TWITTER SENTIMENT ANALYSIS.

PROJECT SYNOPSIS
OF MINI PROJECT

BACHELOR OF TECHNOLOGY
CSE(DS)

SUBMITTED BY GUIDED BY
SARANSH SHARMA Ms. Mimansha Singh
2000321540052 Assistant Professor
DEEP SHARAN
2000321540025

ABES ENGINEERING COLLEGE

GHAZIABAD
2020-2024

AFFILIATED TO
DR. A.P.J. ABDUL KALAM TECHNICAL
UNIVERSITY U.P., LUCKNOW
 STUDENT’S DECLARATION

I / we hereby declare that the work being presented in this report entitled “Twitter
Sentimental Analysis.” is an authentic record of my/ our own work carried out under the
supervision of Mr. Prabhat Singh, Assistant Professor, CSE-DS. The matter embodied
in this report has not been submitted by us for the award of any other degree.

Date:

Signature of student Signature of student

Name: Saransh Sharma Name: Deep Sharan

Roll No.2000321540052 Roll No.2000321540025

Department: CSE-DS Department: CSE-DS

This is to certify that the above statement made by the candidate(s) is correct to the best
of my knowledge.

Signature of HOD Signature of Supervisor

…………………… Mr. Prabhat Singh

CSE-DS Assistant Professor

Date: CSE-DS

i
 ACKNOWLEDGEMENT

We would like to convey our sincere thanks to Ms. Mimansha Singh for giving the
motivation, knowledge and support throughout the course of the project. The continuous
support helps in a successful completion of project. The knowledge provided is very
useful for us.
We also like to give a special thanks to the department of Information and Technology
for giving us the continuous support and opportunities for fulfilling our project.

We would also like to extend our sincere obligation to Mr. Prabhat Singh, Head
of Department, CSE(DS) for providing this opportunity to us.

Signature of student Signature of student

Saransh Sharma Deep Sharan

2000321540052 2000321540025

ii
iii
 ABSTRACT

The dossier determined by family, or the users of the public -

socializing for professional or personal gain scene, has transformed on
account of the behaviour of different types of public socializing for
professional or personal gain sites, like Instagram, Twitter, Snap-Chat,
the use of friendly socializing for professional or personal gain sites is
increasing rapidly. It can create heaps or possibly a lot of data points.
Text, program, or visual and audio entertainment transmitted via radio
waves content is situated continually. This is on account of the
experience that a certain site has heaps of consumers.
These consumers begoing express their ideas and belief on anything
subject they select. Even few of these consumers post inefficiently.
These posts are brief; as a result, they are only destined to indicate
individual consumer's outlook on a particular subject. In this essay, we
attempt to collect the affections that hold in check these posts. Twitter
has existed picked as our public networking program for this. Tweets
are the posts on this friendly socializing for professional or personal
gain section. In this work, we study approaches for cleaning and
culling twitter data using Python so that conclude the sentiments latent
tweets. After that, we use a classifier to train and determine the data.

1
 CHAPTER 1
INTRODUCTION
Today's earth has mutated microblogging sites into a lake of dossier
that analysts can use. This is on account of the case that the most of
crowd in contemporary's institution use a microblogging podium to
express all of their excitement for differing affairs. It wouldn't do wrong
to desire that all the one has approach to these microblogging sites
immediately has a right to freedom of speech by some means. In
actual time for action or event, public from everywhere the realm are
free to talk, comment, and express their hopes on some subject of
their choice. These blogs generally involve illnesses or verbalizations
of appreciation concerning some issue of me's selecting. They benefit
from appropriating a fair appraisal of their trade or crop, that
authorizes ruling class to learn advantageous position for those selling
and the changes that need expected fashioned in consideration of
specify better merchandise from now on. Therefore, if belief study
maybe used to these microblogging sites, maybe implicit from the
reason above that they commit benefit a assortment of organisations,
two together public and private. An active form for trying many
websites place things issue their plans on a material of interest is
emotion reasoning, frequently famous as reasoning of impressions.
With the use concerning this type of study, trades can determine what
shoppers consider a particular system or brand that interests
bureaucracy by examination their comments, tweets, or reviews.

2
 CHAPTER 2

RELATED WORK

The connected work guide our project is likely beneath:

1.1. Existing Approaches

 Twitter Sentiment Analysis using Python:

 To do the emotion analysis of twitter tweets using python and find

the positive and negative tweets percentage [5].

 Word repetitiveness and sentiment study of twitter tweets during Coronavirus

pandemic in the world [9]

 To find the repetitiveness of each discussion and do the sentiment

study of the universal pandemic dataset [2].

1.2. Comparative Analysis of Existing Works

 In the existing projects, the words with positive or negative polarity are obtained

but our project we are obtaining the polarity of the overall data set.

 In existing projects, it is not specified that which machine learning model is best

for sentiment analysis but in our project we will be determining that too.

3
 CHAPTER 3

PROJECT OBJECTIVE

 This project will analyze the emotions of people.

 To implement an algorithm for automatic classification of tweets into positive,

negative or neutral.

 This project will resolve various Algorithms and finds the individual

accompanying best veracity.

4
 CHAPTER 4

PROJECTED METHODOLOGY

The projected methods had connection with our project is likely beneath:

Step 1: Identify the legendary hashtags all the while the universal in India on Twitter.

Tweets under those hashtags are derived from the Twitter API applying Tweepy study.

Step 2: The preprocessing of the dataset is finished. It includes the following steps:

 Removal of hashtags.
 Removal of links, gifs, emoji, concepts and distinguished figures.
 Removal of stop conversation.
 Removal of non-English letters.
 Lemmatization
Step 3: Analyzing the antinomy of the dataset.

Step 4: Giving the step 3 result in different machine intelligence algorithms and analyze it
to find the algorithm accompanying best preciseness.

Step 5: The results are displayed using various charts.

Extraction of Dataset from Twitter API

Pre-processing of Data to remove special characters, punctuations, Stop Words and Images

Processing of Data to analyze the polarity of the Dataset

To use Algorithm and find which fits best for performing Sentiment Analysis

Results

Fig.1. Projected Approach

5
 CHAPTER 5

DESIGN AND EXERCISE

The design and exercise of our project is in this manner:

5.1. Work Flow Diagram

These dataset have been derived from Twitter API utilizing the tweepy library in
python. Python library Numpy is secondhand for the mathematical computing and
pandas is used for the evidence manipulation. Natural Language Toolkit is used for
the preprocessing of the dataset. Text Blob library is used for orthography checks
and resolving the sentiments.
Matplotlib is used for the graphical representation of results.

Fig.2. Work Flow Diagram

6
 CHAPTER 6

RESULTS AND DISCUSSION

The output we received from evaluating the tweets is likely beneath in Fig.3.

Fig.3. Proportion of positive +, negative - and neutral tweets.

Fig.3. shows that 46.0 % of the total tweets are neutral (Orange), about 17.5% tweets are

negative (Blue) and 36.5% tweets are positive (Green).

7
 CHAPTER 7

CONCLUSION AND FUTURE SCOPE

 The project will present the overall opposition score of Tweets and will find which

is the best Algorithm for operating Sentiment Analysis.

 From the studies of the tweets, we note that most of the people as political feel

neutral, certain positive or negative.

 In future we will be planning to perform the analysis on various other social

platforms Instagram, Facebook, etc. and also try to further classify the sentiments.

8
 REFERENCES

[1] Medford, R. J., Saleh, S. N., Sumarsono, A., Perl, T. M., & Lehmann, C. U. (2020). An"
Infodemic": Leveraging High-Volume Twitter Data to Understand Public Sentiment
Outbreak. medRxiv.

[2] Rajput, N. K., Grover, B. A., & Rathi, V. K. (2020). Word repetitiveness and
sentiment study of twitter messages . arXiv preprint arXiv:2004.03925.

[3] Samuel, J., Ali, G. G., Rahman, M., Esawi, E., & Samuel, Y. (2020). Covid-19 public
sentiment insights and machine learning for tweets classification. Information, 11(6), 314.

[4] Kumar, A., Khan, S. U., & Kalra, A. (2020): a sentiment analysis. European
Heart Journal.

[5] Ahuja, S., & Dubey, G. (2017, August). Sentiment analysis on Twitter data. In 2017
2nd International Conference on Telecommunication and Networks (TEL- NET) (pp. 1-
5). IEEE.

[6] Suman, C., Saha, S., Bhattacharyya, P., & Chaudhari, R. S. (2020). Emoji Helps! A
Multi-modal Siamese Architecture for Tweet User Verification. Cognitive Computation, 1-
16