Empathy Cause Identification: Towards Unveiling Empathic Triggers in Online Interactions

The study of empathy and its triggers is an emerging area in natural language processing (NLP), offering vital insights for creating empathetic and emotionally intelligent technologies. This thesis addresses a gap in research by focusing on empathy cause identification—a challenging task aimed at pinpointing the specific triggers prompting empathetic responses in communicative settings. To advance this field, this work introduces a novel dataset annotated specifically for empathy cause identification and explores various models designed to evaluate and demonstrate the dataset’s applicability. This research not only contributes to the understanding of empathy in textual communication but also paves the way for the development of AI systems capable of more nuanced and supportive interactions. The dataset AcnEmpathize used to create the new dataset, received a letter of non-determination, see the Appendix, from the Institutional Review Board (IRB) at the University of Illinois Chicago (UIC) and was determined not to constitute human subjects research.