oriolao/AbusiveLanguage

Abusive Language of African on Twitter # AbusiveLanguage Abusive Language of South Africans on Twitter The project focuses on automatic detection of South African Abusive Language on Twitter. Surface-level features such as N-gram, negative sentiments, syntactic features are explored. Static Word Embeddings and contextual word embeddings are also used. Both semi-supervised learning and supervised machine learning techniques are explored. Publication include: 1. Oriola, O., & Kotzé, E. (2019). Automatic Detection of Abusive South African Tweets using a Semi-Supervised Learning Approach. Proceedings of Forum for Artificial Intelligence Research 2019, 1-13, 4-6 December 2019, Cape Town, South Africa. ceur-ws.org Oriola, O., & Kotzé, E. (2019). Automatic Detection of Toxic South African Tweets using Support Vector Machines with N-Gram Features. Proceedings of the 6th International Conference on Soft Computing & Machine Intelligence (ISCMI 2019), 126-130., 19-20 November 2019, Johannesburg, South Africa. doi.org Oriola, O., & Kotzé E. (2020). Evaluating Machine Learning Techniques for Detecting Offensive and Hate Speech in South African Tweets, IEEE Access, 8, 21496-21509. doi.org Oriola, O., & Kotzé E. (2020). Improved semi-supervised learning technique for automatic detection of South African abusive language on Twitter. South African Computer Journal, 32(2),1-24. doi.org Oriola, O. & Kotzé, E. (2022). Exploring Neural Embeddings and Transformers for Isolation of Offensive and Hate Speech in South African Social Media Space, in Gervasi O. et al. (Eds.): ICCSA 2022, LNCS 13375, pp. 1–13, 2022. doi.org.