PROJECT SYNOPSIS

On

Campus Enquiry Chatbot

Submitted for Partial Fulfilment of Award of
BACHELOR OF TECHNOLOGY
In
Artificial Intelligence and Machine Learning
(2025)
By
Harsh Deshmukh(Roll No: 2101221640022)
Jaskaran Singh (Roll No: 2101221640030)

Under the Guidance

of
Dr. Sadhana Rana

SHRI RAMSWAROOP MEMORIAL COLLEGE

OF
ENGINEERING & MANAGEMENT, LUCKNOW
Affiliated to

DR. APJ ABDUL KALAM TECHNICAL

UNIVERSITY, LUCKNOW
TABLE OF CONTENTS
 Campus Enquiry Chatbot

CHAPTER 1……………………………………………………....................3-4
1. INTRODUCTION……………………………………………………..3-4
CHAPTER 2………………………. …………………………………...……5-7
2. LITERATURE REVIEW...……………………………………………5-7
2.1 EARLY APPROACHES (PRE AI ERA)
……………………………..5
2.2 AI BASED APPROACHES…………….
………………………….....6
2.3 ADVANCES NLP & CONVERSATIONAL
AGENTS……............ ..7
CHAPTER 3……………………………………………………………..….8-12
3. PROBLEM DEFINITION ..………………………………….......…..8-12
3.1 PROJECT OBJECTIVE…………………………………………..…..9
3.2 PROPOSED METHODOLOGY…………………………………10-12
CHAPTER 4……………………………………………………………….13-14
4. TECHNOLOGIES USED…………………………………………...13-14
4.1 Python……………………………………………………………….13
4.2 Natural Language Processing (NLP)…………………………...…...13
4.3 Flask…………………………………………………………....……14
4.4 HTML/CSS/JavaScript……………………………………………...14
CHAPTER 5……………………………………………………………….15-18
5. IMPLEMENTATION ALGORITHM ……………………..…15-18
5.1 PRE-REQUISTES……………………………………………..15
5.2 DATA STRUCTURE………………………………………….15
5.3 RUNNING THE
SERVER…………………………………….15
5.4 CODE FOR QUICK SUMMARY……………….……..….16-18
CHAPTER 6………………………………………………………. ……...19-20
6. DIAGRAMMATIC SCHEMA…………………………..……19-20
CHAPTER 7……………………………………………………………..……21
7. S/W & H/W REQUIREMENTS………………………………….21
CHAPTER8..………………………………………………………............22-23

CSE Department, SRMCEM, Lucknow

 Campus Enquiry Chatbot

8. CONCLUSION………………………………………………..22-23
REFERNCES 24

CHAPTER 1
INTRODUCTION

In an era of digital advancements, chatbots have emerged as valuable tools for

enhancing communication and delivering instant information. Colleges and
universities recognize the need to provide quick and accurate responses to
queries from students, parents, and prospective applicants. To address this
demand, this project focuses on the development of a college enquiry chatbot—
a conversational agent capable of answering a wide range of questions related to
admissions, academic programs, campus life, financial aid, and student support
services. The primary objective of this project is to create a user-friendly
chatbot with an intuitive interface that accommodates both text-based and voice-
based interactions. Leveraging natural language processing capabilities, the
chatbot will comprehend and interpret user input, enabling a seamless
conversational experience. By leveraging a comprehensive knowledge base, the
chatbot
will provide prompt and precise responses to common enquiries while also gene
rating dynamicresponses when confronted with unique or specific queries.
Beyond academics, the chatbot will also serve as a gateway to understanding
campus life. It will offer information on student organizations, events, and
facilities, facilitating an enriched college experience. Additionally, the chatbot
will cater to queries regarding financial aid, shedding light on available options
and guiding users through the application process. Throughout the development
process, rigorous testing and continuous user feedback will be integral to fine-
tuning the chatbot. Beta testing with a diverse sample of users will provide
valuable insights into the chatbot's performance and us ability. By implementing
the college enquiry chatbot, colleges and universities can streamline their
communication channels and improve their responsiveness to inquiries. This
project endeavors to leverage the power of chatbot technology to offer a

CSE Department, SRMCEM, Lucknow

 Campus Enquiry Chatbot

convenient and accessible means of accessing information about a college. The

ultimate goal is to enhance the user experience and foster effective
communication between educational institutions and their stakeholder.
Colleges and universities face the challenge of efficiently and effectively
providing accurate information to students, parents, and prospective applicants
who have a multitude of questions regarding admissions, academic programs,
campus life, financial aid, and student support services. The traditional methods
of information dissemination, such as websites or manual inquiry handling,
often result in delayed responses, limited availability, and overwhelming staff
workloads. As a result, there is a need to develop a solution that can address
these issues and improve the overall experience for individuals seeking
information about the college.
The problem at hand is the absence of a comprehensive and readily accessible
platform that can cater to the diverse queries of college-related topics. Without a
dedicated system in place, individuals may struggle to find accurate and up-to-
date information, leading to frustration, confusion, and potential disengagement
with the college. Additionally, the lack of a streamlined communication channel
hinders colleges' ability to efficiently address inquiries, resulting in wasted
resources and missed opportunities to engage with prospective students.
In light of these challenges, the development of a college enquiry chatbot
emerges as a viable solution. By leveraging advancements in natural language
processing and artificial intelligence, a chatbot can serve as a virtual assistant,
capable of understanding user queries, accessing relevant information, and
delivering prompt, accurate, and personalized responses. Such a chatbot would
alleviate the burden on staff, improve response times, enhance accessibility, and
ensure consistent and reliable information dissemination to users.

CSE Department, SRMCEM, Lucknow

 Campus Enquiry Chatbot

CHAPTER 2
LITERATURE REVIEW

2.1 Early APPROACHES (PRE-AI Era)

The initial implementations of campus enquiry chatbots were largely
rule-based systems. These systems operated on predefined sets of rules
and relied heavily on pattern matching or keyword-based approaches to
generate responses. While effective for answering frequently asked
questions, these systems lacked flexibility and could not adapt to
complex or ambiguous queries, limiting their overall usefulness.
 Weizenbaum (1966)[1] introduced "ELIZA," a pioneering rule-based
chatbot that used simple pattern matching to simulate conversations.
Though ELIZA was not originally designed for educational purposes, its
architecture demonstrated that a machine could follow structured scripts
to mimic human dialogue. This approach was adopted by early campus
enquiry systems, which provided responses to common questions like
“What are the library hours?” or “When is the next exam?” through
predefined responses triggered by specific keywords.
 Colace et al. (2018) [2] designed a basic rule-based chatbot for
university environments, which primarily answered FAQs about campus
logistics and administrative details. Their model relied on pre-
programmed responses and could not interpret variations in user queries,
leading to limited conversational flexibility. However, it proved
effective for routine queries, reporting a response accuracy of around
80% for questions that closely matched predefined rules. This model
highlighted the utility of chatbots for automating simple administrative
tasks but also pointed to the limitations of rule-based systems in
handling unexpected or more nuanced questions.

CSE Department, SRMCEM, Lucknow

 Campus Enquiry Chatbot

Despite their success in handling repetitive and routine tasks, early rule-
based chatbots were constrained by their rigid structure. They required
manual updates to their rule sets whenever new types of queries
emerged, making them less adaptive to evolving user needs.
2.2 AI-BASED APPROACHES
The development of artificial intelligence (AI) and machine learning,
particularly Natural Language Processing (NLP), revolutionized the
capabilities of chatbots. AI-based approaches allowed chatbots to
understand the context, intent, and even subtleties of user queries, vastly
improving both the scope and accuracy of interactions.
 Banchs & Li (2012) [3] advanced the chatbot landscape by introducing a
retrieval-based dialogue system for conversational agents. Unlike rule-
based systems, retrieval-based models could search through a large
database of potential responses and select the most appropriate reply
based on the context of the query. This method greatly improved the
relevance and variety of responses. In the context of a campus enquiry
chatbot, this approach allowed the system to provide dynamic responses
to a broader range of student questions, such as “Where can I find details
on my upcoming exam?” or “What courses are available next semester?”
 Kuligowska (2015) [4] focused on enhancing the conversational abilities
of chatbots through the application of machine learning and NLP
techniques. She demonstrated that chatbots equipped with NLP could
process unstructured queries and generate contextually appropriate
answers. By using algorithms such as decision trees and logistic
regression, the system could adapt to new user inputs without the need
for manual updates, unlike rule-based systems. In her evaluation of
educational chatbots, she observed a significant increase in user
satisfaction when the chatbot could handle complex inquiries, such as
“What are the eligibility criteria for this scholarship?” or “How can I
change my major?”
 Sarikaya et al. (2016) [5] took this a step further by introducing end-to-
end models for task-oriented dialogue systems. These systems used deep
learning architectures such as Recurrent Neural Networks (RNNs) and
Long Short-Term Memory (LSTM) networks to process conversations in

CSE Department, SRMCEM, Lucknow

 Campus Enquiry Chatbot

a more human-like manner. Unlike retrieval-based systems that select

pre-written responses, end-to-end models generate responses based on
learned patterns from large datasets. This made chatbots capable of
handling a wide variety of queries while maintaining conversational
flow. In a university setting, these models allowed chatbots to manage
complex interactions, such as navigating multiple campus systems (e.g.,
course databases, library catalogs, student records) to provide
personalized and real-time responses.
 Serban, I. V., Sankar (2017) [6] introduced Reinforcement Learning
(RL) to chatbots, allowing them to learn and optimize their responses
through continuous interaction. In a campus enquiry context, an RL-
based chatbot could learn from past interactions, improving its ability to
guide students through administrative processes or answer specific
queries like “What’s the procedure for course registration?” with
increased accuracy and personalization over time.
2.3 ADVANCES IN NLP & CONVERSATIONAL AGENTS
Recent advancements in NLP models, particularly transformer-based
architectures, have significantly elevated the performance of campus
enquiry chatbots. Devlin et al. (2018) [7] introduced BERT
(Bidirectional Encoder Representations from Transformers), which
enabled chatbots to process the meaning of words in context,
significantly improving their comprehension of complex, multi-faceted
questions. For example, a chatbot equipped with BERT could handle
queries like “How do I apply for both financial aid and a scholarship?”
by understanding the relationship between the multiple components of
the query.
This ability to comprehend and generate responses based on the
contextual meaning of user inputs has made modern chatbots far more
effective in educational settings, allowing them to function as robust
virtual assistants capable of managing academic, administrative, and
logistical queries with minimal human intervention.

CSE Department, SRMCEM, Lucknow

 Campus Enquiry Chatbot

CHAPTER 3
PROBLEM DEFINITION

Educational institutions face significant challenges in managing the high

volume of inquiries they receive on a daily basis from students, parents, and
prospective applicants. Common questions include inquiries about admission
procedures, course offerings, fee structures, campus facilities, and event
schedules. Traditionally, these queries are handled by administrative staff
through phone calls, emails, or face-to-face meetings, which can be time-
consuming and inefficient, particularly during peak times such as admission
seasons, examination periods, or campus events.
One of the major problems is the repetitive nature of these inquiries.
Administrative staff are often required to answer the same questions multiple
times, leading to an unnecessary increase in their workload. This not only
affects the productivity of staff but also delays the response time for students
and applicants, leading to frustration. The manual handling of such inquiries
also introduces the risk of inconsistency in the information provided, as
different staff members may provide slightly different responses to the same
query. Moreover, many educational institutions operate within limited office
hours, restricting the time during which students and prospective applicants can
seek assistance. Outside of these hours, there is often no way to get immediate
answers to urgent questions.
Another significant challenge is the difficulty students face in finding specific
information. While most institutions provide information on their websites,
navigating through various pages to find relevant details can be confusing and
time-consuming. This often leads students to resort to contacting staff directly,
further adding to their workload.

CSE Department, SRMCEM, Lucknow

 Campus Enquiry Chatbot

The rise of digital solutions presents an opportunity to streamline this process,

yet many institutions still lack an efficient system for providing real-time
responses. Most existing systems do not leverage advanced technologies like
Artificial Intelligence (AI) and Natural Language Processing (NLP) to automate
the inquiry process and provide immediate answers. As a result, users are often
left waiting for responses during peak periods or outside of office hours, causing
dissatisfaction and delays in decision-making for prospective students.
Given these challenges, there is a need for a more efficient, scalable, and
automated solution that can provide real-time, accurate, and consistent answers
to frequently asked questions. An AI-powered chatbot, integrated with a
backend system for real-time data retrieval, would serve as a valuable tool to
address these issues. Such a system would reduce the workload on staff by
handling repetitive inquiries, ensure that information is available 24/7, and
improve the overall user experience by providing immediate and reliable
responses.
By automating the inquiry process, educational institutions can focus their
resources on more complex tasks that require human intervention, while
students and applicants benefit from quick and easy access to the information
they need. Additionally, a chatbot system can be continuously updated with the
latest information on admissions, courses, and campus events, ensuring that
users always receive the most accurate and relevant details.
The Real-Time Campus Enquiry Chatbot aims to address these challenges by
leveraging AI and NLP to provide instant, accurate, and 24/7 accessible
information, thereby improving operational efficiency and enhancing the overall
user experience.
3.1 PROJECT OBJECTIVE
The primary objective of the Real-Time Campus Enquiry Chatbot project is to
design and develop an AI-powered chatbot that provides students, parents, and
prospective applicants with immediate, accurate, and relevant information about
the college. The chatbot will leverage Natural Language Processing (NLP) to
understand and respond to user queries in real time. The following specific
objectives are key to achieving this goal:
1. Automate Response to Frequently Asked Questions (FAQs)
2. Provide 24/7 Availability and Instant Responses

CSE Department, SRMCEM, Lucknow

 Campus Enquiry Chatbot

3. Enhance User Experience and Accessibility

4. Ensure Consistency and Accuracy of Information
5. Reduce Administrative Workload
6. Encourage User Engagement and Feedback
7. Increase Awareness of Campus Events and Activities
By meeting these objectives, the chatbot will streamline the process of
providing information to users, reduce response times, and enhance operational
efficiency for the institution.
3.2 PROPOSED METHODOLOGY
1. Requirement Analysis and Understanding
 Objective: Define the scope and requirements of the chatbot system,
focusing on the type of inquiries it will handle (e.g., admissions, course
details, fees, events).
 Method: Identify frequently asked questions and user interactions by
conducting research or gathering data from administrative staff and
students. Ensure that the chatbot meets the most common needs.
 Deliverable: A well-defined set of use cases and inquiries the chatbot
will handle.
2. Natural Language Processing (NLP) Setup
 Objective: Enable the chatbot to understand and process natural
language queries.
 Method: The chatbot code uses the chatterbot library, which is based on
NLP. Implement intent recognition, query classification, and response
generation using this library.
 Steps:
o Use Chat Bot for machine learning-based dialogue generation.
o Train the bot on specific college-related questions.
 Deliverable: A functioning NLP model capable of recognizing common
inquiries and providing accurate responses.
3. Dialogue Flow and Conversational Design
 Objective: Design an effective conversation flow between the user and
the bot.

CSE Department, SRMCEM, Lucknow

 Campus Enquiry Chatbot

 Method: Define dialogue responses for common queries, fallback

mechanisms for misunderstood questions, and a suggestion system for
continuous improvement.
 Deliverable: A smooth and intuitive conversation flow with predefined
responses for key intents.
4. Backend Integration
 Objective: Provide accurate and up-to-date information from the
backend.
 Method: Use a backend database (SQL or NoSQL) to store and retrieve
important college-related information like admissions, courses, and fees.
 Deliverable: A backend data integration that provides dynamic
responses based on real-time data.
5. Training the Chatbot
 Objective: Train the chatbot using relevant data.
 Method: Train the chatterbot model using the specific corpus related to
college inquiries. The chatbot should be trained on admissions, courses,
fees, and general campus information. Incorporate feedback loops to
continuously improve the training dataset.
 Deliverable: A trained model that becomes more accurate over time as it
interacts with users.
6. User Interface (UI) Design
 Objective: Develop a user-friendly interface for the chatbot.
 Method: Use a simple web-based or mobile UI where users can type
questions. The interface could be a front-end application using
HTML/CSS and JavaScript.
 Deliverable: A user-friendly UI for students, parents, and staff to
interact with the bot.
7. Testing and Debugging
 Objective: Ensure the chatbot functions as expected under various
conditions.
 Method: Perform unit and integration tests. Test various user queries
and edge cases to ensure the bot responds accurately and gracefully
handles unrecognized queries.

CSE Department, SRMCEM, Lucknow

 Campus Enquiry Chatbot

 Deliverable: A tested chatbot with accurate and appropriate responses

for a wide range of inquiries.
8. Feedback Mechanism and Continuous Learning
 Objective: Implement a feedback system for improvement.
 Method: Integrate a suggestion box or rating system where users can
provide feedback on the bot's responses. This feedback will be used to
fine-tune the NLP model and improve the accuracy of responses over
time.
 Deliverable: A system that continuously evolves based on user feedback
and becomes more effective.

CSE Department, SRMCEM, Lucknow

 Campus Enquiry Chatbot

CHAPTER 4
TECHNOLOGIES USED

1. Python
 Role: Core programming language for building the chatbot.

 Usage: Python is used for scripting and integrating various components of

the chatbot, including NLP, backend logic, and response handling.
 Key Libraries:
o ChatterBot: A Python library used to generate automated responses
to user inputs. It is built on machine learning algorithms and is
specifically used for creating conversational agents.
o ChatterBotCorpusTrainer: Utilized to train the bot using pre-defined
datasets, ensuring it understands specific queries related to college
information.

2. Natural Language Processing (NLP)

 Role: To process and understand user queries in natural language.
 Usage:
o ChatterBot: Handles NLP tasks such as intent recognition and
response generation. It allows the bot to analyze the text entered by
the user, identify the intent behind the query, and generate
appropriate responses.
 Other Potential NLP Libraries:
o spaCy or NLTK: Could be used for more advanced text processing
if needed.
3. Flask
 Role: Backend web framework.
 Usage: Flask is used to create a web server for handling HTTP requests.
This allows the chatbot to be accessed via a web interface where users can
input queries.

CSE Department, SRMCEM, Lucknow

 Campus Enquiry Chatbot

 Purpose:
o Routing user queries to the chatbot system.
o Serving responses from the chatbot to the front-end.

4. HTML/CSS/JavaScript
 Role: Frontend technologies for creating the user interface.
 Usage: These technologies are used to create the chatbot’s front-end,
allowing users to interact with the bot through a web interface. The user
interface is where queries are typed, and responses are displayed in a
chatbox format.
 Potential Enhancements: Frameworks like React.js or Vue.js could be used
for dynamic user interfaces.

5. MySQL (Database)
 Role: Database for storing structured information.
 Usage: A backend database (MySQL) is used to store frequently accessed
data such as course details, admission criteria, fee structures, and event
schedules. The chatbot queries this database to fetch real-time, up-to-date
information.
 Purpose: To ensure that the chatbot delivers accurate information based on
live data.

CSE Department, SRMCEM, Lucknow

 Campus Enquiry Chatbot

CHAPTER 5

IMPLEMENTATION ALGORITHMS

5.1 PRE-REQUISITES

Install the following libraries:

 pip install Flask

 pip install chatterbot
 pip install chatterbot-corpus
 pip install -U pip setuptools wheel
 pip install -U spacy
 python -m spacy download en_core_web_sm
 pip install Flash reCAPTCHA
 pip install mysql-connector-python
 pip install mysql-connector-python-rf

5.2 DATA STRUCTURE

1. Create Database

Query - create database register;

2. Create Table Users

Query - create table users(name varchar(30), email varchar(30), password

varchar( 15)):

3. Create Table suggestion

CSE Department, SRMCEM, Lucknow

 Campus Enquiry Chatbot

Query - create table suggestion(email varchar(30), message varchar(255));

5.3 RUNNING THE SERVER

1. Load the project folder in an editor(VSC)

2. Install all the required libraries mentioned above and create the database
structure in any database of your choice. (Change the connection statements
according to the database you are using).

3. On the terminal locate your project directory.

4. In order to run the project, give the command python app.py runserver

5. Paste the link in the browser of your choice.

6. Create an account through register page and login to the system.

7. Ask your question!

8. Logout of the system once done.

5.4 CODE FOR QUICK SUMMARY

1. Creating Web App

CSE Department, SRMCEM, Lucknow

 Campus Enquiry Chatbot

CSE Department, SRMCEM, Lucknow

 Campus Enquiry Chatbot

2. Dataset

CSE Department, SRMCEM, Lucknow

 Campus Enquiry Chatbot

CHAPTER 6

DIAGRAMMATIC SCHEMA

Data Flow Diagram: A data flow diagram (DFD) depicts the information flow
in this system. It displays data inputs, outputs, storage locations, and routes
between each destination using predefined symbols such as rectangles, circles,
and arrows as well as brief text labels. The entity, process, data store, and data
flow are the four essential components of all data flow diagrams.

LEVEL 0 - As our methodology follows iterative model, in our basic stage,

basic users of the application is designed.

CSE Department, SRMCEM, Lucknow

 Campus Enquiry Chatbot

LEVEL 1 - Then the design follows functional aspects with regards to the users
defined in Level 0.

LEVEL 2 - Interactions and complete algorithm is enhanced in Level 1.

CSE Department, SRMCEM, Lucknow

 Campus Enquiry Chatbot

CHAPTER 7

CSE Department, SRMCEM, Lucknow

 Campus Enquiry Chatbot

SOFTWARE AND HARDWARE

REQUIREMENT

TABLE: HARDWARE REQUIREMENTS

S.NO REQUIREMENTS

1 Processor: Intel Core i3 or above

2 RAM: Minimum 4GB (8GB recommended for

smoother performance)
3 Storage: At least 500MB for project files

4 Internet Connectivity: Required for accessing

external libraries, databases, and deploying the
chatbot.

TABLE: SOFTWARE REQUIREMENTS

S.NO REQUIREMENTS

1 Operating System: Windows, macOS, or Linux

2 Programming Languages: Python, HTML, CSS

3 Frameworks: Flask, NTLK or Chatterbot

CSE Department, SRMCEM, Lucknow

 Campus Enquiry Chatbot

CHAPTER 8
CONCLUSION

The Campus Enquiry Chatbot, developed using Python, Flask, MySQL, HTML,
CSS, JavaScript, and Bootstrap, demonstrates a practical application of web-
based technologies to improve campus communication. It efficiently automates
responses to common student queries, reducing the workload on administrative
staff while enhancing the user experience through real-time interaction.

8.1 ADVANTAGES:
1. Efficiency: The chatbot provides instant responses, reducing the need
for students to wait for assistance and freeing up administrative
resources.
2. Accessibility: The use of Bootstrap ensures a responsive design, making
the chatbot accessible on various devices such as smartphones, tablets,
and desktops.
3. Scalability: By using Flask and MySQL, the system is capable of
handling large amounts of data and can be easily expanded to include
more features and information over time.
4. User-Friendly Interface: The combination of HTML, CSS, and
JavaScript provides an intuitive and easy-to-navigate interface for users.
5. 24/7 Availability: The chatbot is accessible at any time, ensuring
students can receive answers to their queries outside of normal working
hours, improving campus service accessibility.
6. Consistency in Responses: Unlike human operators, the chatbot
provides consistent answers to the same queries, ensuring students
receive accurate and reliable information every time.

8.2 LIMITATIONS:
1. Database Dependency: Since it relies on a pre-set database (MySQL),
the chatbot can only answer queries for which information has already
been stored. New queries require manual updates to the database.

CSE Department, SRMCEM, Lucknow

 Campus Enquiry Chatbot

2. No Voice or Multilingual Support: The chatbot currently functions

only through text input and responds in one language, which may limit
its use in a diverse campus population.
3. Limited to Predefined Queries: The chatbot can only respond to
questions it has been programmed to understand. Any query outside of
its programmed knowledge base requires manual intervention or updates
to the database.
4. Basic Error Handling: The chatbot may not always handle unexpected
user input gracefully. If a user asks an unclear or vague question, the
chatbot might struggle to provide an accurate answer.
5. No Emotional Intelligence: Unlike human interaction, the chatbot
cannot understand or respond to the emotional state of the user, which
could be important in cases of sensitive or urgent inquiries.

8.3 FUTURE IMPLICATIONS

1. Machine Learning Integration: In the future, the chatbot can be
enhanced with Natural Language Processing (NLP) and machine
learning to better understand user intent and handle more complex
queries.
2. Voice Recognition: Adding voice-based interaction would make the
chatbot more versatile, allowing for easier accessibility, especially for
users with disabilities or those who prefer voice interaction.
3. Multilingual Support: Implementing multiple language options would
increase the chatbot's utility, making it accessible to a broader audience,
particularly international students.
4. Real-Time Data Integration: Linking the chatbot to live campus data
systems such as academic portals or event calendars could provide real-
time updates, making it even more valuable for students and staff alike.

In conclusion, while the current version of the Campus Enquiry Chatbot

provides significant benefits in terms of efficiency and user engagement, there is
ample potential for future development. By addressing its limitations and
incorporating advanced technologies, the chatbot can evolve into an even more
powerful tool for campus communication and student support.

CSE Department, SRMCEM, Lucknow

 Campus Enquiry Chatbot

REFERENCES

[1] Weizenbaum, J. (1966). ELIZA—a computer program for the study of

natural language communication between man and
machine. Communications of the ACM, 9(1), 36-45.Shawar, B. A., &
Atwell, E. (2007). Chatbots: are they really useful?. Journal for Language
Technology and Computational Linguistics, 22(1), 29-49.
[2] Colace, F., De Santo, M., Lombardi, M., Pascale, F., Pietrosanto, A., &
Lemma, S. (2018). Chatbot for e-learning: A case of study. International
Journal of Mechanical Engineering and Robotics Research, 7(5), 528-533
[3] . Banchs, R. E., & Li, H. (2012, July). IRIS: a chat-oriented dialogue system
based on the vector space model. In Proceedings of the ACL 2012 System
Demonstrations (pp. 37-42).
[4] Kuligowska, K. (2015). Commercial chatbot: performance evaluation,
usability metrics and quality standards of embodied conversational
agents. Professionals Center for Business Research, 2.
[5] Sarikaya, R., Hinton, G., & Deng, L. (2016). End-to-end task-completion
neural dialogue systems. arXiv preprint arXiv:1703.01008.
[6] Serban, I. V., Sankar, C., Germain, M., Zhang, S., Lin, Z., Subramanian,
S., ... & Bengio, Y. (2017). A deep reinforcement learning chatbot. arXiv
preprint arXiv:1709.02349.
[7] Devlin, J. (2018). Bert: Pre-training of deep bidirectional transformers for
language understanding. arXiv preprint arXiv:1810.04805.

CSE Department, SRMCEM, Lucknow