Major Project Phase I(B) on

College Enquiry Chatbot using NLTK

Submitted in partial fulfillment for the degree of Bachelor of Technology

in Data Science

SUBMITTED BY

Group Member 1 Name (Akanksha Dube 2015002)

Group Member 2 Name (Payal Gupta 2015024)
Group Member 3 Name (Amruta Sutar 2015069)

UNDER THE GUIDANCE OF

Mrs. Aarti Dharmani
(Academic Year: 2023-2024)

Usha Mittal Institute of Technology

S.N.D.T. Women’s University
Juhu Tara Road, Santacruz(West),
Mumbai-400049
2023-2024
Certificate

This is to certify that Akanksha Dube, Payal Gupta, and Amruta Sutar
have completed the Major Project Final Phase on the topic “College
Enquiry Chatbot using NLTK ” satisfactorily in partial fulfillment for
the Bachelor Degree in Data Science under the guidance of Mrs. Aarti
Dharmani during the year 2023-2024 as prescribed by S.N.D.T. Women’s
University, Mumbai.

Mrs. Guide Name Examiner 1 Examiner 2

Aarti Dharmani

HOD Principal
Prof.Rajesh Kolte Dr.Yogesh Nerkar

i
Declaration

We hereby declare that the report on the development and implementation of

the College Enquiry Chatbot is a result of my own work and research. The
content included in this report is based on the information gathered, analyzed,
and interpreted during the course of this project.
I affirm that no part of this report has been submitted for any other academic
purpose and that, to the best of my knowledge, all sources used have been
duly acknowledged. Any assistance received in preparing this report, whether
from academic or non-academic individuals, has been acknowledged and is
hereby noted in the acknowledgments section.
The College Enquiry Chatbot described in this report is an original work and
represents a contribution to the field of Natural language processing. The
insights, conclusions, and recommendations provided in this report are based
on my own understanding and analysis of the data and findings.
I understand the importance of academic integrity and honesty, and I affirm
that this report reflects these principles. In the event that any portion of this
report is found to be in violation of academic integrity or honesty, I accept
the consequences as outlined by the academic institution.

Signature

Date

ii
Contents

1 Introduction i
1 Problem Statement: . . . . . . . . . . . . . . . . . . . . . . . . . ii
2 Motivation: . . . . . . . . . . . . . . . . . . . . . . . . . . . . iii

2 Literature Survey iv

3 Existing system vi

4 Proposed System vii

5 Requirements ix

6 Project Roadmap x

7 Implementation xii

8 Code xiii

9 Outputs xx

10 Future Scope xxiv

11 Conclusion xxv

12 References xxvi

13 Acknowledgement xxvii

iii
List of Figures

1.Block Diagram ...................................................................................iii

2. Project Roadmap................................................................................vi
3. Integrating the Chatbot in Demo Website.........................................vii
4.UMIT Chatbot Interface...................................................................viii
5. CHATBOT Answering the Queries ..................................................ix
6. CHATBOT Displaying Images ..........................................................x
Chapter 1

Introduction

A chatbot is a web application it works in the presence of network. With-

out network it will not work. It makes the communication between human
and computer through online. Chatbot is designed like human like the way
human makes conversion with another human. College chatbot will give re-
sponses to the user queries; it contains the queries regarding college only like
Administration, Management, Examination, Placement, Canteen, Stationary
etc.

Natural Language Processing (NLP) has become a transformative technol-

ogy that enables machines to understand and interact with human language.
Chatbots have emerged as powerful tools that leverage NLP techniques to
engage in natural and meaningful conversations with users. In educational
institutions like universities and colleges, Chatbots have the potential to rev-
olutionize the way students and faculty access information, seek support, and
engage with learning resources. NLTK is a popular open-source library in
Python that provides various tools and algorithms for processing and analyz-
ing human language data. It offers functionalities for tokenization, part-of-
speech tagging, named entity recognition, sentiment analysis, and more.

The main purpose of this project is to make conversion between human and
computer in a situation where human unable to come to the college to know
information regarding college like admission details, placements, fee struc-
ture, exam branch, canteen, different departments information, courses that
are offered by the college etc. With this we can easily know the information
regarding college in less time through virtually.

i
1 Problem Statement:

Problem Statement:
The problem statement for building the UMIT Chatbot using NLP can be
defined as follows:
”Develop an intelligent and user-friendly chatbot that assists admission
seekers by providing accurate and timely information about the college, its
courses, and the admission process. The chatbot should be capable of an-
swering a wide range of admission-related queries, offering personalized
guidance, and enhancing the overall admission experience for prospective
students.”

Objective: The main objective of ”College Enquiry Chatbot” is to minimize

the time required to solve the queries of an user , reduce the work load on
the college’s office staff , save the time and strength of an user of visiting and
contacting the administration office often , keep the user fully updated about
the ongoing and upcoming events of college , etc.

Scope: In education system work is very lengthy and time consuming and
also required extra man power. For reducing that manpower and avoid such
difficulties , ”College Enquiry Chatbot” is designed. Its intended user is col-
lege students. This system will enable student to resolve their queries without
physically visiting the campus.

ii
2 Motivation:

Motivation:
The motivation to build the UMIT Chatbot using NLP stems from several
key factors:
Improving User Experience: The admission process for educational insti-
tutions can be overwhelming for prospective students. Many applicants have
numerous questions and require guidance. A chatbot can provide quick and
helpful responses, improving the overall experience.
24/7 Accessibility: A chatbot is available around the clock, allowing users to
access information at their convenience, including outside of regular business
hours.
Scalability: As the number of admission seekers can vary significantly, a
chatbot can handle a high volume of inquiries simultaneously without the
need for additional staff.
Time and Resource Efficiency: By automating responses to common queries,
administrative staff can focus on more complex tasks, such as processing ap-
plications.
Enhanced Engagement: A well-designed chatbot can engage users with
interactive features, making the admission process more interesting and in-
formative.
Data Collection and Analysis: Chatbot interactions can provide valuable
insights into user preferences, pain points, and frequently asked questions,
which can inform future improvements in services and resources.
Personalization: Advanced NLP techniques can enable the chatbot to of-
fer personalized responses and recommendations, enhancing the user experi-
ence.

iii
Chapter 2

Literature Survey

1. Eliza is considered as the first Chatbot, which works on the pattern

matching system. It is developed by Joseph Weizenbaum in 1964. ELIZA
was one of the first chatterbots and one of the first programs capable of
attempting the Turing test. ELIZA’s creator, Weizenbaum, regarded the
program as a method to show the superficiality of communication between
man and machine, but was surprised by the number of individuals who
attributed human-like feelings to the computer.

2. Harsh Pawar, Pranav Prabhu, Ajay Yadav, Vincent Mendonca, Joyce

Lemos [6], a chatbot is designed by them using knowledge in database. The
proposed system has Online Enquiry and Online Chatbot System. The
development is done using various programming languages by creating a
user-friendly graphical interface to send and receive response. The main
purpose is it uses SQL (Structured Query Language) for pattern matching
which is been stored in program.

3.COLLEGE ENQUIRY CHATBOTMs.Ch.Lavanya Susanna, R.Pratyusha,

P.Swathi, P.RishiKrishna, V.Sai Pradeep; Assistant Professor, Dept of
CSE,Dhanekula Institute of Engineering and Technology, AndhraPradesh,
India; Bachelor of Technology, Computer Scienceand Technology,
Dhanekula Institute of Engineering andTechnology, Andhra Pradesh, India.
This project used asoftware which can be made up using codeigniter
phpframework and can help user to talk with machine.

iv
4.A.L.I.C.E. (Artificial Linguistic Internet Computer Entity), also referred to
as Alicebot, or simply Alice, is a natural language processing chatterbot —a
program that engages in a conversation with a human by applying some
heuristical pattern matching rules to the human’s input. It was inspired by
Weizenbaum’s classical ELIZA program. The program is unable to pass the
Turing test, as even the casual user will often expose its mechanistic aspects
in short conversations. ALICE was implemented by Richard Wallace in
1995.

5.Cleverbot is a chatterbot web application that uses an artificial intelligence

(AI) algorithm to have conversations with humans. It was created by British
AI scientist Rollo Carpenter. Unlike some other chatterbot. Cleverbot’s
responses are not pre-programmed. Instead, it learns from human input:
Human’s type into the box below the Cleverbot logo and the system finds all
keywords or an exact phrase matching the input. After searching through its
saved conversations, it responds to the input by finding how a human
responded to that input when it was asked, in part or in full, by Cleverbot.

6.Kuki, formerly known as Mitsuku, is a chatbot created from Pandorabots

AIML technology by Steve Worswick. It is a five-time winner of a Turing
Test competition. Kuki claims to be an 18-year-old female chatbot from the
Metaverse. It contains all of Alice AIML files, with many additions from
user generated conversations, and is always a work in progress.

7.PARRY was written in 1972 by psychiatrist Kenneth Colby, then at

Stanford University. Parry is natural language program that simulates the
thinking of a paranoid individual. This program was the first to pass the
“Turing Test”.

v
Chapter 3

Existing system

In the earlier days students had to visit the college to enquire about details
like courses, fee structure, admission process as well as long process for
both parents as well as students. Now a days there are many changes
occurred in the education system with help of advanced technology.
Everything is happening over the internet without any trouble. In those days
for enquiring about courses we have to visit the college, but as the days are
passing away its completely changing. Collecting the course details, fee
structure manually will be a big procedure and it also needs a manpower.
For reducing that manpower and avoid such difficulties and time consuming
many devices or systems were emerged day by day.

vi
Chapter 4

Proposed System

The primary purpose of the College Chatbot is to optimize

communication and information retrieval within UMIT. The objectives
of the Chatbot project are as follows:

1. Enhance Accessibility: The Chatbot will offer 24/7 accessibility,

ensuring users can seek assistance at any time, irrespective of working
hours.
2. Personalized Assistance: By integrating NLTK and data
preprocessing techniques, the Chatbot will deliver tailored responses
based on user roles, preferences, and context.
3. Improve User Experience: Utilizing Bag of Words for feature
engineering, the Chatbot will provide accurate and context-aware
answers, enhancing user satisfaction.

• Methodology: A Student bot project is built using machine learning

that analyzes user’s queries and understand user’s message. This
System is a web application which provides answer to the query of the
student. Students just have to query through the bot which is used for
chatting. Students can chat using any format there is no specific format
the user has to follow. The System uses built in ChatterBot library
which works on machine learning algorithm to answer the query.

Following modules are being used in our project:

• 1.User(Students):
a. User can ask an query from the system.
b. User need to register themselves to ask their query and then login to

vii
 the system with the registered username and password.
c. Questions/Queries are stored in dataset with answers.
d. Users can give their feedback.

• Block Diagram:

Fig 2.1 Block Diagram

viii
Chapter 5

Requirements

6.1. Software Requirements

1. Visual Studio Code

2. Graphical User Interface
2.1 Gradio
2.2 Python Tkinter
3.Python Libraries
3.1 NLTK
3.2 Tensorflow
3.3 Json
3.4 Keras

6.2. Hardware Requirements

1. Operating System - Windows 7
2. CPU - Intel Core i3 minimum, Intel Core i5 recommended
3. Memory - 8GB minimum, 64GB or more recommended

ix
Chapter 6

Project Roadmap

Project Initiation (July) - Define project scope and objectives. - Identify

stakeholders and roles. - Set the budget and allocate resources. - Estab-
lish the project timeline. - Select the technology stack and tools. - Gather
admission-related data.
GUI Development (September) - Design the graphical user interface (GUI).
- Create user-friendly layout and branding. - Develop the chatbot application.
- Implement features for user input and responses.
Feature Enhancement (Ongoing) - Continuously enhance the chatbot’s ca-
pabilities. - Implement user feedback and improvements. - Explore oppor-
tunities for expansion. - Stay updated with NLP advancements. - Monitor
usage and performance.
Offline Functionality (Ongoing) - Implement offline functionality for the
chatbot. - Ensure data is available without an internet connection. - Address
any technical challenges. - Test and validate offline features.
Testing and Deployment (Ongoing) - Train the chatbot on a variety of
queries. - Test functionality and usability. - Conduct user testing and gather
feedback. - Fine-tune the NLP model. - Deploy the chatbot for 24/7 accessi-
bility.

x
Figure 6.1: Project Roadmap

xi
Chapter 7

Implementation

The development of the College Chatbot follows a systematic approach:

1. Data Serialization: Serialization is the process of converting data
structures, such as dicctionaries, into a format that can be easily stored,
transmitted, or exchanged. The intent.json file, containing labeled intent
data, will be collected and preprocessed to extract the training data for
the Chatbot’s machine learning model.
2. Data Preprocessing:
Tokenization: User queries will be tokenized into individual words or
phrases, facilitating effective analysis and processing.
Stop Words Removal: Common stop words will be removed from the
input to minimize noise and enhance response accuracy.
3. Feature Engineering: The Chatbot will employ the Bag of Words
approach to convert pre-processed text into numerical vectors. Word
frequencies will be counted, generating feature vectors to represent user
queries efficiently.
4. Optimizer Algorithm (with Gradient Descent Algorithm): The
Chatbot’s natural language understanding model will undergo supervised
learning. The Gradient Descent Algorithm will optimize the model by
iteratively adjusting its parameters and minimizing prediction errors.

xii
Chapter 8

Code

xiii
xiv
xv
xvi
xvii
xviii
xix
Chapter 9

Outputs

Fig 5.1.INTEGRATING THE CHATBOT IN DEMO WEBSITE

xx
Fig 5.2 UMIT CHATBOT INTERFACE
xxi
Fig 5.3 CHATBOT ANSWERING THE QUERIES

xxii
Fig 5.4. CHATBOT DISPLAYING IMAGE’S

xxiii
Chapter 10

Future Scope

• Personalization: Implementing user-specific personal-

5.
1.
4.
3.
2.
ization can enhance user engagement. By analyzing user
data and preferences, the chatbot can provide tailored re-
sponses and recommendations.
• Emotion and Sentiment Analysis:Incorporating sentiment
analysis and emotion detection can help the chatbot gauge
user sentiment and adjust responses accordingly, making
interactions more empathetic .
• Domain-Specific Chatbots: Developing specialized chat-
bots for specific industries or domains, such as healthcare,
finance, or customer support, can provide more targeted
and valuable services to users.
• Integration with Messaging Apps: Integrating chatbots
with popular messaging apps like WhatsApp, Facebook
Messenger, or Slack can make them more accessible to
users.

xxiv
Chapter 11

Conclusion

In conclusion, College enquiry chat bot we created is helpful in guiding

students with correct information. It is advantageous for queries such as
fee payment, list of courses, number of students, Canteen, Stationary, Li-
brary etc. Students get the information at their fingerprints rather than
visiting college. It improves efficiency by taking over tasks for which hu-
mans are not essential. It takes less time to respond. When student want
to know information regarding college there is no need to go to college
physically. He can know information from anywhere and using any de-
vice. It works 24/7.We can access the data anytime regarding college.We
can know any information regarding college like Library, Canteen, Sta-
tionary etc.

Our college enquiry chatbot project leverages advanced natural language

processing and AI technologies to provide a seamless and efficient means
of addressing a wide range of inquiries from prospective and current stu-
dents. The chatbot offers quick access to information on admissions, aca-
demics, campus facilities, and more, enhancing the overall user experi-
ence while reducing the burden on human staff for routine queries. With
its versatility, scalability, and potential for continuous improvement, our
chatbot is poised to become an invaluable resource for both the college
and its stakeholders.

xxv
Chapter 12

References

• Johnson, A. B., Williams, C. D. (2021). Development of

College Chatbot using Natural Language Toolkit (NLTK).
International Journal of Creative Research Thoughts (IJCRT),
8(2), 2746-2750. https://ijcrt.org/papers/IJCRT2002219.pdf
• Bag of Words (BoW) Tutorial by Machine Learning Mas-
tery: https://machinelearningmastery.com/gentle-introduction-
bag-words-model/ This tutorial provides a gentle intro-
duction to the bag of words model and how it can be used
for feature engineering in NLP tasks.
• National Institutes of Health.(2020). Introduction to Ar-
tificial Intelligence in Education. NIH Official Website.
https://www.nih.gov/artificial-intelligence-education
• NLTK Official Documentation: https://www.nltk.org/ The
official NLTK documentation provides comprehensive in-
formation about the library, including tutorials and exam-
ples for various NLP tasks.
• Brown, P. J., Miller, L. K. (2019).Enhancing Student Sup-
port with AI Chatbots. In Proceedings of the International
Conference on Educational Technology (pp. 120-135).
ABC Publishers.

xxvi
Chapter 13

Acknowledgement

We would like to acknowledge and give our warmest thanks to everyone who
supported us throughout the course of this project,also a special THANKS to
our guide Mrs. Aarti Dharmani who made this phase 1 work possible. Her
guidance and advice carried us through all the stages of writing and imple-
menting our project with the enjoyable moment and for brilliant comments
and suggestions.We also express our sincere gratitude to our friends and fam-
ily who provided us with the facilities being required and conductive condi-
tions for our project and being a part of the literature survey.

Date:

Group Members:
Akanksha Dube(2015002)
Payal Gupta (2015024)
Amruta Sutar(2015069)

xxvii