K-Act2Emo: Korean Commonsense Knowledge Graph for Indirect Emotional Expression

In many literary texts, emotions are indirectly conveyed through descriptions of actions, facial expressions, and appearances, necessitating emotion inference for narrative understanding. In this paper, we introduce K-Act2Emo, a Korean commonsense knowledge graph (CSKG) comprising 1,900 indirect emotional expressions and the emotions inferable from them. We categorize reasoning types into inferences in positive situations, inferences in negative situations, and inferences when expressions do not serve as emotional cues. Unlike existing CSKGs, K-Act2Emo specializes in emotional contexts, and experimental results validate its effectiveness for training emotion inference models. Significantly, the BART-based knowledge model fine-tuned with K-Act2Emo outperforms Figure 1: Illustration of inferential knowledge in K-various existing Korean large language Act2Emo: PosEnv for inferences in positive situations, models, achieving performance levels comparable NegEnv for negative situations, and NonEmo when expressions to GPT-4 Turbo.