PROJECT REPORT

on
Sentiment Analysis in Hindi Language
for
Digipodium
towards partial fulfillment of the requirement
for the award of degree of

Bachelor of Computer Application

from

Babu Banarasi Das University

Lucknow

Developed and Submitted by Under Guidance of

Himani Raj Zaid Kamil
Deepak Vishwakarma

Academic Session 2018 - 19

School of Computer Applications

I Floor, H-Block, BBDU, BBD City, Faizabad Road, Lucknow (U. P.) INDIA 226028
PHONE: HEAD: 0522-3911127, 3911321 Dept. Adm. & Exam Cell: 0522-3911326 Dept. T&P Cell: 0522-3911128; E-Mail: head.sca@gmail.com
 Babu Banarasi Das University
Lucknow
CERTIFICATE
This is to certify that Project Report entitled

Sentiment Analysis in Hindi Language

being submitted by

Himani Raj and Deepak Vishwakarma

towards the partial fulfillment of the requirement
for the award of the degree of
Bachelor of Computer Applications
to
Babu Banarasi Das University
Lucknow
in the Academic Year 2018-19 is a record of the
student’s own work carried out at Digipodium
and to the best of our knowledge the work reported herein does not
form a part of any other thesis or work on the basis of which degree
or award was conferred on an earlier occasion to this or any other
candidate.

Prabhash Ch. Pathak

HEAD (School of Computer Applications)
 ACKNOWLEDGEMENT

I have taken efforts in this project. However, it would not have been
possible without the kind support and help of many individuals and
organizations. I would like to extend my sincere thanks to all of them.

I am highly indebted to DIGIPODIUM INSTITUTE for their

guidance and constant supervision as well as for providing necessary
information regarding the project & also for their support in
completing the project.

I would like to express my gratitude towards my friends & member

of DIGIPODIUM for their kind co-operation and encouragement
which help me in completion of this project.

I would like to express my special gratitude towards my friends & member

of DIGIPODIUM for their kind co-operation and encouragement which help
me in completion of this project.

I would like to express my special gratitude and thanks to group members for
giving me such attention and time.

My thanks and appreciations also go to my colleague in developing the project

and people who have willingly helped me out with their abilities
DECLARATION
DECLARATION
I Himani Raj and Deepak Vishwakarma hereby declare that this project report
entitled Sentiment Analysis in Hindi Language submitted by us, under the
guidance of Mr. Zaid Kamil of DIGIPODIUM INSTITUTE, LUCKNOW is our
own and has not been submitted to any other University or Institute or published
earlier.

Signature of Student :
Himani Raj
Deepak Vishwakarma
BCA VIth Semester
Date:
 ABSTRACT
Sentiment analysis in Hindi Language is the field of study that analyzes people's
opinions, sentiments, evaluations, attitudes, and emotions from written hindi language.
Sentiment analysis is one of the most active research areas in natural language
processing and is also widely studied in Data mining, Web mining, and Text mining.

In fact, this research has spread outside of computer science to the management
sciences and social sciences due to its importance to business and society as a whole.
The growing importance of sentiment analysis coincides with the growth of social
media such as reviews, forum discussions, blogs, micro-blogs, Twitter, and social
networks.

In the implemented system, Hindi sentences are collected and sentiment analysis is
performed on them to get the polarity of the given Hindi sentences as positive,
negative or neutral.
 TABLE OF CONTENT

1. Problem Statement
2. Introduction
2.1. What is Sentiment?
2.2. Examples of Sentiment
3. Objectives
4. Scope
5. Proposed System
6. Feasibility Study
7. Planning Steps
8. Development Life Cycle Model
9. Module Description
10. Resources To be used:
10.1. Hardware Requirements
10.2. Software Requirements
11. Use Case Diagram
12. Class Diagram
13. Activity Diagram
14. Screenshots
15. Conclusions
 INTRODUCTION OF PROJECT

Sentiment analysis is the process of using natural language processing, text analysis, and statistics
to analyze customer sentiment. The best businesses understand the sentiment of their customers—
what people are saying, how they’re saying it, and what they mean. 

Customer sentiment can be found in tweets, comments, reviews, or other places where people
mention your brand. Sentiment Analysis is the domain of understanding these emotions with
software, and it’s a must-understand for developers and business leaders in a modern workplace.

Since customers express their thoughts and feelings more openly than ever before, sentiment
analysis is becoming an essential tool to monitor and understand that sentiment.

So, sentiment analysis is a natural language processing task that deals with automated extraction of
subjective content from digital text and predicting the subjectivity such as positive, negative or
neutral
 NEED
OF
IDENTIFICATION

Objective:
This project aims to analyze and predict the sentiment of the Hindi
sentences as positive, negative or neutral.
 To evaluate the persons opinion
 To determine the emotional tone behind the series of the word
 implement in algorithm for automatic classification of text into
positive /negative
 To teach the machine to analyse the various grammatical nuances.

Scope:
 It can be very effective in predicting movie review, websites etc.
 Brand Monitoring
 Keeping an Eye on Your Competition
 Reviews of digital platforms can be also used to give useful data
which can be used to predict future
 Proposed System

Datasets acquiring: Getting the right data means gathering or identifying

the data that correlates with the outcomes you want to predict.

Data pre-processing: It is a process of preparing the raw data and making it

suitable for a machine learning model.

Dataset as input: It is the process in which the input is given and the training of the model is done.

Filtering using Model: In this process the filtration is done using the model of which the sentiment is
to identify.

Classifying the data: In this process the classification is observed whether the sentiment is positive,
negative or, neutral.

Output: The sentiment analysis’s result is obtained so as we get the sentiment.

 PROBLEM STATEMENT

Majority of the existing work in this field is in English but our work is a foray into
sentiment analysis for Hindi.

The problem in Hindi sentiment analysis is classifying the polarity of a given text in
document, sentence etc.

Whether the expressed opinion in a document, a sentence or an entity feature aspect

is positive, negative or neutral.
 System Analysis

System Design
Spiral model is a combination of sequential and prototype model. This model is best
used for large projects which involves continuous enhancements. There are specific
activities which are done in one iteration (spiral) where the output is a small prototype
of the large software. The same activities are then repeated for all the spirals till the
entire software is build.
Spiral Model
 FEASIBILITY
STUDY
A feasibility study is an assessment of the practicality of a proposed project or system.
A feasibility study aims to objectively and rationally uncover the strength and
weaknesses of an existing project.
The feasibility report of the project holds the advantages and flexibility of
the project.
This is divided into three sections:-
 Technical Feasibility
 Economic Feasibility
 Operational Feasibility

Technical Feasibility
This assessment focuses on the technical resources available to the organization. Its
helps organization determine whether the technical resources meet capacity and
whether the technical team is capable of converting the ideas into working system

Economic Feasibility
This assessment typically involves a cost/benefits analysis of the project, helping
organizations determine the viability, cost, and benefits associated with a project
before financial resources are allocated.

Operational Feasibility
This assessment involves undertaking a study to analyse and determine whether—and
how well—the organization’s needs can be met by completing the project. Operational
feasibility studies also examine how a project plan satisfies the requirements identified
 Modules

1. Data collection
2. Text Processing and tokenization
3. Lemmatization & Vectorization
4. Feature Extraction
5. Model Creation
6. Model Training
7. Model Evaluation and Testing
8. Database Manager
9. View Display Manager
10. Setting system
In this project two members are involved and so we have divided the whole
project into two groups:-

The following modules are handled by Deepak Vishwakarma:-

■ Data collection

■ Text Processing and tokenization

■ Lemmatization & Vectorization.

■ Feature Extraction

■ Model Creation

The following modules are handled by Himani Raj:-

■ Model Training

■ Model Evaluation and Training

■ Database Manager

■ View Display Manager

■ Setting System
Use case Diagram
Class Diagram
Activity Diagram
 Module Description
• Data Collection: A data set is a collection of data. As we need training data set to analysis so
it is the actual data set used to train the model for performing various actions.

• Text Processing and tokenization: Text processing modules will contain that concept in
which the coding for breaking, cleaning and analyzing the text, word into different segments.

• Lemmatization & Vectorization: In this modules all the words are converted into simple
forms by finding their particular tense then they are charged in numbers form by using
vectorization process.

• Feature Extraction: This module helps us to select all the important columns which are
necessary for prediction.

• Model Creation: In this module we write our code for the program.

• Model Training: Model Training in the process of feeding an ML algorithm with data to
help to identify and learn good values for all attributes involved. So we will be using several
types of machine learning models, of which the most common ones are supervised.

• Model Evaluation and Testing: Model evaluation aims to estimate the generalization
accuracy of a model on future data. Moreover the models will be primarily used for testing the
model performance in terms of accuracy/precision of the model.
• Database Manager: As understood by name, database manager manages database. It can
create, add, and store the data.

• View Display Manager: This module will contain code related to frontend of the
application we are creating.

• Setting System: This module contains all the setting regarding the project
 SOFTWARE
REQUIREMENT SPECIFICATION

Gantt Chart
A Gantt chart is popular type of chart that illustrates a project schedule. Gantt
Chart illustrates the start and finish dates of the terminal elements and
summary elements of a project. Terminal element and summary comprise the
work breakdown structure of the project.

Task 4Feb- 28Feb- 10Mar- 13Apr- 17May- 22May-

28Feb 9Mar 12Apr 16May 22May 28May
Develop
project proposal 27 days

Analysis
10 days
Designing
30 days
Coding
34days
Unit Testing
5 days
Implementation
5 days
Functional Requirements:

SR. REQ. PRIORITY REQUIREMENTS

NO NO.

1. R1 R Start application

2. R2 R Input through text sentence.

3. R3 R prediction

4. R4 R View Records.

Non Functional Requirements:

CATEGORY NON FUNCTIONAL

REQUIREMENTS

USABILITY Users must be able to install the app

RELIABILITY App permission would be important and will not use

any private data of users

PERFORMANCE The will able to give good perform on most of the OS

SUPPORTABILITY This software supports all windows above windows 7

OPERATION All the operations performed by user settings in

the software
 Software Requirement

Client Side
 Web Browser (Google Chrome, Firefox, IE9 or above)

Developer Side
 Web Browser (Google Chrome, Firefox, IE9 or above)
 Python 3.7 or above
 Vs code
 SQLite manger
 Libraries
8. Hardware Requirements:

CLIENT SIDE

Processor Dual Core or above

RAM 2 GB
Disk space 500 GB
Monitor 14”
Others Keyboard, mouse, Internet
Connection

SERVER SIDE
Processor Dual Core or above
RAM 4 GB or above
Disk space 500 GB
Monitor 14”
Others Keyboard, mouse, Internet
Connection
Screenshots
(Database)