Inferring Political Preferences from Twitter

TL;DR

This paper explores political sentiment analysis on Twitter during the 2020 Delhi Elections, using classical machine learning to classify political opinions, with Support Vector Machines showing the best results.

Contribution

It demonstrates the application of classical machine learning algorithms, especially SVM, for political sentiment classification on Twitter data in an election context.

Findings

Support Vector Machines outperform other classifiers

Twitter data effectively used for political opinion analysis

Classical machine learning methods are viable for domain-specific sentiment analysis

Abstract

Sentiment analysis is the task of automatic analysis of opinions and emotions of users towards an entity or some aspect of that entity. Political Sentiment Analysis of social media helps the political strategists to scrutinize the performance of a party or candidate and improvise their weaknesses far before the actual elections. During the time of elections, the social networks get flooded with blogs, chats, debates and discussions about the prospects of political parties and politicians. The amount of data generated is much large to study, analyze and draw inferences using the latest techniques. Twitter is one of the most popular social media platforms enables us to perform domain-specific data preparation. In this work, we chose to identify the inclination of political opinions present in Tweets by modelling it as a text classification problem using classical machine learning. The tweets related to the Delhi Elections in 2020 are extracted and employed for the task. Among the several algorithms, we observe that Support Vector Machines portrays the best performance.