Empathify at WASSA 2024 Empathy and Personality Shared Task: Contextualizing Empathy with a BERT-Based Context-Aware Approach for Empathy Detection

2024-01-01
Numanoğlu, Arda
Ateş, Süleyman
Çiçekli, Fehime Nihan
Küçük, Dilek
Empathy detection from textual data is a complex task that requires an understanding of both the content and context of the text. This study presents a BERT-based context-aware approach to enhance empathy detection in conversations and essays. We participated in the WASSA 2024 Shared Task (Giorgi et al., 2024), focusing on two tracks: empathy and emotion prediction in conversations (CONV-turn) and empathy and distress prediction in essays (EMP). Our approach leverages contextual information by incorporating related articles and emotional characteristics as additional inputs, using BERT-based Siamese (parallel) architecture. Our experiments demonstrated that using article summaries as context significantly improves performance, with the parallel BERT approach outperforming the traditional method of concatenating inputs with the ‘[SEP]‘token. These findings highlight the importance of context-awareness in empathy detection and pave the way for future improvements in the sensitivity and accuracy of such systems. Our system officially ranked 8th at both CONV-T and EMP tracks.
14th Workshop on Computational Approaches to Subjectivity, Sentiment, and Social Media Analysis, WASSA 2024
Citation Formats
A. Numanoğlu, S. Ateş, F. N. Çiçekli, and D. Küçük, “Empathify at WASSA 2024 Empathy and Personality Shared Task: Contextualizing Empathy with a BERT-Based Context-Aware Approach for Empathy Detection,” presented at the 14th Workshop on Computational Approaches to Subjectivity, Sentiment, and Social Media Analysis, WASSA 2024, Bangkok, Tayland, 2024, Accessed: 00, 2024. [Online]. Available: https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85204910192&origin=inward.