Sentiment Analysis of Twitter

Abstract

Hate Speech is a widespread problem that degrades a person or people based on their race, religion, gender or disability. This research work proposes a tool to raise awareness on the persistent hate speech in social media platforms. The primary aim of this research work is to highlight the content that promotes violence or hatred against individuals or groups based on religion, gender or ethnicity. Logistic regression is a technique borrowed by machine learning from the field of statistics. It is the go-to method for binary classification problems. Using this algorithm, the model trains itself from the dataset and identifies and displays the sentiment of the tweets. Also, to get the real-time analysis on tweets, Twitter API and libraries such as Tweepy and Textblob are used. The proposed model has the ability to detect the appropriate sentiment with 83.98 percent accuracy. The tool is made free and available for demo use to thepublic

New Education Policy 2020: A Sentiment Classification

“…Highlight the content that promotes violence or hatred against individuals or groups based on religion, gender or ethnicity by analysing the sentiments of tweets. Logistic regression algorithm was used to detect the appropriate sentiments with 83.98% accuracy (15) .…”