Ndlovu, LungisaniDe Kock, Antonie JMkuzangwe, Nenekazi NPThwala, NtombizodwaMokoena, Chantel JMMatimatjatji, Rethabile J2024-11-272024-11-272023-12978-3-031-66594-3https://doi.org/10.1007/978-3-031-66594-3_19http://hdl.handle.net/10204/13876Continuous monitoring of the risk of civil unrest events and predicting their occurrence is of paramount importance. This task involves identifying and understanding the primary factors that contribute to such events, especially in regions with unique dynamics, such as South Africa. Although many global and South African-specific studies have conducted research on predicting the frequency or probability of these events, there is a notable gap in identifying the influential factors behind them. This study unveiled several contributing factors, including demanding behaviour, power outages, service delivery, wage disputes, acts of violence, gender-based conflicts, and unemployment rates. These factors, individually or collectively, contribute to the complexity of civil unrest in the region. The 2021 South African unrest, also known as the July 2021 riots, the Zuma unrest, or Zuma riots, serves as an example. This event was triggered by the imprisonment of former president Jacob Zuma for contempt of court, inciting his followers to demand his release, a situation aligning with the 'demanding behaviour' influential factor identified in our study. We used advanced data analysis and machine learning techniques to explore these factors. Specifically, the Logit model was used to determine the coefficients that optimally fit the data, establishing significant relationships between these factors and incidents of civil unrest. Our research not only offers insights on influential factors, but also presents a predictive framework. We evaluated logistic regression, support vector clustering, decision tree classifier, and random forest classifier models to predict civil unrest. The results showed that the decision tree and the random forest classifiers perform better, achieving an accuracy of 98%, compared to logistic regression and support vector clustering, which have an accuracy of 97%.FulltextenSouth African civil unrestOpen source intelligenceOSINTMachine learningConference PresentationN/A