Abstract: This study presents an empirical analysis of appellate copyright jurisprudence in South Africa using data science techniques to model outcome sentiments. The study seeks to determine whether there are any patterns or trends in the outcomes that may be found through quantitative analysis in order to better understand how copyright matters are handled in South African appellate courts. To achieve this, a dataset of selected appellate copyright cases from the South African courts is collected and coded based on various factors, including the nature of the dispute, the legal issues at stake, and the outcome of the case. Sentiment analysis techniques are then applied to the dataset to model the sentiment of the court's decision in each case using transformers’ pre-trained models, allowing for the identification of patterns and trends in the outcomes. The results of the study provide valuable insights into the nature of copyright jurisprudence in South Africa and demonstrate the potential of data science techniques for analyzing legal outcomes.