Moodley, AvashlinMarivate, Vukosi N2020-01-312020-01-312019-11Moodley, A., and Marivate, V.N. 2019. Topic modelling of news articles for two consecutive elections in South Africa. 6th International Conference on Soft Computing & Machine Intelligence (ISCMI 2019), University of Johannesburg, South Africa, 19-20 November 2019, 5pp.http://www.iscmi.us/ISCMI2019_Program.pdfhttp://www.wikicfp.com/cfp/servlet/event.showcfp?eventid=85763http://www.iscmi.us/ISCMI2019.htmlhttp://hdl.handle.net/10204/11291Paper presented at the 6th International Conference on Soft Computing & Machine Intelligence (ISCMI 2019), University of Johannesburg, South Africa, 19-20 November 2019.In election cycles, the political-themed articles published by news providers present a rich source of information about election discourse. Extracting useful themes from a large article corpus manually is infeasible, text mining techniques such as topic modelling provide a mechanism to automatically infer themes from a corpus of text. Exploring the coverage of a single election period uncovers topical discourse that is relevant to current affairs in that election period. Analysing two consecutive election periods allows one to analyse the evolution of discourse from one period to another. Articles published by News24 were sourced to conduct the analysis and answer the research questions set forth. The articles were cleaned and topic models were built to identify 20 latent topics. The articles are classified with their topic before a pairwise cosine similarity comparison is applied on topic corpora to identify similar topics between election periods. The results of this study provide important insights relating to the two election periods, some of these include: coverage of corruption related content is consistent between the two election periods and most political-themed articles in this corpus address problematic themes.enNatural language processingElectionsTopic modellingCosine similarityTopic modelling of news articles for two consecutive elections in South AfricaConference PresentationMoodley, A., & Marivate, V. N. (2019). Topic modelling of news articles for two consecutive elections in South Africa. ISCMI. http://hdl.handle.net/10204/11291Moodley, Avashlin, and Vukosi N Marivate. "Topic modelling of news articles for two consecutive elections in South Africa." (2019): http://hdl.handle.net/10204/11291Moodley A, Marivate VN, Topic modelling of news articles for two consecutive elections in South Africa; ISCMI; 2019. http://hdl.handle.net/10204/11291 .TY - Conference Presentation AU - Moodley, Avashlin AU - Marivate, Vukosi N AB - In election cycles, the political-themed articles published by news providers present a rich source of information about election discourse. Extracting useful themes from a large article corpus manually is infeasible, text mining techniques such as topic modelling provide a mechanism to automatically infer themes from a corpus of text. Exploring the coverage of a single election period uncovers topical discourse that is relevant to current affairs in that election period. Analysing two consecutive election periods allows one to analyse the evolution of discourse from one period to another. Articles published by News24 were sourced to conduct the analysis and answer the research questions set forth. The articles were cleaned and topic models were built to identify 20 latent topics. The articles are classified with their topic before a pairwise cosine similarity comparison is applied on topic corpora to identify similar topics between election periods. The results of this study provide important insights relating to the two election periods, some of these include: coverage of corruption related content is consistent between the two election periods and most political-themed articles in this corpus address problematic themes. DA - 2019-11 DB - ResearchSpace DP - CSIR KW - Natural language processing KW - Elections KW - Topic modelling KW - Cosine similarity LK - https://researchspace.csir.co.za PY - 2019 T1 - Topic modelling of news articles for two consecutive elections in South Africa TI - Topic modelling of news articles for two consecutive elections in South Africa UR - http://hdl.handle.net/10204/11291 ER -