International Research Journal of Engineering and Technology (IRJET) Volume: 09 Issue: 06 | June 2022
www.irjet.net
e-ISSN: 2395-0056 p-ISSN: 2395-0072
TWITTER SENTIMENT ANALYSIS Mayur Mahajan1, Vijayraj Bhakare2, Aditya Bhure3, Sumeet Patil4, Sarita Patil5 1,2,3,4,5 G
H Raisoni College of Engineering and Management, Wagholi, Pune -----------------------------------------------------------------------***----------------------------------------------------------------------Abstract Nowadays, social media is getting more attention. Public and private opinions on a wide range of topics are constantly expressed and distributed via a variety of social media platforms. Twitter is one of the most prominent social networking platforms. Twitter provides businesses with a quick and effective approach to assess customers' viewpoints on issues that are crucial to market success. Creating a sentiment analysis programme is a method for computing consumer perceptions. This study describes the creation of a sentiment analysis that extracts a large number of tweets. Tweepy, numpy, pandas, textblob, and nltk are some of the Python modules utilised in this project. Results classify customers' perspective via tweets into positive and negative, which is represented in a pie chart and tabular form.
1. Introduction As the internet grows in size, so does its reach to the general public. Twitter, Facebook, and Tumblr are among the most popular social media and microblogging sites for rapidly disseminating concise news and hot topics around the world. When several people contribute their opinions and judgements on a topic or piece of news, it becomes a valuable source of internet perspective on that topic. These themes are usually used to promote political campaigns, public people during elections, commercial endorsements, and entertainment such as award shows and movies. Large corporations and businesses use user feedback on these platforms to improve their goods and services which further help in enhancing marketing strategies. One example is releasing images of the future iPhone in order to generate a buzz and tap into people's emotions in order to advertise the product before it is released. As a result, there is a big opportunity for business-driven applications to uncover and analyse intriguing patterns from the endless social media data. The prediction of emotions in a word, sentence, or corpus of texts is known as sentiment analysis. It's designed to be a tool for deciphering the opinions, attitudes, and feelings stated in an internet comment. The intention is to gain or access an overview of the wider public opinion behind certain topics. Precisely, it is a paradigm of categorizing conversations into positive, negative, or neutral labels. Many people use social media sites for networking with other people and to stay upto-date with news and current events. These sites (Twitter, Facebook, Instagram, google+) offer a platform for people to voice their opinions.
2. Overview Sentiment Analysis is a machine-based way of understanding text that categorises the text's feelings as positive, terrible, or neutral. Performing arts Sentiment Analysis on Twitter data will assist businesses in gaining qualitative insights into how people are talking about their entire. Twitter has grown to become one of the most important social media platforms for news, data, and interaction with brands and influential personalities around the world, with over thirty million active users and a daily average of 500 million tweets.
3. Need Sentiment analysis combined with social media monitoring allows you to determine how invested your target audience is in any emerging trends. And how they feel about the trends in question.
4. Literature Survey Ortigosa and Alvaro et. al [2] proposed a novel method for sentiment analysis in social media behemoth Facebook that supports: (i) extracting useful information about Facebook users' sentiment polarity (whether positive, neutral, or negative) from messages written by users; and (ii) modelling users' normal sentiment polarity and analysing significant emotional changes in users, all based on messages written by users. [3] As proposed by Pak and Alexander et al. Author creates a
© 2022, IRJET
|
Impact Factor value: 7.529
|
ISO 9001:2008 Certified Journal
|
Page 1326