AtmosERC: Modeling Dialogue-Level Affective Atmosphere for Emotion Recognition in Conversation

Researchers propose AtmosERC, a graph-based framework for Emotion Recognition in Conversation (ERC) that models dialogue-level affective atmosphere to improve emotion prediction. The framework uses a relation-aware graph extractor to produce affective priors, enhancing both lightweight and LLM-based ERC systems, as demonstrated on four benchmarks.

arXiv:2607.26726v1 Announce Type: new Abstract: Emotion Recognition in Conversation ERC aims to predict utterance-level emotions in dialogues and has largely advanced through context-centric modeling. However, global context is a heterogeneous signal, and not all contextual information is equally relevant to emotion prediction. This paper focuses on the affect-oriented component of this signal, termed dialogue-level affective atmosphere, which captures a latent tendency commonly reflected in conversational emotion patterns. To estimate and exploit this tendency, we propose AtmosERC, a graph-based ERC framework that models each dialogue as a conversational graph over utterances and speakers. A relation-aware graph extractor filters and fuses heterogeneous graph signals to produce dialogue-level and speaker-conditioned affective priors. The resulting compact prior guides lightweight sequential emotion prediction and can also be verbalized into prompt-level cues for LLM-based ERC without modifying backbone models. Experiments on four ERC benchmarks show that AtmosERC improves lightweight ERC, enhances LLM-based ERC as a plug-in cue, and yields more stable predictions under local emotional deviations.