Dialogue Summarization with Emotion Dynamics Using Topic- and Participant-Centric Decomposition
This work addresses the need for dialogue summarization that captures emotional dynamics, which is important for applications like customer service and therapy, but the gains are incremental over existing methods.
The paper proposes a dialogue summarization framework that models both semantic and emotion dynamics using multimodal inputs, decomposing dialogues into topic- and participant-centric segments. Experiments with small language models show the framework produces summaries with both semantic and emotion content, and the authors introduce emotion trajectory metrics for evaluation.
Existing text summarization research has focused much on monologic information (e.g., newspaper articles, reports) without accounting for the interaction between speakers or authors. In contrast, dialogues are a rich communication channel where multiple participants conduct back and forth exchanges to construct meaning. We propose a dialogue summarization framework that explicitly models both semantic and emotion dynamics using multimodal dialogue inputs, built on an adapted hierarchical Chain-of-Agents approach. We decompose dialogues from two perspectives: (1) topic segments based on the utterances of all participants, and (2) participant-specific utterance segments. These are used to generate corresponding summaries while incorporating automatically inferred emotions. Topic- and participant-level summaries are aggregated into a dialogue summary capturing semantic content and emotion trajectories. To evaluate beyond content accuracy, we introduce emotion trajectory metrics measuring how well summaries preserve emotional flow. Experiments with small language models on multimodal dialogue datasets show that our framework produces summaries with both semantic and emotion content. Further experiments on explicit emotion label availability highlight the efficacy of our proposed methodology and the opportunities in dialogue analysis using language models.