Shaping Event Backstories to Estimate Potential Emotion Contexts
This addresses the problem of unreliable emotion annotation in NLP by providing contextual information to reduce ambiguity, though it appears incremental as it builds on existing story generation techniques.
The paper tackles emotion analysis ambiguity by automatically generating multiple event chains with different emotions to create enriched contexts for event descriptions, finding through evaluation that these contextual narratives help annotators produce more consistent emotion annotations.
Emotion analysis is an inherently ambiguous task. Previous work studied annotator properties to explain disagreement, but this overlooks the possibility that ambiguity may stem from missing information about the context of events. In this paper, we propose a novel approach that adds reasonable contexts to event descriptions, which may better explain a particular situation. Our goal is to understand whether these enriched contexts enable human annotators to annotate emotions more reliably. We disambiguate a target event description by automatically generating multiple event chains conditioned on differing emotions. By combining techniques from short story generation in various settings, we achieve coherent narratives that result in a specialized dataset for the first comprehensive and systematic examination of contextualized emotion analysis. Through automatic and human evaluation, we find that contextual narratives enhance the interpretation of specific emotions and support annotators in producing more consistent annotations.