Disambiguation of Emotion Annotations by Contextualizing Events in Plausible Narratives

TL;DR

This paper introduces a method to generate plausible narratives to disambiguate emotion annotations in text, helping clarify emotional interpretations by filling missing context with coherent stories.

Contribution

It presents a novel approach combining story generation techniques to create contextual narratives that improve emotion analysis accuracy in ambiguous cases.

Findings

Generated narratives clarify emotion interpretation, especially for relief and sadness.

Joy does not significantly benefit from additional context.

The dataset EBS enables systematic study of contextualized emotion analysis.

Abstract

Ambiguity in emotion analysis stems both from potentially missing information and the subjectivity of interpreting a text. The latter did receive substantial attention, but can we fill missing information to resolve ambiguity? We address this question by developing a method to automatically generate reasonable contexts for an otherwise ambiguous classification instance. These generated contexts may act as illustrations of potential interpretations by different readers, as they can fill missing information with their individual world knowledge. This task to generate plausible narratives is a challenging one: We combine techniques from short story generation to achieve coherent narratives. The resulting English dataset of Emotional BackStories, EBS, allows for the first comprehensive and systematic examination of contextualized emotion analysis. We conduct automatic and human annotation and find that the generated contextual narratives do indeed clarify the interpretation of specific emotions. Particularly relief and sadness benefit from our approach, while joy does not require the additional context we provide.