Vibhor Agarwal
Academic and research departments
Computer Science Research Centre, Distributed and Networked Systems Group.About
My research project
Why do you hate me? Interpreting and explaining automatic classifications of hate in social mediaThere are numerous examples where hateful speech has been found online and several engines have been developed, focusing for example on racism, misogyny, etc. While they claim to work well on well defined datasets, it is not often clear whether a text is hateful or 'merely offensive'. This project aims to develop new methods to take the context in which a possible hateful utterance is found on social media, and provide interpretations or explanations helping to understand whether something is hateful.
Supervisors
There are numerous examples where hateful speech has been found online and several engines have been developed, focusing for example on racism, misogyny, etc. While they claim to work well on well defined datasets, it is not often clear whether a text is hateful or 'merely offensive'. This project aims to develop new methods to take the context in which a possible hateful utterance is found on social media, and provide interpretations or explanations helping to understand whether something is hateful.
Publications
Highlights
GraphNLI: A Graph-based Natural Language Inference Model for Polarity Prediction in Online Debates. Vibhor Agarwal, Sagar Joglekar, Anthony P. Young, and Nishanth Sastry. In Proceedings of the ACM Web Conference 2022.
"Way back then": A Data-driven View of 25+ years of Web Evolution. Vibhor Agarwal, and Nishanth Sastry. In Proceedings of the ACM Web Conference 2022.
AnnoBERT: Effectively Representing Multiple Annotators' Label Choices to Improve Hate Speech Detection. Wenjie Yin*, Vibhor Agarwal*, Aiqi Jiang*, Arkaitz Zubiaga, and Nishanth Sastry. In Proceedings of the International AAAI Conference on Web and Social Media (ICWSM) 2023.
A Graph-Based Context-Aware Model to Understand Online Conversations. Vibhor Agarwal, Anthony P. Young, Sagar Joglekar, and Nishanth Sastry. In ArXiv 2022 (Under Review).