Prediction of Twitter Sentiment Analysis by Using Naive Bayes Algorithm

Abstract

The purpose of our study is to do a sentiment
analysis of tweets to determine whether they
are positive, negative, or neutral. Many
businesses use sentiment analysis to
determine how well their products and
companies are performing in the
marketplace. In a burgeoning discipline,
sentiment analysis is now being used to
predict the outcome of political elections and
polls. Twitter is an internet platform that
allows users to send tweets with a maximum
of 140 characters. We intend to get a
representation of public opinion by analyzing
the sentiments conveyed in the tweets due to
the enormous amount of data we are using.
This research investigates sentiment analysis,
which involves extracting many tweets and
analyzing them using a machine-learning
technique like the naive Bayes classifier.
Results are classified as several positive,
negative or neutral and it is also expressed in
the pie chart and bar chart. With the speedup development of websites, informal
organizations, websites, online entries,
surveys, feelings, proposals, evaluations, and
criticism are created by scholars. This author
created opinion content that can be about
books, individuals, lodgings, items, research,
occasions, and so on. These sentiments
become extremely useful for organizations,
state-run administrations, and people. While
this content is intended to be helpful, a
greater part of this essayist's produced
content requires utilizing the message mining
procedures and feel analysis. In any case,
there are a few difficulties confronting the
opinion examination and assessment process.
These difficulties become snags in dissecting
the exact significance of feelings and
distinguishing the appropriate opinion
extremity. Opinion analysis is the act of
applying regular language handling and text
examination strategies to recognize and
remove abstract data from text. This paper
presents a review of the feeling examination
challenges pertinent to their methodologies
and strategies