Categorical Emotions or Appraisals - Which Emotion Model Explains Argument Convincingness Better?

TL;DR

This paper addresses how to best explain and predict the convincingness of arguments by comparing cognitive appraisal-based emotion models with traditional categorical emotion models. Using zero-shot prompting across three large language models on the ContArgA corpus, the authors show that appraisal dimensions consistently yield stronger improvements in convincingness prediction than discrete emotions, though joint modeling of emotions/appraisals with convincingness yields only limited gains. The work provides the first systematic comparison of emotion models for convincingness in computational argumentation and argues for cognitively grounded appraisal frameworks to enhance theoretical understanding and practical applications in argument analysis. The findings have implications for designing more robust, human-aligned argument analysis and generation systems, while also highlighting limitations of zero-shot prompting and the need for better automatic appraisal prediction methods.

Abstract

The convincingness of an argument does not only depend on its structure (logos), the person who makes the argument (ethos), but also on the emotion that it causes in the recipient (pathos). While the overall intensity and categorical values of emotions in arguments have received considerable attention in the research community, we argue that the emotion an argument evokes in a recipient is subjective. It depends on the recipient's goals, standards, prior knowledge, and stance. Appraisal theories lend themselves as a link between the subjective cognitive assessment of events and emotions. They have been used in event-centric emotion analysis, but their suitability for assessing argument convincingness remains unexplored. In this paper, we evaluate whether appraisal theories are suitable for emotion analysis in arguments by considering subjective cognitive evaluations of the importance and impact of an argument on its receiver. Based on the annotations in the recently published ContArgA corpus, we perform zero-shot prompting experiments to evaluate the importance of gold-annotated and predicted emotions and appraisals for the assessment of the subjective convincingness labels. We find that, while categorical emotion information does improve convincingness prediction, the improvement is more pronounced with appraisals. This work presents the first systematic comparison between emotion models for convincingness prediction, demonstrating the advantage of appraisals, providing insights for theoretical and practical applications in computational argumentation.