Where are We in Event-centric Emotion Analysis? Bridging Emotion Role Labeling and Appraisal-based Approaches
This work addresses the integration of psychological theories into NLP for emotion analysis, which is incremental as it synthesizes existing approaches rather than introducing new methods.
The paper examines the relationship between emotions and events in natural language processing, arguing that emotions can be viewed as events themselves or as caused by events, and it bridges the separate research directions of emotion role labeling and appraisal-based emotion classification to discuss open questions.
The term emotion analysis in text subsumes various natural language processing tasks which have in common the goal to enable computers to understand emotions. Most popular is emotion classification in which one or multiple emotions are assigned to a predefined textual unit. While such setting is appropriate for identifying the reader's or author's emotion, emotion role labeling adds the perspective of mentioned entities and extracts text spans that correspond to the emotion cause. The underlying emotion theories agree on one important point; that an emotion is caused by some internal or external event and comprises several subcomponents, including the subjective feeling and a cognitive evaluation. We therefore argue that emotions and events are related in two ways. (1) Emotions are events; and this perspective is the fundament in natural language processing for emotion role labeling. (2) Emotions are caused by events; a perspective that is made explicit with research how to incorporate psychological appraisal theories in NLP models to interpret events. These two research directions, role labeling and (event-focused) emotion classification, have by and large been tackled separately. In this paper, we contextualize both perspectives and discuss open research questions.