A

Project Report
On

BCOE Guide Chatbot

Submitted in partial fulfillment of the requirements

For the degree of

Bachelor of Engineering in
Computer

By

Katherine Nadar Roll.no 26

Anjali Singh Roll.no 32
Shivam Singh Roll.no 33
Shubham Palekar Roll.no 28

Supervisor
Prof. (Supriya Pawar)

Department of Computer Engineering

Innovative Engineers’ and Teachers’ Education society’s

Bharat College of Engineering
Badlapur: - 421504
(Affiliated to University of Mumbai)
(2022-23)
 Bharat College of Engineering
(Affiliated to the University of Mumbai)
Badlapur: - 421504

CERTIFICATE
This is to certify that, the Project titled

“ BCOE Guide Chatbot”

is a bonafide work done by

Katherine Nadar Roll.no 26

Anjali Singh Roll.no 32
Shivam Singh Roll.no 33
Shubham Palekar Roll.no 28

and is submitted in the partial fulfillment of the requirement for the degree of
Bachelor of Engineering In
Computer
To the
University of Mumbai

________________________ __________________________
Supervisor External
(Prof.Supriya Pawar) (Prof. )

Subject Incharge Head of Department Principal

(Prof. Supriya Pawar) (Prof. Deepa Athawale) (Dr.Siddhartha Ladhake)

 ABSTRACT

REASEARCH FOCUS : BCOE Guide (Chat bot) application is to understand and

interpret complex college-related inquiries and provide accurate and relevant responses.

PRESENTATION TYPE : Digital Presentation.

As a result of the rapid technological development and the development of the chatbot concept
and time and efforts it can save. Many specialized frameworks have emerged to undertake
Chatbot creation and development. By relying on artificial intelligence, the chatbot has
integrated machine learning with it, and it has become more comprehensive and wider for
various technological fields. Users interact with systems more and more through voice
assistants and chatbots. A chatbot is a computer program that can converse with humans using
Artificial Intelligence in messaging platforms. Every time the chatbot gets input from the user,
it saves input and Response which helps chatbot with little initial knowledge To evolve using
gathered responses.

With increased responses, precision of the chatbot also gets increases. The ultimate goal of this
project is to add a chatbot feature for Bharat College of Engineering named as BCOE Guide.
In this project, we are developing a chat bot which will provide result to the user’s queries
about the students of our college and the college itself, The user will be able to ask various
questions to the chat bot about the college and students, the questions may be concerned with
the infrastructure, accreditation, training & placements, result etc.

(i)
 CONTENTS
Abstract ............................................................................................................................................[i]

List of Figures .............................................................................................................................[iii]

List of Tables ...............................................................................................................................[iv]

1. Introduction 1 …………………………………….……………………………..…………...1
1.1 About
1.2 Problem Definition
1.3 Scope of project

2.Review of Related Work ………………………………………………………………….3

3.Planning ………………………………………………………………………….......................5

4. Methodology ……………………………………………………………………………….…6
4.1 Project System & Methodology …………………………………………….
4.2 System Requirements …………………………………………………….
4.3 User Requirements…………………………………………………………..

5. Design of The System ………………………………………………………………….…9

5.1 System Flow Chart………………………………………………………….
5.2 Output & Results……………………………………………………………
5.3 Code ………………………………………………………………………..

6. Experimental Results ………………………………………………………..……….……16

7. Conclusion …………………………………………………………………………….…..…..16

8. References...................................................................................................................................17

(ii)
 List of Figures

Fig No. Figure Name Page No.

3 Work Plan 6

4.1 Natural Language Processing 7

5.1.1 System Flow-chart 10

5.1.2 User Case Diagram 11

5.2 Output of Program 12

(iii)
 List of Tables

Table No. Table Name Page No.

2.2.1 Strength & Weakness of Reviewed App 4

2.2.2 Comparison Among Reviewed & Proposed App 5

(iv)
1. Introduction:

1.1 About

User interfaces for software applications can come in a variety of formats, ranging from
Command-line, graphical, web application, and even voice. While the most popular user
interfaces include graphical and web-based applications, occasionally the need arises for an
alternative interface. Whether due to multi-threaded complexity, concurrent connectivity, or
details surrounding execution of the service, a chat bot-based interface may suit the need.

Chat bots typically provide a text-based user interface, allowing the user to type commands
and receive text response. BCOE Guide is a Python-based application that provides a user-
friendly platform for college-related inquiries. The application is designed to understand
natural language input and provide accurate and relevant responses to a wide range of college-
related inquiries. The BCOE Guide uses natural language processing techniques and machine
learning algorithms to improve its understanding and response capabilities. It also incorporates
sentiment analysis and personalized recommendations to enhance the user experience. This
application is a simple and effective tool for students and others seeking information about
college-related inquiries, providing them with quick and easy access to information at their
fingertips.

There are two categories of chatbots. One category is command based chatbots where chatbots
rely on a databank of replies and heuristics. The user must be very specific while asking the
questions so that the bot can answer. Hence, these bots can answer limited set of questions and
cannot perform function outside of the code. The other category is chatbots based on AI or
machine learning algorithms, these bots can answer ambiguous questions which means the user
do not have to be specific while asking questions. Thus, these bots create replies for the user’s
queries using Natural Language Processing (NLP).

1
1.2 Problem Defination
The BCOE Guide chatbot is an application designed to provide a solution to the problem of
inefficient and time-consuming access to college-related information. The problem definition
can be broken down into various components, including the nature of the problem and the users
affected by the problem.

 The Nature of the Problem

The problem that the BCOE Guide chatbot aims to solve is the lack of a user-friendly, efficient,
and easily accessible platform for college-related inquiries. Many students and other
individuals seeking information about college-related inquiries struggle to find the information
they need quickly and easily. This often involves searching through multiple websites and
sources, which can be time-consuming and frustrating.

 Users Affected by the Problem

The problem of inefficient access to college-related information affects a wide range of users,
including students, parents, and others seeking information about college-related inquiries.
These users may have questions about admission requirements, course offerings, campus
facilities, financial aid, and other related topics. They may also need help navigating college
websites and portals, which can be confusing and overwhelming.

 The Role of BCOE Guide Chatbot in Addressing the Problem

The BCOE Guide chatbot addresses the limitations of existing solutions by providing a user-
friendly, efficient, and easily accessible platform for college-related inquiries. The chatbot uses
natural language processing techniques and machine learning algorithms to understand natural
language input and provide accurate and relevant responses to a wide range of college-related
inquiries. It also incorporates sentiment analysis and personalized recommendations to enhance
the user experience.

2
1.3 Scope of Project
The scope of the BCOE Guide chatbot project is to design and develop a user-friendly and
efficient platform that enables users to access accurate and relevant information about college-
related inquiries. The project includes various components, such as the target audience, features
of the chatbot, development process, and potential future enhancements.

 Target Audience
The target audience for the BCOE Guide chatbot includes students, parents, and others seeking
information about college-related inquiries. The chatbot will be designed to cater to the needs
of various users, regardless of their level of technical expertise.

 Features of the Chatbot

The BCOE Guide chatbot will include various features that enable users to access college-
related information quickly and easily. Some of these features include:

Natural language processing:

The chatbot will use natural language processing techniques to understand user input and
provide accurate and relevant responses.

Machine learning:

The chatbot will use machine learning algorithms to improve its understanding of user input
and enhance its response capabilities over time.

Sentiment analysis:

The chatbot will use sentiment analysis to understand the tone and context of user input and
provide appropriate responses.

Access to frequently asked questions:

The chatbot will provide users with access to frequently asked questions about college-related
inquiries.

3
2. Review of Related Work:

The BCOE Guide chatbot project aims to provide a user-friendly and efficient platform for
college-related inquiries. In this section, we will review some related work in the area of
chatbot development for college inquiries.

1.4 Review on Existing Application

There are several chatbots available in colleges that cater to different college inquiry needs.

Ask SID :

Ask SID by Symbiosis International University provides student support services such as
course selection and academic inquiries.

MyCampusMate :

MyCampusMate by University of Hyderabad provides campus information such as events and

facilities.

VIVA :

VIVA by VIVA College provides general college inquiries, including admission process and
course information.

2.2 Critical Remarks

2.2.1 Features

Chatbot Name Purpose Institution/Organization Features

Ask SID Student support Symbiosis International Course selection,

services University academic inquiries

MyCampusMate Campus University of Hyderabad Campus event,

information facilities information

VIVA General College VIVA college Addmission process,

inquires course information,
FAQs
Table 2.2.1 Features of Reviewed Application

4
2.2.2 Application Comparison

Application/Criterial Proposed Ask SID MyCampusMate VIVA

Application Chatbot
BCOE Guide
Availability 24/7 24/7 24/7 24/7

Platforms supported Web and Web and Web and Web and
Mobile Mobile Mobile Mobile
Natural Language
Yes Yes Yes Yes
processing
Personalized No Yes Yes Yes
response
Integration with Yes No No Yes
college website
Language supported English English, English English
Hindi
Inquire categories Admissions, Admissions, Admissions, Admissions,
Courses, Scholarships Courses, Exams Scholarships
Faculty,
Facilities,
About College

Table 2.2.2 Comparison among Reviewed and Proposed Application

5
3. Planning:

The total time taken for the complete implementation of our project was about 56 days which
roughly measures up to almost 8 weeks. The complete project underwent the phases of
requirement proposal, information planning and collecting, background and alternatives,
system requirements, system test, documentation, and finally deployment.

Fig.3 Work Plan

6
 4. Methodology:

4.1 Project System and Methodology

In this project, the Natural Language Processing (NLP) methodology will be used. Natural
Language Processing (NLP) is a field of artificial intelligence that focuses on the interaction
between human language and computers. NLP algorithms in chatbots enable the bots to
understand and interpret the natural language input from users, and generate appropriate
responses.

 Tokenization:
The first step in NLP is to break down the input text into individual words or tokens. This is
done using tokenization algorithms that identify the boundaries of words and punctuation in
the text.

 Named Entity Recognition:

Named Entity Recognition (NER) is the process of identifying and extracting named entities
such as people, organizations, and locations from the input text. This is done using machine
learning algorithms trained on large amounts of annotated data.

Fig.4.1 Natural Language Processing

7
4.2 System Requirements

4.2.1 Software Requirements

1. Operating system

2. Python

3. Visual studio code

4.2.2 Hardware Requirements

1. Laptop

 Processor: AMD Ryzen 5 5600H with Radeon Graphics 3.30 GHz

 RAM: 8.00 GB
 Graphic Card: NVIDIA GeForce GTX 1650 4GB Graphics
 Hard Disk Storage: 512GB
 Operating System: Windows 11 Home Single Language

4.3 User Requirements

Functional Requirements

1. The system must provide clear information about Admission policy.

2. The system must provide clear and fully detailed information about College.
3. The system must provide clear and fully detailed information about colleges Programs.
4. The system should clarify the duration of study for each Courses.
5. The chatbot should be available 24/7 to provide round-the-clock assistance to users.
6. The chatbot should be able to handle inquiries related to different categories such as
admission, fees, courses, faculty and placements.

8
Non-functional Requirements

1. The system shall handle multiple users inputs, If two or more students are chatting with
the bot, none of the students has to wait too long to be answered by the system.
2. The system should have the appropriate data set. The correct data set is the basis for the
chatbot, when the data set is correct and tuned, the chatbot will be trained on it give the
best possible result.

3. The system should prevent abusive language.

4. The chatbot should be maintainable and easy to update and modify as per changing user
needs and requirements.

9
5. Design of The System

5.1. System Flow-chart:

5.1.1. User Case Diagram:

10
5.1.2. User Case Diagram:

11
5.2 Output And Results:
In this section, execution results of BCOE Guide Chatbots are provided by listing
several functionalities included in this project and explaining these functionalities with the
help of the screenshots.

Fig : 5.2 Output of Program

The results of this project are measured in whether sentiment analysis and active learning is
correctly implemented or not. Sentiment analysis correctly recognizes the user’s query such as
positive, negative, and neutral by storing all the conversations in the database. These results
are used to add empathy to the bot. However, the system was partially successful in adding
empathy to the bot. It is because, although large amount of data was added to include some
common answers to the queries which are off scripts and to add empathy to the bot, since scope
of these queries is vast, the system requires more rigorous data to handle all the questions which
are out of script.

12
5.3 Code:

import random

import json

import pickle

import numpy as np

import nltk

from nltk.stem import WordNetLemmatizer

from tensorflow.keras.models import load_model

lemmatizer = WordNetLemmatizer()

intents = json.loads(open('intents.json').read())

words = pickle.load(open('words.pkl', 'rb'))

classes = pickle.load(open('classes.pkl', 'rb'))

model = load_model('chatbotmodel.h5')

def clean_up_sentence(sentence):

sentence_words = nltk.word_tokenize(sentence)

sentence_words = [lemmatizer.lemmatize(word) for word in sentence_words]

return sentence_words

def bag_of_words(sentence):

sentence_words= clean_up_sentence(sentence)

bag = [0] * len(words)

for w in sentence_words:

for i, word in enumerate(words):

if word == w:

bag[i] = 1

13
 return np.array(bag)

def predict_class(sentence):

bow = bag_of_words(sentence)

res = model.predict(np.array([bow]))[0]

ERROR_THRESHOLD = 0.25

results = [[i,r] for i, r in enumerate(res) if r > ERROR_THRESHOLD]

results.sort(key=lambda x:x[1], reverse=True)

return_list = []

for r in results:

return_list.append({'intent': classes[r[0]], 'probability': str(r[1])})

return return_list

def get_response(intents_list,intents_json):

tag= intents_list[0]['intent']

list_of_intents =intents_json['intents']

for i in list_of_intents:

if i['tag'] == tag:

result = random.choice(i['responses'])

break

return result

print("|============= Welcome to College Equiry Chatbot System! =============|")

print("|=========================Feel Free============================|")

print("|===========================To===============================|")

print("|=============== Ask your any query about our college ================|")

while True:

14
message = input("| You: ")

if message == "bye" or message == "Goodbye":

ints = predict_class(message)

res = get_response(ints, intents)

print("| Bot:", res)

print("|==================The Program End here!=====================|")

exit()

else:

ints = predict_class(message)

res = get_response(ints, intents)

print("| Bot:", res)

15
 6. Experimental Result:
• The Chatbot was tested the chatbot performed efficiently with no errors.

• The code did not crash at any point in time.

• BCOE Guide chatbot was able to reply to each query of user.

• Based on the commands received from the user, the bot replied to it.

• While examining the working of the chat bot, it was found that there is success rate in each

direction of the control.

7. Conclusion:
In conclusion, the BCOE Guide chatbot for college inquiries is a highly useful and efficient
tool that helps students and stakeholders get answers to their queries and concerns about the
college. With its natural language processing capabilities, personalized responses, the chatbot
provides a seamless user experience and reduces the workload of the college staff in handling
routine inquiries.

By meeting both functional and non-functional requirements, the chatbot ensures reliable,
scalable, secure, and accessible assistance to users, while being easy to use and maintain. It is
also compatible with different devices and platforms, making it highly accessible to a wide
range of users.

Overall, the BCOE Guide chatbot is a valuable addition to the college's digital infrastructure,
providing students and stakeholders with an intuitive and efficient way to access information
about the college, and thus enhancing their overall college experience.

16
 8. References:
[1] "Chatbot", en.wikipedia.org, 2010. [Online]. Available:

https://en.wikipedia.org/wiki/Chatbot.

[2] "Chatbot: What is Chatbot? Why are Chatbots Important? -", Expertsystem.com,

2018. [Online]. Available: https://www.expertsystem.com/chatbot/

A guide to Natural Langugage Processing, Available at

https://en.wikipedia.org/wiki/Natural_language_processing

Basics of Natural Language ToolKit, Avalilable at https://www.nltk.org/

"Building Chatbots - A comparison of Rasa-NLU and Dialogflow." 17 Apr. 2018, Building

Chatbots - A comparison of Rasa-NLU and Dialogflow.

Python documentation: https://docs.python.org/3/

NLTK: https://www.nltk.org/

TensorFlow: https://www.tensorflow.org/tutorials

Numpy: https://numpy.org/

Chatterbot : https://chatterbot.readthedocs.io/en/stable/

"LUIS.AI: Automated Machine Learning for Custom Language Understanding",

azure.microsoft.com, 2017. [Online]. Available: https://azure.microsoft.com/en-

us/blog/luis-ai-automated-machine-learning-for-custom-language-

understanding/

17