You are on page 1of 5

University Automated Chatbot Using Text Classification

with Machine learning and NLP

Ali Shan Muhammad Ali Raja Zayad Sadiq

051-18-129805 051-18-129790 051-18-129820

Supervised by
Supervisor_Name
Ms. Maria Hanif

A Final Year Project Proposal Report is


Submitted in Partial Fulfilment of the
Requirements for the Degree of
Bachelor of Science in [Computer Science | Software Engineering]

Department of Computing & Technology


Iqra University
2021
Chapter 1 Introduction

1.1 Overall Description

In simple words, chat bots aim to understand users’ queries and generate a relevant response to meet users’
needs. Simple chat bots scan users’ input sentences for general keywords, skim through their predefined
list of answers, and provide a response relevant to the user’s query. On the other hand, more modern chat
bots rely on AI and natural language processing (NLP) to recognize users’ intent from the context of their
input and generate correct responses [1].
Educational environments, like all sectors of society, seek to evolve, improve the services and experience
of its members. This implies that several of the university campuses gradually become intelligent campuses
[2]. Smart Campuses are conducive environments where students and campus members interact with each
other to create an ecosystem where all campus resources are focused on meeting the needs of students.
1.1.1. Objectives

The use of text classification for the creation of a user-friendly chatbot, interactive and efficient web
application is one of the key motivating factors. The objectives of our project are as below:
 To provide quick response to save the time of student as well as save the resources.
 To provide good and fast web browsing experience.
 To provide a platform where a student can complain or talk about what they need.
1.1.2 Problem Description

In this modern era of technology, Students want to save their time instead of visiting the Universities to get
some kind of information. Because the Traditional ways are, time consuming, as the students have to visit
the university personally. It would be much more time saving if the student can obtain that information by
staying at home and just visit our web application. Where will be our Chatbot to answer his all questions.
1.1.3 Methodology

In this section, we discuss our proposed solution along with data-set used and ML algorithms
employed. Figure 1 shows an overview of steps followed in this work. We will first collect our
dataset, process the data and use that dataset for training the model. This will involve collection of
all relative data to extract important features from data.
Figure 1 Project flow diagram

1.1.4 Product Scope

We are going to develop a website that can be student friendly and will be easy to use for every
one. This website will provide ease of access to the students who want to join the institution and
also help the newly registered students to explore about the institution.
1.1.5 User Classes and Characteristics

1.1.5.1. Users

Users have the option to get information regarding there queries by talking to
the chatbot.

1.1.5.2. Admin

Admin can grant and revoke privileges of user.

1.1.6 Operating Environment

As stated above our project has two main modules. Module one which is chatbot for which we will
first collect a dataset then by applying we will train and improve this machine learning algorithm
and then again test and improve this system. The second module (web application) shall be user
friendly.
1.1.7 Assumptions and Dependencies

 Sample size of dataset is very important


 Chatbot will answer certain questions not every question.
 Similarly, the language of chatbot will be English so the user should be able to understand
that.

1.2 External Interface Requirements

None

1.2.1 User Interfaces

We plan on using Node JS for the final front-end user interface. Which is user friendly and easy
to use and fast as well.

1.2.2 Communication Interfaces

Rest API

1.3 System Features

Our project has two main modules. Module one which is chatbot for which we will first collect a
dataset then by applying we will train and improve this machine learning algorithm and then again
test and improve this system. The second module (web application) shall be user friendly.

1.3.1 System Feature 1: Chatbot

It is a system which interact with the user and the user interact with it by using the modern
techniques of NLP and by using machine learning algorithms and the dataset it will answer the
questions of the user.

1.3.2 System Feature 2: University Website

The second module makes the user able to interact with the chatbot this module will be made by
Node JS which is quite fast and will provide the user a quick and interactive interface.

1.4 Nonfunctional Requirements


Non-functional Requirements refer to the constraints or restrictions on the system. They

include emergent system properties such as reliability, response time and store

occupancy or the platform, implementation techniques and tools.

Following are some nonfunctional requirements

1.4.1 Performance Requirements

All data used to train the models must be up to mark and no flaws.

1.4.2 Safety Requirements

Our project is a machine learning based project; our aim is to provide user correct information.

1.4.3 Security Requirements

Data security is our foremost priority and security is at the forefront when designing the system

1.4.4 Software Quality Attributes

Real Time Details available


Security Strong

You might also like