Automatic Emotion Experiencer Recognition

TL;DR

This paper introduces the task of automatic emotion experiencer recognition, providing baseline experiments to assess its difficulty and impact on emotion classification pipelines, highlighting the challenges in detecting emotion experiencers in text.

Contribution

It presents the first baseline experiments for automatic detection of emotion experiencers in text and analyzes its effect on emotion categorization without gold mentions.

Findings

Experiencer detection has an F1 score of 0.66.

Detection precision is 0.82, recall is 0.56.

The task is challenging and warrants joint modeling approaches.

Abstract

The most prominent subtask in emotion analysis is emotion classification; to assign a category to a textual unit, for instance a social media post. Many research questions from the social sciences do, however, not only require the detection of the emotion of an author of a post but to understand who is ascribed an emotion in text. This task is tackled by emotion role labeling which aims at extracting who is described in text to experience an emotion, why, and towards whom. This could, however, be considered overly sophisticated if the main question to answer is who feels which emotion. A targeted approach for such setup is to classify emotion experiencer mentions (aka "emoters") regarding the emotion they presumably perceive. This task is similar to named entity recognition of person names with the difference that not every mentioned entity name is an emoter. While, very recently, data with emoter annotations has been made available, no experiments have yet been performed to detect such mentions. With this paper, we provide baseline experiments to understand how challenging the task is. We further evaluate the impact on experiencer-specific emotion categorization and appraisal detection in a pipeline, when gold mentions are not available. We show that experiencer detection in text is a challenging task, with a precision of .82 and a recall of .56 (F1 =.66). These results motivate future work of jointly modeling emoter spans and emotion/appraisal predictions.