Shedding Light on Loadshedding with Natural Language Processing: A social media case study on public perspectives of the South African electricity crisis in 2022

Abstract

In times of collective discomfort and dissatisfaction, people often find solace in shared adversity on social media platforms like X (formerly known as Twitter). These platforms offer a unique window into the public’s emotions andviewpoints concerning common challenges. I n2022, South Africa experienced an electricity crisis, during which the country was subjectedto rolling blackouts, commonly known as load-shedding, by Eskom, the country’s primary electricity provider, to prevent a national electricity grid shutdown. This study conducted adata-driven exploration of the public discourse surrounding Eskom and loadshedding on X using natural language processing and data science techniques. The dataset utilised for thisstudy comprised tweets containing keywords related to Eskom and loadshedding. The studydelved into the topics of discussion by applying topic modelling techniques to uncover latent themes within the discourse. The topics were analysed through a multifaceted lens to unpack and highlight patterns within the sentiments, emotions and biases that underpin conversations related to loadshedding and Eskom. A notable inclusion in the analysis was the incorporation of sarcasm classifications,which enhanced the interpretation of the emotion and sentiment within the topics discussed.The findings uncovered from the analysis were contrasted with loadshedding-related events in 2022 to understand the public discourse as the electricity crisis escalated. The methodologyof this study provides a framework for utilising natural language processing techniques touncover and examine the perspectives of a collective within discourse related to events of shared interest.