Sentiment Analysis of Tweets on Telangana State Government Flagship Schemes

Abstract

Over the last decade, the usage of social media has evolved to a greater extent. Today, social media platforms like Twitter, facebook, snapchat are vastly used to incept the opinions of public about a particular entity. Social media has become a great source of text data. Text analytics plays a crucial role on social media data to give answers to a wide variety of questions about public feedback on many issues or topics. The primary objective of this work is to analyse the public opinion or sentiment in social media on Telangana state government welfare schemes. The purpose of sentiment analysis is to find opinions from tweets and extract sentiments from them and find their polarity, i.e., positive, neutral or negative. Here we are using twitter as it has gained much popularity and media attention. The first step is to extract the tweets on particular schemes through Twitter API and Python language followed by cleaning and pre- processing steps of the raw tweets. Then tfidf vectorizer was invoked for feature extraction and creation of bag of words and finally sentiment polarity scores were obtained by using VADER (Valence Aware Dictionary and sentiment Reasoner), lexicon and rule-based sentiment analysis tool.