Understanding Emotion in Discourse: Recognition Insights and Linguistic Patterns for Generation
This work addresses gaps in understanding modeling choices for emotion recognition in conversation and provides linguistic insights for emotion generation, though it's incremental with focused analysis on a specific dataset.
The researchers systematically studied emotion recognition in conversation to identify which modeling choices affect performance and analyzed linguistic patterns to link recognition findings to generation cues. They found conversational context dominates performance (90% gain from recent 10-30 turns), hierarchical representations only help without context, and affective lexicons don't improve results, achieving 82.69% 4-way and 67.07% 6-way weighted F1 scores.
Despite strong recent progress in Emotion Recognition in Conversation (ERC), two gaps remain: we lack clear understanding of which modeling choices materially affect performance, and we have limited linguistic analysis linking recognition findings to actionable generation cues. We address both via a systematic study on IEMOCAP. For recognition, we conduct controlled ablations with 10 random seeds and paired tests (with correction for multiple comparisons), yielding three findings. First, conversational context is dominant: performance saturates quickly, with roughly 90% of gain achieved using only the most recent 10-30 preceding turns. Second, hierarchical sentence representations improve utterance-only recognition (K=0), but the benefit vanishes once turn-level context is available, suggesting conversational history subsumes intra-utterance structure. Third, external affective lexicon (SenticNet) integration does not improve results, consistent with pretrained encoders already capturing affective signal. Under strictly causal (past-only) setting, our simple models attain strong performance (82.69% 4-way; 67.07% 6-way weighted F1). For linguistic analysis, we examine 5,286 discourse-marker occurrences and find reliable association between emotion and marker position (p < 0.0001). Sad utterances show reduced left-periphery marker usage (21.9%) relative to other emotions (28-32%), aligning with accounts linking left-periphery markers to active discourse management. This pattern is consistent with Sad benefiting most from conversational context (+22%p), suggesting sadness relies more on discourse history than overt pragmatic signaling.