Sentiment Analysis of Twitter

Submitted in partial fulfillment of the requirements for the award of degree of

BACHELOR OF ENGINEERING
IN
COMPUTER SCIENCE & ENGINEERING

Submitted to:
Er. Parul sood

Submitted By:

Name: Rakesh Nagar Name: Apurbo Mitra

UID : 18BCS8050 UID : 18BCS8057

Name: Shivam Kashyap Name: Sonika Negi

UID : 18BCS8044 UID : 18BCS8058

DEPARTMENT OF COMPUTER SCIENCE & ENGINEERING

Chandigarh University, Gharuan
August 2019
 Chapter 04

Screenshots

This is the dashboard of the project from where we can enter the name whose tweets are
searching(eg. Donald trump). After that selecting the number of tweets from that we are
analysing data. And then click the button “ANALYSE”.

This is the webpage where the result is shown of selecting data from the dashboard page. That
page contains the bar graph of the results and detail report of the tweets. It shows the results in
different colour .
 ACKNOWLEDGEMENT

We are thankful to for coordinating our project, constructive evalution , suggestions and giving
us benefits of his substantiate experience. We want to thank the teachers of CHANDIGARH
UNIVERSITY Er. Paroul Sood mam for giving us privilege to undergo our project in their
prominent organization.

We are also very thankful to my college that has encouraged us to though my project
work and help us directly or indirectly in our project.

We work on a project “Sentiment Analysis Techniques of Twitter Data” and gave

user all relevant tasks to perform. And our design system performs that entire task successfully.

The “Sentiment Analysis Techniques of Twitter Data” is the software of

professional models. In many cases , the information about the model goes beyond simple
statistics or biographical details to include complete information about the appearance of the
model in advertisements , magazine covers and fashion shows , as well as information about
their hobbies , official and other websites , and other relevant notes.

NAME:- RAKESH NAGAR

 Abstract
Twitter is a popular social networking website where users posts and interact with messages
known as "tweets". This serves as a mean for individuals to express their thoughts or feelings
about different subjects. Various parties such as consumers and marketers have done sentiment
analysis on such tweets to gather insights into products or to conduct market analysis.
Furthermore, with the recent advancements in machine learning algorithms, the accuracy of our
sentiment analysis predictions can improve. We will attempt to conduct sentiment analysis on
"tweets" using various machine learning algorithms.

Sentiment analysis is also known as “opinion mining” or "Emotion Artificial Intelligence" and
alludes to the utilization of natural language processing (NLP), text mining, computational linguistics,
and bio measurements to methodically recognize, extricate, evaluate, and examine emotional states and
subjective information. Sentiment analysis is generally concerned with the voice in client materials; for
example, surveys and reviews on the Web and web-based social networks.
Sentiment analysis is a process of the deriving sentiment of a particular statement or sentence.
It's a classification technique which derives opinion from the tweets and formulates a sentiment
and based on which, sentiment classification is performed.

Sentiments are subjective to the topic of interest. We are required to formulate what kind of
features will decide for the sentiment it embodies.

Sentiment analysis approaches can be broadly categorized into two classes – lexicon-based and
machine learning-based. Lexicon based approach is unsupervised as it proposes to perform
analysis using lexicons and a scoring method to evaluate opinions. Whereas the machine learning
approach involves the use of feature extraction and training the model using a feature set and
some dataset.

The basic steps for performing sentiment analysis include data collection, pre-processing of data,
feature extraction, selecting baseline features, sentiment detection and performing classification
either using simple computation or else machine learning approaches.