Prasanna Kumar Kumaresan
PhD NLP researcher focusing on hate speech in under-resourced languages
Summary
Work
Education
Projects
Writing
Dataset for Identification of Homophobia and Transphobia for Telugu, Kannada, and Gujarati
January 1, 2024Introduces an expert-labeled dataset of YouTube comments in Telugu, Kannada, and Gujarati for identifying homophobic and transphobic content, plus baseline transformer models.
Homophobia and transphobia detection for low-resourced languages in social media comments
January 1, 2023Describes dataset creation, annotation methodology, and experiments (including transformer baselines) for detecting homophobia and transphobia across multiple low-resource languages; focuses on improving automated detection and cross-lingual transfer.
Exploring Techniques to Detect and Mitigate Non-Inclusive Language Bias in Marketing Communications Using a Dictionary-Based Approach
January 1, 2023Paper reporting techniques to detect and mitigate non-inclusive language bias in marketing communications; includes contributions to experiments and analysis.
Dataset for Identification of Homophobia and Transphobia in Multilingual YouTube Comments (arXiv)
January 1, 2021Presents a hierarchical taxonomy and an expert-labelled dataset (15,141 annotated multilingual comments) for automatic identification of homophobic and transphobic content, including baseline models; emphasizes annotation guidelines and use of expert annotators.