Semi-supervised learning approaches for predicting South African political sentiment for local government elections

TL;DR

This paper employs a semi-supervised, graph-based method to analyze Twitter sentiments during South African local elections, revealing predominantly negative opinions especially towards the ANC, with insights into underlying concerns.

Contribution

It introduces a semi-supervised, graph-based approach for sentiment classification and topic extraction in South African political Twitter data, addressing data labeling challenges.

Findings

Overall negative sentiment towards all four parties

Most negative sentiment directed at ANC

Corruption and loadshedding are key concerns

Abstract

This study aims to understand the South African political context by analysing the sentiments shared on Twitter during the local government elections. An emphasis on the analysis was placed on understanding the discussions led around four predominant political parties ANC, DA, EFF and ActionSA. A semi-supervised approach by means of a graph-based technique to label the vast accessible Twitter data for the classification of tweets into negative and positive sentiment was used. The tweets expressing negative sentiment were further analysed through latent topic extraction to uncover hidden topics of concern associated with each of the political parties. Our findings demonstrated that the general sentiment across South African Twitter users is negative towards all four predominant parties with the worst negative sentiment among users projected towards the current ruling party, ANC, relating to concerns cantered around corruption, incompetence and loadshedding.