Detection of Islamophobic Tweets on Twitter Using Sentiment Analysis

Abstract

Social networks, becoming more accessible as the Internet usage increases, have turned into platforms where people share their feelings and opinions on various subjects. The 90 per cent of the data we have today has been generated over the past two years. Yet, carrying out traditional analyses through this data might take days, if not months. Therefore, emotional analyses are preferred to be made via social networks by means of machine learning. Tweets on Twitter are sought to be found out whether they are Islamophobic or not by using emotion analysis. Estimations are made using precision, recall and F1 measures via models trained with linear ridge model. In the end, accurate results, in the range of 96.3 per cent to 96.5 per cent on average, are obtained for positive tweets.

Keywords

• Sentiment analysis
• Islamophobia
• Twitter
• Mahine Learning
• Machine learning