Sentiment Analysis of Political Tweets for Israel using Machine Learning

TL;DR

This paper analyzes Israeli political tweets to interpret public opinion on the Palestinian-Israeli conflict using machine learning algorithms, providing insights into ethnic and leadership attitudes.

Contribution

It introduces an analytical approach applying machine learning to Israeli political Twitter data for sentiment analysis on a specific geopolitical issue.

Findings

Support Vector Classifier achieved the highest accuracy.

Naive Bayes provided faster processing times.

Decision Tree offered interpretable decision rules.

Abstract

Sentiment Analysis is a vital research topic in the field of Computer Science. With the accelerated development of Information Technology and social networks, a massive amount of data related to comment texts has been generated on web applications or social media platforms like Twitter. Due to this, people have actively started proliferating general information and the information related to political opinions, which becomes an important reason for analyzing public reactions. Most researchers have used social media specifics or contents to analyze and predict public opinion concerning political events. This research proposes an analytical study using Israeli political Twitter data to interpret public opinion towards the Palestinian-Israeli conflict. The attitudes of ethnic groups and opinion leaders in the form of tweets are analyzed using Machine Learning algorithms like Support Vector Classifier (SVC), Decision Tree (DT), and Naive Bayes (NB). Finally, a comparative analysis is done based on experimental results from different models.