommenders when analyzing facts in the decision-making process is one of the
basic elements that many people apply during this process (Prem and Vikas
2010). The development and improvement of existing systems are one of the
current researches in the world. These developments are applied based on the
continuous evolution of statistical methods, machine learning, artificial intelli­
gence, data mining, and information retrieval (Prem and Vikas 2010;
Manouselis et al. 2012). This paper aims to design an Educational
Recommender System (ERS) that recommends the relevant resources to users
based on their interests and features in the relevant dataset. Indeed, our recom­
mender system contains individual features such as educational background,
age, and so on, including the individual’s interests in pre-clicked, the down­
loaded resources, and the user score given to each resource. Hence, such
a system must be educated to be able to recommend new resources to users.
if there is an inherent structure that the model can exploit, deep neural
networks are very efficient for this issue. For instance, both CNN and RNN
have long employed the internal structure of machine vision or natural
language. Because the nature of recommending textbooks depends on the
time and long-term review of student performance, the sequential structure
of sessions or report clicks is very appropriate for inferential errors in con­
ventional or recursive models. In many of these methods, the same weight is
considered in learning for all users’ interests, and only the user’s past informa­
tion is used in learning. While in the present article, having a network that
looks both backward and forwards can also cover changes in learner behavior
and offer more up-to-date recommendations.
In the following, the sources and descriptions are reviewed on the basic
methods on which ERS operates. Then, some examples of different ERS
classifications are provided according to their specific characteristics and
basic methods. In the next section, the proposed method is presented, which
is a combination of the architecture of MLP deep learning networks. In the
fourth section, the results of the implementation of the proposed algorithm
based on accuracy and efficiency are surveyed. Ultimately, some future sugges­
tions are provided in the fifth section.

Recommender Systems: A Review

In recommender systems, we encounter a set of users, options, and their
transactions in the system. Options are entities that are recommended to
users based on their content and user transaction with the system. These
recommendations are related to various decision-making processes, such as
buying an entity, listening to music, or reading online news. A recommender
 APPLIED ARTIFICIAL INTELLIGENCE e2005298-471

Figure 1. Types of recommender systems.

system usually focuses on a specific type of entity. For example, we can refer to
an article or news item to provide valuable and practical recommendations for
that particular type of entity. In recent years, research on recommender
systems has increased compared to other information systems and methods
(such as datasets with search engines) (Covington, Adams, and Sargin. 2016).
Nowadays, many recommender systems are running, which are based on
different approaches and methods. The methods are shown in Figure 1.

Deep Learning-based Methods

Currently, deep learning has revolutionized the structure of recommenders. It
has attracted the attention of many researchers by coping with many of the
barriers to traditional models and generating some quality recommendations.
Deep learning can receive non-linear user-item relationships and display
abstract representations of data at higher layers. Moreover, it can extract com­
plex relationships within conceptual, textual, and visual data (Zhang, Yao, and
Sun 2017). An example of a beautiful feature of neural networks and deep
learning is that they are end-to-end differentiable and provide suitable inductive
biases for the type of input data. As such, deep neural networks can combine
several neural building blocks into a differentiable function and educate end-to-
end. Here, the key advantage is when it comes to content-based recommenda­
tion systems. Multi-modal data is very common for user-item modeling on the
web. For instance, when working with textual data such as review data (Zheng,
Noroozi, and Yu2017), tweets (Gong and Zhang 2016), items, image data (social
posts, product images), CNN/RNNs become the main building blocks. Here, less
attention has been paid to the traditional solutions such as modality-specific
features, and as a result, the recommender system cannot take advantage of
video learning (Zhang et al. 2018).

Educational Recommender Systems (ERS)

Educational recommender systems are increasingly utilized as tools to assist
students and teachers in implementing the learning process (Muthukumar and
Bhalaji 2020; Zhang et al. 2018). Here, e-learning is one of the fields that its use is
e2005298-472 H. AHMADIAN YAZDI ET AL.

inevitable to improve the quality of education. E-learning is a form of education

provided using various electronic tools (Internet, intranet, extranet, satellite
networks, audio and videotapes, CDs). It is controlled in different ways (self-
directed/controlled by the educator), and its implementation is without geogra­
phical and time restrictions (simultaneous/asynchronous learning). Other terms
are used to describe this method of learning and educating, such as online
learning, virtual learning, distributed education, and web-based learning
(Mubarak, Cao, and Ahmed 2021; Tejeda-Lorente et al. 2015).

The Most Important Challenges in ERS

Despite the many improvements that recommendation systems have made,

these systems also encounter some challenges that can be summarized as
follows: Automatic information retrieve, cold start problem (user/new
items), highly specialized content, the lack of diversity in recommendations,
data scarcity problem, fraud problem, and critical mass problem (Zhang et al.
2018).
In the Automatic information retrieval problem, the main issue is that
today’s algorithms have limited ability to analyze the content of recommended
items automatically. Items with associated textual content (such as books, web
pages, etc.) are usually easily described (using different approaches for
Information retrieval from texts). The most developed algorithms are tailored
for analyzing textual content (Santos and Boticario 2011). They use keywords
and phrases that are found in the text and compare them with search para­
meters. With the higher correlation between these data, the likelihood that
a particular text can be recommended to the designated user is greater
(Adomavicius and Tuzhilin 2005).
The Cold-start (New User/Item) problem appears in situations when ERS
encounters a user or an item that could be recommended for the first time. In
such cases, the system does not have enough information about this user or the
item to prepare a meaningful recommendation (Al Mamunur, Karypis, and
Riedl 2008). Consequently, the system depends on the manually entered initial
parameters about the user or the items of recommendation provided by the
user or system administrator. Implicitly gathered information about the user,
which does not require the user’s cooperation, will give the system more
accurate information about the user’s interest, how the user uses the design,
what contents are recommended, etc. (Reddy, 2016). However, for implicit data
collection, the user must use the system for a certain period of time. in open
education surroundings there is a danger that, due to the lack of information
about the new items, they will not be treated like that by the system. In these
cases, ERS relies only on the available information about items that are in some
cases dependent on the other users of the plan (through ratings, etc.).
(Adomavicius and Tuzhilin 2005; Al Mamunur, Karypis, and Riedl 2008).
 APPLIED ARTIFICIAL INTELLIGENCE e2005298-473

Content overspecialization and non-diversity problem are pronounced

when the ERS only recommends items that score highly with the user’s profile.
In these cases, there is a risk that the user will only be recommended very
similar items. In ERS, this issue is more pronounced in open educational
environments that usually determine recommendations based on matching
the user’s profile and recommended items (Sunil and Saini 2013). In formal
education environments, teachers could rectify the system to ensure that
various items are recommended (in accordance with the objectives of the
course). On the other hand, in open education environments, the most
common approach for solving this problem is the introduction of a random
selection of content that will be recommended, taking into account that there
is a proper correlation between this content and the content the user is
interested in (Adomavicius and Tuzhilin 2005; Cremonesi et al. 2011).
The Sparsity and Gray Sheep problem usually appears when ERS depends
on the ratings of items by the system’s users or when the recommendation is
done based on grouping and comparing similar users. Suppose some items
that the system can recommend have been evaluated by a few users of these
items, regardless of their quality. In that case, they will not be widely recom­
mended to other users. In addition to the items’ content, the problem of
sparsity could appear among system users. The user who does not fit well in
any of the groups will not get good recommendations.
In formal educational environments, these problems can be solved through
interventions done by teachers. However, in open education environments, there
is a risk that they will remain unresolved (Adomavicius and Tuzhilin 2005).
Fraud problem in ERS is related to the data entered by the user. These data
could be basic data on/about the user’s profile or the data collected through
tests used for monitoring user advancement through the course. Although
fraud problems make no sense in open education environments, in formal
education environments where achievement in an assignment may have con­
sequences for the overall success of the user, there is a possibility of fraud. This
can happen when the user is not monitored during the use of the ERS.

Examples of Educational Recommender Systems

Today, many different ERSs are utilized. Their objective is to facilitate the
modernization of the educational process in both formal and open educational
environments. These systems are usually a combination of design and beha­
vior, methods, and strategies to create the recommendations. In this way, ERS
can be divided into systems that recommend educating, learning objects,
teamwork to implement joint activities, different educating methods through
learning cases based on the user’s unique preferences, or helping to create
e2005298-474 H. AHMADIAN YAZDI ET AL.

a personal learning path (PLP) (Zhang et al. 2018). Likewise, the ERS educat­
ing method recommends dividing users into methods in formal learning
environments and freely available methods on the World Wide Web.
Regarding the widespread use of web2.0 tools for e-learning, most ERSs
recommend a combination of these methods. Besides, some ERSs help tea­
chers to perform a part of student supervision (Tejeda-Lorente et al. 2015) or
find some ways to recommend the learning topics (Huang, Zeng, and Chen
2007; Mubarak, Cao, and Ahmed 2021). Sunita et al. (Aher and Lobo 2012)
recommend ERS courses available to students. Then, they developed their
recommender system based on the best combination of lessons available and
each user’s unique interests. In (Imran et al. 2016) developed their recom­
mender system of Personalized Learning Object Recommender System
(PLORS), which is an ERS in the LMS by various learning objects to persona­
lize the formal educational process, based on monitoring the activities of
previous students and then comparing them with other students and their
activities. In (El-Bishouty et al. 2014), they proposed an ERS model that helps
teachers proportion e-learning content to their students’ different learning
styles.
Moreover, the E-learning Activities Recommender System (ELARS) (Hoic-
Bozic, HolenkoDlab, and Mornar 2016) exploits visual, auditory, read/write,
mobile (VARK) descriptions (Fleming 1995), and learning styles as an essen­
tial element in a user profile. (Marian, Popescu, and Costel 2015) suggest the
use of ERS to help students find the groups who can help them solve
a particular problem in learning the content of a specific course. In several
different systems, the use of ERS to communicate with students has anon­
ymously been proposed.
In addition, one of the objectives of ELARS is to be able to recommend
when forming a group to work on a specific problem or on a particular project.
When this feature is added to the ERS, students usually have the freedom to
decide independently whether to accept recommendations and communicate
with appropriate colleagues or to ignore them (Zhang et al. 2018).
Determining a personal learning path is one of the objectives of a number of
ERSs. These systems employ different input parameters to define a unique
path of educational content for each user. China Ming et al. (Chin Ming, Chih
Ming, and Mei Hui 2005) arranged the syllabus in such a way that the system
utilizes the student’s incorrect answers to devise more learning paths so that
the user can obtain sufficient knowledge of the course content.
On the other hand, Lata et al. (Latha and Kirubakaran 2013) developed a
model of ERS that its algorithm employed the graph theory and knowledge of
different learning styles to recommend different PLPs for each user. In (Chin
Ming et al. 2007), each user’s basic knowledge level is compared to the complex­
ity of individual learning objects. According to the results of this comparison,
the ERS provides some recommendations for different learning paths. Besides,
 APPLIED ARTIFICIAL INTELLIGENCE e2005298-475

in (Onah and Sinclair 2015), the PLP building was designed based on
a comparison of the user profile and the aim of proper learning defined by
the user. The ERS monitors the user’s progress and changes the learning path to
ensure that all the required knowledge is acquired to succeed in further learning.
To obtain the better performance of the algorithms used in ERS, several
methods of artificial intelligence (fuzzy sets, artificial neural networks, evolution­
ary strategies) or their interactions are utilized (Zhang et al. 2018) In the papers of
(Tejeda-Lorente et al. 2015; Jamsandekar and Mudholkar 2013), they use fuzzy
inference methods to process data on student success with the aim of better
monitoring students’ progress through course content. Artificial neural networks
are considered to develop algorithms that are capable of self-learning based on
data from a given domain (Negnevitsky 2005), on the ERS of artificial neural
networks for complex modeling relationships between user profiles and their
interests (De Gemmis et al. 2009), as well as for modeling the relationship between
recommended objects and other parameters in the ERS to determine specific
recommendations that are unique for each user (Adomavicius and Tuzhilin 2005;
Jamsandekar and Mudholkar 2013) This method can obtain better overall results
in the same environment, as compared to cases where only one of these methods is
employed (Zhang et al. 2018). Some methods of artificial intelligence based on
evolutionary calculations include genetic algorithms, evolutionary strategies, and
genetic programming (Negnevitsky 2005). It should be noted that genetic algo­
rithms and various evolutionary strategies are commonly used in ERS (Zhang
et al. 2018). In (Sengupta, Sahu, and Dasgupta 2011), they used the Ant Colony
Optimization approach (an evolutionary algorithm) to identify system users’
effective and optimal learning paths. This system is exploited to access informa­
tion about unfamiliar terms that the user encounters during the learning process.
The paper (Chin Ming et al. 2007) utilized the genetic algorithm to create
a personal learning path for the user, while (Cayzer and Aickelin 2002) used the
biological immune system model to obtain a set of possible recommendations.

Proposed Method
This paper aims first to obtain a dataset of users, including their interest in the
resources under study and the extent to which they use and click on these
resources and related features. After that, the practical items from them are
chosen. In the second phase, using deep neural networks, we educate our
recommender system with acceptable accuracy, and finally, we recommend
resources to users using the educational network. The recommender algo­
rithm encompasses data extraction from OULAD data source files, data pre-
processing, construction of a deep learning network of MLP, LSTM, and
BiLSTM networks improved by Attention method, initialization of para­
meters, educating, and finally, educating point predicting. In our proposed
architecture, as illustrated in Figure 2, in each layer for each feature in the
e2005298-476 H. AHMADIAN YAZDI ET AL.

Figure 2. Proposed network architecture.

dataset, one BiLSTM cell and one LSTM cell are considered so that the cells are
focused on one feature of each record. Each cell considers only the pattern of
one feature. Finally, the total of these patterns leads to obtaining a better result.

Predicting Resource Scores

In the process of model educating, data labeled as class is considered as an

educating set to model educating. Then, according to the user-lesson attribute
vector, the recommendation problem becomes the category prediction pro­
blem. In this paper, using the label of rating classes, the loss information is
published to each layer from top to bottom by accurately tuning the observer’s
parameters. After educating the model to obtain a certain amount of loss, a set
test can be employed to test the performance of the recommender model. The
data in the set test is categorized into two classes: user-lesson attribute vector
and lesson assessment. Each user-lesson attribute vector corresponds to a
category level, while each level corresponds to a score. All lessons that corre­
spond to a user are sorted based on the expected scores, and then the lesson
recommendations are generated.
Using the Bilstm structure in the first layer due to its two-sided nature
focuses on short-term and long-term interests. In this architecture, two layers
of LSTM and Bilstm are siblings used to extract the general patterns in the total
database data. Finally, the output of these two layers is sent to the attention
layer. In this architecture, we have used the Seq weighted model of the
attention technique to reduce the useless features and side effects of noise
data; At the beginning of the proposed architecture classification step, the
Dense layer was used, and since the inputs of these layers are vectors, we used
the Flatten layer to convert the output of the higher layers into vectors. As you
can see in Figure 2, before the last layer, which is the softmax output and
 APPLIED ARTIFICIAL INTELLIGENCE e2005298-477

determines the probability of belonging to each class, dropout has been used to
use the secret aggregation, ensemble feature; Also, it prevents network over­
load and increases the generalization capability of the model.

Implementation

The volume of dataset data used is about 11 million data, which after elim­
inating those records via missing fields, finally remains 10543682 records
consisting of 12 features. It should be noted that this set of records is gathered
from the activities of 23326 different students. The implementation steps are
carried out in two parts: the first part contains the hybrid architecture (see
Figure 2) that refers to our idea in the paper. On the other hand, the second
part includes implementing several traditional methods and the deep learning
based on the DBN network related to the idea of the study of (Zhang et al.
2018), which developed scientific resources. In this article, we have used 3
divisions 70% – 30%, 80% – 20%, 90% – 10% to train and test our proposed
model, and for each case 3 values of 0.1, 0.2, 0.3 For validation split.(Table 7)
After the completion of the Epochs, the graphs and the results of the perfor­
mances show that the accuracy and loss of our work are far better than the
results of the implementation of the proposed network (Zhang et al. 2018; Lic.
Mar´ıa Emilia Charnelli et al.2019; Hui Chen et al. 2020; Rumei Li et al. 2019;
Lingyao Yan et al. 2021)

Dataset
Students generate a diversity of behavioral data by learning in an online
learning environment. This behavioral data is gathered and stored through
data collection methods (Kuzilek, Hlosta, and Zdrahal 2017). The
resources dataset provides data sources for this platform. This resources
dataset can be exploited to extract content features that reflect students’
interest in resources. The feature vectors of students are generated by
combining student features and lesson features. Afterward, the combina­
tion vectors of behavioral feature and user-lesson feature are created. The
dataset consists of 3 students, teachers, and lessons. It includes informa­
tion about 22 courses provided, 32,593 students, their assessment results,
and their interaction with the Virtual Learning Environment (VLE), which
is summarized by Students’ daily clicks on various “resources” (10,655,280
inputs) are provided. The dataset is anonymous using the ARX data
encryption tool [PK15]. The data is investigated for loss detection and
then confirmed and published by the Open Data Institute1.
OULAD is a sample subset of the collected student data, which contains
student demographics, student performance in the course assessment, and last
but not least, student behavior in the VLE. This resource provides a unique
dataset of student performance and prepares an opportunity to create new
e2005298-478 H. AHMADIAN YAZDI ET AL.

generations of learning management systems. Courses (called modules) with

a history of at least two successive presentations were chosen as the first stage.
This course covers the topic of learning and the set of sessions completed with
the test.
Module-presentation: represents the academic year so that the courses are
taught. After that, the data is converted and identified using a data
Anonymizer tool.

Dataset Plan
Figure 3 depicts the overall structure of the presented data set. This data set
generally represents students and then the course. The main table of
StudentInfo contains the student files that are linked to the courses (A student
can have more than a one registered course). Each course has several assess­
ments related to the student using the student assessment table, including the
history of the student assessment results.

● courses.csv: The file contains a list of all available and presented courses.
● assessments.csv: This file contains information about the assessments of
the presented courses. Usually, each course has a number of assessments
followed by a final exam.

There are three types of assessment: Teacher-Made Assessment (TMA),

Computer-Made Assessment (CMA), and Final Exam (Exam).

Data Description
● vle.csv: Contains information about the tool’s existence in the VLE. It is
usually HTML, pdf, etc., pages. Students have access to these resources
online, and their interactions with them are then recorded.
● studentInfo.csv: This information includes demographic information
about students and their results. Each student may have several rows.
Each row contains information about one student in the studied course,
including the following columns:
● studentRegistration.csv: This table encompasses information about the
student registration time to participate in the module. Besides, it is
recorded for students who have not registered the registration date.
● StudentAssessment.csv: This file contains student assessment results. If
the student does not submit an assessment, no result is recorded.
Meanwhile, if the assessments are not stored in the system, there will be
no final exams.
● studentVle.csv: it includes information about each student’s interaction
with resources in the VLE.
 APPLIED ARTIFICIAL INTELLIGENCE e2005298-479

Figure 3. Dataset structure of the data set (Kuzilek, Hlosta, and Zdrahal 2017).

Data Pre-processing
Figure 4 shows the pre-processing steps. The input consists of four sections:
provided resources, student features, held courses, and student performance
and assessment history in each course. These four sections are combined to
perform further analysis, categorization, feature mapping. Table 1 clearing
blank or mistake data, and feature normalization.
The features are normalized before implementing any work (the data range
is [0, 1]). To do so, Eq. (1) is utilized to perform the normalization as follows:
x xmin
x� ¼ (1)
xmax xmin
Where Xmin denotes the lowest eigenvalue, which is Xmin = min{X1, X2, . . .,
Xn}. Xmax denotes the maximum eigenvalue that is Xmax = max{X1, X2, . . .,
Xn}. X*indicates the normalized value, x means the primary data. Ultimately,
after pre-processing, the data is divided into an education set and a test set.

Records Labeling
The dataset is labeled after the initial stages of pre-processing as follows:
For each student from the set of registered activities for the joint courses, the
resource with the most clicks (which can indicate the student’s taste and interest)
in the course that had the highest grade (which can be the influence of the
e2005298-480 H. AHMADIAN YAZDI ET AL.

Figure 4. Data pre-processing steps.

resources studied in that course to show the student to be more successful) was
chosen as the label. Therefore, 562 labels were generated, which were mapped
from 0 to 561. The frequency of repetition of labels is illustrated in Figure 5.
In the end, after the pre-processing step, the data is divided into an educa­
tion set, a validation set, and a test set. The education set enters our proposed
network as input.

Network Construction
The current research was conducted on a Google Colab server. Here, it is
worthwhile to mention that Google Colab is a cloud service provided by
Google that allows Python programming, which prepares to install and work
with several Python language packages and deep learning frameworks such as
Tensorflow, Keras Pytorch, and more. In terms of this service, it provides
a free GPU to users, which has practically multiplied the efficiency of this
service. The service has been provided with an Nvidia Tesla P100 and 25.51GB
of RAM. Besides, both LSTM and Bidirectional Keras library have been used to
build the recommended network. After entering data into the network, the
data enters the Bidirectional layer with 1536 neurons. At the end of the output
of this layer, they enter the LSTM layer with 512 neurons, and at the end of the
output of this layer, they enter the Attention layer. In this implementation,
SeqWeightedAttention existence in the Keras library has been employed to
implement the attention technique.
Initialization of network parameters:
In the model educating process, we must repeatedly adjust the model
parameters to achieve better results in feature extraction. During the learning
process, the minibatch process method is exploited to solve the problem of
large data volumes. Besides, some parameters such as learning rate, number of
repetitions, and Bach-Size are set as follows:
Bach-size: 2048, Learning rate: 0.0001, Epoch: 120, Activation function:
Softmax
Table 1. Values of mapped features to numbers.
code_module AAA = 0.1 BBB = 0.2 CCC = 0.3 DDD = 0.4 EEE = 0.5 FFF = 0.6 GGG = 0.7
code_presentation 2013B = 540 2013 J = 720 2014B = 180 2014 J = 360 - - -
age_band 0–35 = 0.1 35–55 = 0.2 55≤ = 0.3 - - - -
highest_education A Level or Equivalent = 0.1 HE Qualification = 0.2 Lower Than A Level = 0.3 No Formal quals = 0.4 Post Graduate Qualification = 0.5 - -
final_result Distinction = 0.1 Fail = 0.2 Pass = 0.3 Withdrawn = 0.4 - - -
gender F = 0.1 M = 0.2 - - - - -
APPLIED ARTIFICIAL INTELLIGENCE
e2005298-481
e2005298-482 H. AHMADIAN YAZDI ET AL.

Figure 5. Frequency of repetition labels.

The higher the number of network parameters, the higher its computational
load in the network educating phase. In our proposed network, in the educat­
ing phase, the first val accuracy can be observed = 0.95 at epoch = 74 via
a minimum loss of 0.08 at epoch = 115. After completing the educating phase,
we entered the test data as input to the network, and then the obtained final
result was equal to 0.96 with one percentage of generalization.

Methods and Tools of Data Analysis

The recommender system developed in this paper aims to predict the best
sequence of educational resources. To do so, there are many criteria to
measure different aspects of recommending performance. Two essential cri­
teria, i.e., Mean Absolute Loss (MAE) and Root Mean Squared Loss (RMSE),
are utilized to measure the accuracy of the predicted scores (P) for each
educational resource relative to the correct scores (R).
Here, to assess the loss of the implemented methods, RMSE is employed.
Then both the accuracy and loss of our architecture are compared to ones of
the architecture of the study (Zhang et al. 2018), which contains a similar
application nature to our work (suggested by scientific sources). Table 7 and
Figure 6 exhibit the accuracy and loss of our network in the educating phase.

Result and Discussion

Investigate the Effect of the Number of Cells in Each Layer
As can be observed in Table 3, the results of single-cell structures in three
single-layer architecture, two layers, and three layers, are implemented and
then investigated, which are not desirable. An LSTM cell could not find well
the pattern of different features, the relationship of features to themselves, or
other features in combination, permutation, and additional models.
 APPLIED ARTIFICIAL INTELLIGENCE e2005298-483

Figure 6. Results of educating and testing of our proposed network(test-split = 0.3, split-valid
= 0.1).

As shown in Table 4, the single-layer multicellular architecture implemen­

ted in the single-layer two architectures of LSTM, the single-layer BiLSTM was
implemented and then investigated and obtained more favorable results.

Investigating the Effect of Using the Attention Mechanism

As mentioned before, the attention technique can filter out useless features from
raw inputs and decrease the side effects of noise data. By applying the attention
technique to the recommender systems, we can eliminate useless content and
choose the items via the most representation along with maintaining interpret­
ability. We added the attention technique to single-layer two architectures of
LSTM and BiLSTM. As can be observed in Table 5, the use of the attention
technique in network architecture has had a positive effect on the obtained results.

Investigating the Effect of the Number of Layers on Neural Network Structure

In deep learning network architecture, the first problem is the relationship of

LSTM cells to themselves, which was investigated in detail. The second problem
is the relationship between the different layers in the implemented architecture

Table 3. Results of educate and testing of LSTM networks (n, 1, 12).

accuracy test val_ accuracy accuracy val_loss loss train 1layer
0.28 0.2879 0.2825 2.6617 2.6907
accuracy test val_ accuracy accuracy val_loss loss train 2layer
0.18 0.1792 0.2607 3.3326 2.8305
accuracy test val_ accuracy accuracy val_loss loss train 3layer
0.25 0.2548 0.266 2.8369 2.8633

Table 4. Results of educating and testing of LSTM and BiLSTM networks (n, 12, 1).
accuracy test val_ accuracy accuracy val_loss loss train LSTM
0.79 0.7876 0.7696 0.5544 0.6194
accuracy test val_ accuracy accuracy val_loss loss train BiLSTM
0.70 0.7086 0.6868 1.0078 1.1137
e2005298-484 H. AHMADIAN YAZDI ET AL.

Table 5. Results of educating and testing of LSTM and BiLSTM network (n, 12, 1) and the attention
technique.
accuracy test val_ accuracy accuracy val_loss loss train LSTM & Attention Techniques
0.94 0.9366 0.9423 0.1254 0.1457
accuracy test val_ accuracy accuracy val_loss loss train BiLSTM & Attention Techniques
0.70 0.758 0.7458 0.6675 0.72223

that this part of the architecture performs the general understanding of the
features in the database. Here, to survey the effectiveness of the relationship
between the layers, we implemented and educated two-layer two architectures
LSTM and two-layer Gru. As shown in Table 6, the results of two-layer archi­
tectures are more favorable than those of single-layer architectures.
As the BiLSTM deep neural network considers both long-term and short-
term interests of the user, and due to their gradual learning natures, they
support learners’ behavioral changes. Hence, we implemented our proposed
two-layer architecture as a combination of the improved LSTM and BiLSTM
network using the attention technique. As can be seen in Table 7, the results of
our proposed architecture are very acceptable and desirable
According to Figure 6 considering the loss rate, it can be seen that the
number of selected epics is appropriate. Besides, according to the accuracy
diagram, it can be seen that as the val and val accuracy diagrams are almost the
same, so that overfitting does not occur in this experiment.

Investigating the Effect of Unconventional Data on Model Accuracy

As shown in Figure 5, we are faced with an unbalanced data set. In these cases,
in addition to the model’s accuracy, it is better to use other evaluation
parameters such as recall and F1 score. To ensure that the model has not

Table 6. Results of educating and testing of two-layer LSTM and GRU networks.
accuracy test val_ accuracy accuracy val_loss loss train LSTM
0.93 0.9265 0.911 0.1622 0.198
accuracy test val_ accuracy accuracy val_loss loss train GRU
0.94 0.9205 0.9066 0.1806 0.2175

Table 7. The result of proposed network in terms of train and test accuracy.
test train
accuracy val_ accuracy accuracy val_loss loss Split-valid Test-split
0.9664 0.9597 0.9511 0.0822 0.1055 0.1 30
0.9674 0.9564 0.9473 0.0909 0.1134 0.2
0.965 0.9581 0.949 0.087 0.1123 0.3
0.9684 0.965 0.9576 0.0704 0.0902 0.1 20
0.9593 0.9516 0.9438 0.102 0.1236 0.2
0.9631 0.9577 0.9484 0.0863 0.1125 0.3
0.964 0.9568 0.9574 0.088 0.1025 0.1 10
0.9611 0.9574 0.9468 0.0878 0.1145 0.2
0.9603 0.9567 0.9462 0.091 0.1175 0.3
 APPLIED ARTIFICIAL INTELLIGENCE e2005298-485

intelligently categorized all the data presented into a repetitive class in the
training process to achieve high accuracy. At the end of the test phase, for all
three parameters precision-recall f1-score, the average value is 96%. We
examined the classification accuracy of each group separately and found that
the data of all classes were very well categorized. To evaluate, we have trained
and tested our model with 3 different data sharing modes. In Table 8, as an
example, we have ten cases of the groups that had the lowest frequency of
repetition and ten cases of the groups that had the highest frequency of
repetition from the test results.
As you can see, in all three divisions of 30–70, 20–80 and 10–90 in the
groups with the value support = 1, the result of most recalls and f1-scores is
equal to 1. On the other hand, the number 1 obtained for recalls and f1-score is
very small in the groups with the most members. This shows that our model
has also met the unconventional data challenge in addition to the data volume
challenge.

Comparison of the Performance of the Proposed Model with Other Models

We have compared the suggested model results in the first row of Table 8 with
other methods presented in related work or implemented by ourselves. As can
be seen, the results are more desirable for different evaluation parameters of
the proposed model than other implemented methods. All evaluations were
performed on OULAD shared data.
The proposed method (Zhang et al. 2018) has been implemented and
trained, tested, and evaluated with OULAD data. As shown in Table 9, it
performed worse than our proposed model in terms of both error and
accuracy criteria. Five methods have been implemented and studied in (Lic.
Mar´ıa Emilia Charnelli et al., 2019). The results show that the SVD algorithm
with an error of 0.839 is more desirable than other schemes, which is several
times higher than the error of our proposed model.
In (Hui Chen et al. 2020), the three criteria, including Recall, Prec, and F1
for the three methods itemCF, Clustering + itemCF, and AROLS are exam­
ined. It shows that the proposed algorithm (AROLS) has a better Prec than the
other two cases. Meanwhile, F1 and Recalls remain relatively steady at n top
recommendation at the same time.
The work (Rumei Li et al. 2019) shows that AROLS performs much better
than traditional participatory filtering, especially User-AROLS calling and
accuracy, which has more than tripled. Also, the calling accuracy of UserCF
is much smaller than ItemCF, probably because UserCF focuses more on the
interests of learners who are more like a particular learner. At the same time,
the ItemCF recommendation is more personal because it primarily suggests
similar items based on the learner’s interest. As can be seen in the first row, the
proposed model performed better than all seven reviewed methods.
 e2005298-486

Table 8. Values of mapping properties given in numbers.

Train test split(test-size = 0.1) Train test split(test-size = 0.2) Train test split(test-size = 0.3)

support f1-score recall precision label support f1-score recall precision label support f1-score recall precision label
1 0.4 1 0.25 530 1 0.4 1 0.25 209 1 1 1 1 326 10 groups with the lowest frequency
1 1 1 1 498 1 1 1 1 228 1 1 1 1 418
1 1 1 1 453 1 1 1 1 547 1 1 1 1 463
2 0.02 0.5 0.01 477 1 0.4 1 0.25 228 1 0.4 1 0.25 391
2 1 1 1 305 1 1 1 1 90 2 1 1 1 446
H. AHMADIAN YAZDI ET AL.

2 1 1 1 460 2 1 1 1 184 2 0.4 1 0.25 442

3 1 1 1 213 3 1 1 1 133 2 0.01 0.5 0.01 171
3 1 1 1 503 3 1 1 1 391 3 1 1 1 408
3 0.02 0.5 0.01 411 3 1 1 1 326 3 1 1 1 547
3 1 1 1 103 4 1 1 1 557 3 1 1 1 550
82212 0.96 0.96 0.96 8 82212 0.96 0.96 0.97 1 86317 0.95 0.95 0.96 16 10 groups with the highest frequency
84858 0.99 0.99 0.99 34 84858 0.98 0.98 0.98 57 94754 0.98 0.98 0.99 20
99036 0.99 1 0.98 5 99036 0.98 0.99 0.98 60 112033 0.98 0.99 0.98 12
101120 0.98 0.99 0.98 28 101120 0.96 0.96 0.97 5 112418 0.99 1 0.99 46
111173 0.96 0.95 0.98 56 111173 0.97 0.97 0.98 11 131070 0.97 0.97 0.98 17
137559 0.98 0.99 0.98 13 137559 0.98 0.99 0.98 18 148366 0.98 0.99 0.98 1
165625 0.97 0.98 0.97 33 165625 0.98 0.98 0.99 16 154820 0.98 0.98 0.99 14
198928 0.98 0.98 0.99 49 198928 0.98 0.98 0.99 19 202925 0.98 0.98 0.98 34
262277 0.97 0.97 0.97 56 262277 0.96 0.96 0.97 26 249276 0.97 0.96 0.97 23
265671 0.98 0.98 0.98 12 265671 0.95 0.95 0.96 41 275379 0.98 0.97 0.98 30
 APPLIED ARTIFICIAL INTELLIGENCE e2005298-487

Table 9. Comparison of the proposed method with other methods.

Model Accuracy RMSE Recall Prec. F1 ref
proposed model 0.959 0.08 - - - Implemented by us
train
test 0.96 - 0.96 0.96 0.96
Naive Bayes(nb) 0.1981 - 0.4725 0.2937 0.1853
Logistic Regression(Lr) 0 - 0 0 0
Latent Dirichlet Allocation 0.5415 - 0.0772 0.4314 0.4579
(lda)
DBN 0.2912 0.225 - - - (Zhang et al. 2018)
KNN Baseline (item-item) - 0.915 - - - (Lic. Mar´ıa Emilia Charnelli
KNN Baseline (user-user) - 0.908 - - - et al.2019)
KNN Means (item-item) - 0.898 - - -
KNN Means (user-user) - 0.944 - - -
SVD - 0.839 - - -
AROLS - - 0.022 0.28 0.04 (Hui Chen et al. 2020)
itemCF - - 0.018 0.18 0.027
Clustering + itemCF - - 0.024 0.24 0.041
ItemCF - - 0.026 0.1334 0.0435 (Rumei Li et al. 2019)
Item-AROLS - - 0.0406 0.1880 0.0668
User-AROLS - - 0.0018 0.0046 0.0026
UserCF - - 0.0005 0.0011 0.0007
CF with ARM - - 0.6874 0.076 0.1374 (Lingyao Yan et al. 2021)
The proposed method - - 0.8647 0.1033 0.1842

In (Lingyao Yan et al. 2021), the results show that OLS characters can make
the recommendation algorithm more accurate and robust, but as seen in the
first row, the proposed model performed better than both studied methods.

Conclusion and Future Works

Today’s ERSs do not usually include the designed mechanisms to assist
teachers in decreasing their workload. Such systems are more focused on the
needs of students. Regarding the work proposed by (Bhojak, Jain, and
Muralidharan 2012), some internal algorithms are designed to assist teachers.
Overall, the data collected by the ERS can noticeably be employed to help
teachers (Zhang et al. 2018). Because of this diversity, the developed systems
for one environment may not efficiently be utilized (without a significant
change in how they work) in a different learning environment. Currently,
the employed systems are specialized for one of these two learning environ­
ments. Indeed, a range of future research and development will construct ERSs
that can work appropriately with minimal changes in both environments. By
introducing the Bologna process in higher education, particularly in contin­
uous monitoring and evaluation of student work, the amount of teacher work
has significantly increased (Zhang et al. 2018). Regarding the lack of functional
understanding, one area of further ERS research and development will cer­
tainly focus on teacher support, especially in formal learning environments.
Systems should take teachers’ workload completely, especially when we need
the continuous monitoring and evaluation of student work during the semester.
Although in terms of education, some algorithms developed for the ERS and
e2005298-488 H. AHMADIAN YAZDI ET AL.

investigated in one course could be employed without any modification in

another course (algorithms are not dependent on the content education).
Generally, systems do not create any link in the student achievement to different
courses. In fact, considering that the education programs based on learning
outcomes and obtaining the general and specific qualifications are predefined,
the obtained results in one course can be considered to provide recommenda­
tions in another course (Zhang et al. 2018). The differences existed between the
different study methods that are suitable for use in other areas, requiring the
system’s flexibility to satisfy the needs of all users. Concerning these differences,
the ERS model can be designed and built to provide some satisfactory services to
the students and teachers who utilize them. The areas for the future development
of ERS confirm that there are still numerous opportunities for further scientific
advancement in the field of ERS (Zhang et al. 2018).

Disclosure Statement
No potential conflict of interest was reported by the author(s).

ORCID
Seyyed Javad Seyyed Mahdavi Chabok http://orcid.org/0000-0003-1856-4579

References
Adomavicius, G., and A. Tuzhilin. 2005. Toward the next generation of recommender systems:
A survey of the state-of-the-art and possible extensions. IEEE Transactions on Knowledge
and Data Engineering 17 (6):734–49. doi:10.1109/TKDE.2005.99.
Aher, S. B., and L. M. R. J. Lobo. 2012. Course recommender system in E-learning.
International Journal of Computer Science and Communication 3 (1):159–64.
Al Mamunur, R., G. Karypis, and J. Riedl. 2008. Learning preferences of new users in
recommender systems: An information theoretic approach. ACM SIGKDD Explorations
Newsletter Journal 10 (2):90–100. doi:10.1145/1540276.1540302.
Alashkar, T., S. Jiang, S. Wang, and Y. Fu (2017, February). Examples-rules guided deep neural
network for makeup recommendation. In Proceedings of the AAAI Conference on Artificial
Intelligence (Vol. 31, No. 1).
Bernhard, T. J. (1997). Challenges and strategies for electrical engineering education. In 27th
Annual Conference Frontiers in Education: Teaching and Learning in an Era of Change (pp.
1459–1462). Pittsburg, Pennsylvania, USA. doi:10.1109/FIE.1997.632708.
Bhojak, H., S. Jain, and V. Muralidharan (2012). Instructor guided personalization of
learningpath-adopting SCORM. In 4th International Congress on Engineering
Education – ImprovingEngineering Education: Towards Sustainable Development.
New York, USA. doi:10.1109/ICEED.2012.6779280.
Bourkoukou, O., and E. El Bachari. 2018. Toward a hybrid recommender system for e-learning
personnalization based on data mining techniques. JOIV: International Journal on
Informatics Visualization 2 (4):271–78. doi:10.30630/joiv.2.4.158.
 APPLIED ARTIFICIAL INTELLIGENCE e2005298-489

Bourkoukou, O., and O. Achbarou. 2018. Weighting based approach for learning resources
recommendations. JOIV: International Journal on Informatics Visualization 2 (3):104–09.
doi:10.30630/joiv.2.3.124.
Cayzer, S., and U. Aickelin (2002). A Recommender System based on the Immune Network.In
Congress on Evolutionary Computation CEC2002, (pp. 807–813), Honolulu, USA.
doi:10.1109/CEC.2002.1007029.
Chen, C., P. Zhao, L. Li, J. Zhou, X. Li, and M. Qiu (2017a, April). Locally connected deep
learning framework for industrial-scale recommender systems. In Proceedings of the 26th
international conference on World Wide Web companion (pp. 769–770).
Chen, J., H. Zhang, X. He, L. Nie, W. Liu, and T. S. Chua (2017b, August). Attentive
collaborative filtering: Multimedia recommendation with item-and component-level
attention. In Proceedings of the 40th International ACM SIGIR conference on Research
and Development in Information Retrieval (pp. 335–344).
Chin Ming, H., C. Chih Ming, and C. Mei Hui (2005). Personalized Learning Path Generation
Approach for Web-based Learning. In 4th WSEAS International Conference on E-activities
(pp. 62–68). Miami, Florida, USA.
Chin Ming, H., C. Chih Ming, C. Mei Hui, and C. Shin Chia (2007). Intelligent web-basedtutoring
system with personalized learning path guidance. In 7th IEEE InternationalConference on
Advanced Learning Technologies, ICALT 2007 (pp. 512–516). Nigata, Japan.
Covington, P., J. Adams, and E. Sargin. (2016). Deep neural networks for youtube
recommendations. In Recsys. 191–98.
Cremonesi, P., F. Garzotto, S. Negro, A. V. Papadopoulos, and R. Turrin (2011). Looking for
good Recommendations: A comparative Evaluation of Recommender Systems. In
P. Campos, N. Graham, J. Jorge, N. Nunes, P. Palanque, and M. Winckler (Eds.), 13th
IFIP TC 13 International Conference INTERACT,2011,(pp. 152–168).Lisbon, Portugal.
doi:10.1007/978-3-642-23765-2_11.
De Gemmis, M., Iaquinta, L., Lops, P., Musto, C., Narducci, F., and Semeraro, G. (2009).
Preference learning in recommender systems. Preference Learning, 41, 41-55.
El-Bishouty, M. M., T. W. Chang, S. Graf, and N. S. Chen. 2014. Smart e-course recommender
based on learning styles. Journal of Computers in Education 1 (1):99–111. doi:10.1007/
s40692-014-0003-0.
Fleming, N. D. (1995, July). I’m different; not dumb. Modes of presentation (VARK) in the
tertiary classroom. In Research and development in higher education, Proceedings of the
1995 Annual Conference of the Higher Education and Research Development Society of
Australasia (HERDSA), HERDSA (Vol. 18, pp. 308–313).
Gallego, D. L., E. Barra, A. Gordillo, and G. Huecas (2013).Enhanced recommendationsfor
e-learning authoring tools based on a proactive context-aware recommender. In IEEE
Frontiers in Education Conference (pp. 1393–1395). Oklahoma City, USA.doi:10.1109/
FIE.2013.6685060.
Gong, Y., and Q. Zhang (2016). Hashtag recommendation using attention-based convolutional
neural network. In IJCAI, 2782–88.
Gulzar, Z., A. A. Leema, and G. Deepak. 2018. Pcrs: Personalized course recommender system
based on hybrid approach. Procedia Computer Science 125:518–24. doi:10.1016/j.
procs.2017.12.067.
Hidasi, B., A. Karatzoglou, L. Baltrunas, and D. Tikk (2016). Session-based recommendations
with recurrent neural networks. In Proceedings of the International Conference on Learning
Representations, San Juan, Puerto Rico, 2–4 May 2016, 1–10.
Hoic-Bozic, N., M. HolenkoDlab, and V. Mornar. 2016. Recommender system and web 2.0
Tools to enhance a blended learning model. IEEE Transactions on Education 59 (1):39–44.
doi:10.1109/TE.2015.2427116.
e2005298-490 H. AHMADIAN YAZDI ET AL.

Hu, B., C. Shi, W. X. Zhao, and P. S. Yu (2018, July). Leveraging meta-path based context for
top-n recommendation with a neural co-attention model. In Proceedings of the 24th ACM
SIGKDD International Conference on Knowledge Discovery & Data Mining (pp. 1531–40).
Huang, Z., D. Zeng, and H. Chen. 2007. A comparison of collaborative-filtering recommenda­
tion algorithms for ecommerce. IEEE Intelligent Systems 22 (5):5. doi:10.1109/
MIS.2007.4338497.
Huimin, Q., C. Ming, and X. Mingming (2010, May). A personalized resource recommenda­
tion system using data mining. In 2010 International Conference on E-Business and
E-Government (pp. 5365–5368). IEEE.
Imran, H., M. Belghis-Zadeh, T. W. Chang, and S. Graf. 2016. PLORS: A personalized learning
object recommender system. Vietnam Journal of Computer Science 3 (1):3–13. doi:10.1007/
s40595-015-0049-6.
Kuzilek, J., M. Hlosta, and Z. Zdrahal, Open university learning analytics dataset, https://www.
kaggle.com/vjcalling/oulad-open-university-learning-analytics-dataset
Latha, C. B. C., and E. Kirubakaran. 2013. Personalized learning path delivery in webbased
educational systems using a graph theory based approach. Journal of American Science
9 (12):981–92.
Lu, J., A personalized e-learning material recommender system, Macquarie Scientific
Publishing, pp. 374–379, 2004.
Manouselis, N., H. Drachsler, K. Verbert, and E. Duval. 2012. Recommender Systems for
Learning. Springer Science & Business Media.
Marian, C. M., P. S. Popescu, and I. Costel (2015). Intelligent tutor recommender system for
on-line educational environments. In 8th International Conference on Educational Data
Mining (pp. 516–519). Madrid, Spain.
Mubarak, A. A., H. Cao, and S. A. Ahmed. 2021. Predictive learning analytics using deep
learning model in MOOCs’ courses videos. Education and Information Technologies
26 (1):371–92. doi:10.1007/s10639-020-10273-6.
Muthukumar, V., and N. Bhalaji. 2020. MOOCVERSITY-deep learning based dropout predic­
tion in MOOCs over weeks. Journal of Soft Computing Paradigm (JSCP) 2 (3):140–52.
doi:10.36548/jscp.2020.3.001.
Negnevitsky, M. 2005. Artificial intelligence – A Guide to Intelligent Systems. London: Addison-
Wesley, Pearson Education Ltd.
Onah, D. F., and J. E. Sinclair (2015, March). Massive open online courses: An adaptive
learning framework. In Proceedings of the 9th International Conference on Technology,
Education and Development (pp. 1258–1266).
Qiao, C., and X. Hu (2018, July). Discovering student behavior patterns from event logs:
Preliminary results on a novel probabilistic latent variable model. In 2018 ieee 18th inter­
national conference on advanced learning technologies (ICALT) (pp. 207–211). IEEE.
Romero, C., S. Ventura, and E. García. 2008. Data mining in course management systems:
Moodle case study and tutorial. Computers & Education 51 (1):368–84. doi:10.1016/j.
compedu.2007.05.016.
Santos, C. O., and G. J. Boticario. 2011. Requirements for semantic educational recommender
systems in formal e-learning scenarios. Open Access Journal: Algorithms 4 (1):131–54.
doi:10.3390/a4030131.
Sengupta, S., S. Sahu, and R. Dasgupta. 2011. Construction of learning path using ant colony
optimization from a frequent pattern graph. International Journal of ComputerScience
8 (6):314–21.
Shishehchi, S., S. Y. Banihashem, N. A. M. Zin, and S. A. M. Noah (2011, June). Review of
personalized recommendation techniques for learners in e-learning systems. In 2011 inter­
national conference on semantic technology and information retrieval (pp. 277–281). IEEE.
 APPLIED ARTIFICIAL INTELLIGENCE e2005298-491

Sunil, L., and D. Saini (2013). Design of a Recommender System for Web Based Learning. In
World Congress on Engineering WCE2013 (pp. 3–8). London, England.
Tejeda-Lorente, A., J. Bernabe-Moreno, C. Porcel, P. Galindo-Moreno, and E. Herrera-
Viedma. 2015. A dynamic recommender system as reinforcement for personalized educa­
tion by a fuzzy linguistic web system. Elsevier - Procedia ComputerScience 55 (1):1143–50.
doi:10.1016/j.procs.2015.07.084.
Wang, J., L. Yu, W. Zhang, Y. Gong, Y. Xu, B. Wang, . . . D. Zhang (2017, August). Irgan:
A minimax game for unifying generative and discriminative information retrieval models.
In Proceedings of the 40th International ACM SIGIR conference on Research and
Development in Information Retrieval (pp. 515–24).
Wang, Q., H. Yin, Z. Hu, D. Lian, H. Wang, and Z. Huang (2018, July). Neural memory
streaming recommender networks with adversarial training. In Proceedings of the 24th
ACM SIGKDD International Conference on Knowledge Discovery & Data Mining (pp.
2467–75).
Xu, Z., T. Lukasiewicz, C. Chen, Y. Miao, and X. Meng (2017, August). Tag-aware personalized
recommendation using a hybrid deep model. AAAI Press/International Joint Conferences
on Artificial Intelligence.
Yago, H., J. Clemente, D. Rodriguez, and P. Fernandez-de-cordoba. 2018. On-smmile:
Ontology network-based student model for multiple learning environments. Data &
Knowledge Engineering 115:48–67. doi:10.1016/j.datak.2018.02.002.
Zhang, H., T. Huang, L. V. Zhihan, S. Liu, and H. Yang. (2018). MOOCRC: A highly accurate
resource Recommendation model for use in MOOC environments. Springer, Mobile
Networks and Applications.
Zhang, S., L. Yao, and A. Sun (2017). Deep learning based recommender system: A survey and
new perspectives. arXiv, arXiv:1707.07435.
Zheng, L., V. Noroozi, and Y. Ph. (2017). Joint deep modeling of users and items using reviews
for recommendation. In WSDM.