Bridging Cognition and Affect: Emotion-Aware Opinion Summarization using LLMs

Opinion summarization systems aggregate customer sentiments without capturing the emotional factors that drive purchasing decisions, resulting in shallow summaries that overlook the affective dimensions shaping customer experiences and fail to explain why customers feel the way they do. This gap exists because prior research has neglected the interplay between expressed opinions and their underlying emotional contexts. To bridge this gap, we introduce EMOTION-AWARE OPINION SUMMA-RIZATION (EAOS), a framework leveraging Large Language Models (LLMs) to integrate emotional dimensions into opinion summaries, moving beyond conventional sentiment polarity. To support this task, we develop a largescale (40K product-summary pairs) training dataset, an evaluation benchmark, a compact 1B-parameter model that matches 70B-scale performance via knowledge distillation, and methods for generating and evaluating emotionaware summaries. A user study shows that 82% of readers prefer our emotion-aware summaries (p < .001), confirming that adding emotion helps in making purchase decisions.