Experiencer-Specific Emotion and Appraisal Prediction
This addresses the oversimplification in emotion detection for NLP by considering multiple participants in events, though it is incremental as it builds on existing emotion semantic role labeling tasks.
The paper tackles the problem of emotion classification in NLP by focusing on individual experiencers within event descriptions, rather than assigning a single emotion to the entire text. It shows that experiencer-aware models outperform experiencer-agnostic baselines on an event description corpus.
Emotion classification in NLP assigns emotions to texts, such as sentences or paragraphs. With texts like "I felt guilty when he cried", focusing on the sentence level disregards the standpoint of each participant in the situation: the writer ("I") and the other entity ("he") could in fact have different affective states. The emotions of different entities have been considered only partially in emotion semantic role labeling, a task that relates semantic roles to emotion cue words. Proposing a related task, we narrow the focus on the experiencers of events, and assign an emotion (if any holds) to each of them. To this end, we represent each emotion both categorically and with appraisal variables, as a psychological access to explaining why a person develops a particular emotion. On an event description corpus, our experiencer-aware models of emotions and appraisals outperform the experiencer-agnostic baselines, showing that disregarding event participants is an oversimplification for the emotion detection task.