This research investigates implicit hostility, threats, and miscommunication in online interactions, where
offensive intent is often subtle and context-dependent. Due to the difficulty of obtaining labeled user-
generated data, the study explores methods to identify and analyze implicit emotional cues using limited
seed information. By leveraging advanced retrieval and generative approaches, the research aims to
alleviate communication breakdowns and prevent misused language from escalating conflicts. The
findings will contribute to better content moderation, improved sentiment analysis, and enhanced digital
discourse understanding in social and professional communication platforms.
- Che Wei Tsai, Yen-Hao Huang, Tsu-Keng Liao, Didier Fernando Salazar Estrada,
Retnani Latifah, Yi-Shin Chen (2024, Nov). Leveraging Conflicts in Social Media
Posts: Unintended Offense Dataset. Proceedings of the 2024 Conference on Empirical
Methods in Natural Language Processing (EMNLP 2024), Miami, Florida, USA.
- Yusra Ghafoor, Shi Jinping, Fernando Henrique Calderon, Yen-Hao Huang, Kuan-
Ta Chen, Yi-Shin Chen (2022). TERMS: Textual Emotion Recognition in
Multidimensional Space. Applied Intelligence.
- Fernando H. Calderón, Namrita Balani, Jherez Taylor, Melvyn Peignon, Yen-Hao
Huang, Yi-Shin Chen (2021). Linguistic Patterns for Code Word Resilient Hate
Speech Identification. ROCLING 2022: 15-24.