Inferring Political Alignments of Twitter Users: A case study on 2017 Turkish constitutional referendum

TL;DR

This study develops machine learning models to accurately infer the political orientations of Twitter users during the 2017 Turkish constitutional referendum, highlighting the effectiveness of semantic and full-text features.

Contribution

It introduces a novel dataset and compares various feature types, demonstrating high accuracy in predicting political alignments using SVM classifiers.

Findings

Semantic features yield 89.9% accuracy

Full-text features outperform hashtag-based models

Language use differences may influence prediction accuracy

Abstract

Increasing popularity of Twitter in politics is subject to commercial and academic interest. To fully exploit the merits of this platform, reaching the target audience with desired political leanings is critical. This paper extends the research on inferring political orientations of Twitter users to the case of 2017 Turkish constitutional referendum. After constructing a targeted dataset of tweets, we explore several types of potential features to build accurate machine learning based predictive models. In our experiments, a three-class support vector machine (SVM) classifier trained on semantic features achieves the best accuracy score of 89.9%. Moreover, an SVM classifier trained on full-text features performs better than an SVM classifier trained on hashtags, with respective accuracy scores of 89.05% and 85.9%. Relatively high accuracy scores obtained by full-text features may point to differences in language use, which deserves further research.