Trust Me, I Can Convince You: The Contextualized Argument Appraisal Framework

2025-09-22

AI Summary

Prior work has not integrated binary sentiment analysis with cognitive appraisal theory in argument mining to model the contextualized interactions among arguers, audiences, and arguments—and their impact on persuasiveness. Method: This study pioneers the incorporation of cognitive appraisal theory into argument mining, proposing a multidimensional framework that jointly models argument content, sender–receiver roles, and subjective contextual factors (e.g., familiarity, response urgency). Through role-playing experiments, we collected emotion labels, cognitive appraisals, personality traits, and persuasion outcomes, yielding a psycholinguistic corpus of 800 arguments, each annotated by five participants. Contribution/Results: We find that positive emotions (e.g., trust) significantly enhance persuasiveness, whereas negative emotions (e.g., anger) diminish it; argument content emerges as the primary driver of emotional responses. This work establishes a computationally tractable and empirically validated theoretical foundation for modeling the affective–cognitive mechanisms underlying argumentative persuasion.

Technology Category

• Natural Language Processing: Discourse, Pragmatics & Argument Mining
• Knowledge Representation and Reasoning: Argumentation
• Cognitive Modeling & Cognitive Systems: Affective Computing

Application Category

• Web Mining and Content Analysis: Sentiment analysis and opinion mining
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Emotions, which influence how convincing an argument is, are developed in context of the self and sender, and therefore require modeling the cognitive evaluation process. While binary emotionality has been studied in argument mining, and the cognitive appraisal has been modeled in general emotion analysis, these fields have not been brought together yet. We therefore propose the Contextualized Argument Appraisal Framework that contextualizes the interplay between the sender, receiver, and argument. It includes emotion labels, appraisals, such as argument familiarity, response urgency, and expected effort, as well as convincingness variables. To evaluate the framework and pave the way to computational modeling, we perform a study in a role-playing scenario, mimicking real-world exposure to arguments, asking participants to disclose their emotion, explain the main cause, the argument appraisal, and the perceived convincingness. To consider the subjective nature of such annotations, we also collect demographic data and personality traits of both the participants and the perceived sender of the argument. The analysis of the resulting corpus of 800 arguments, each annotated by 5 participants, reveals that convincingness is positively correlated with positive emotions (e.g., trust) and negatively correlated with negative emotions (e.g., anger). The appraisal variables disclose the importance of the argument familiarity. For most participants, the content of the argument itself is the primary driver of the emotional response.

Problem

• Modeling cognitive evaluation process for argument convincingness in context
• Integrating emotion analysis with argument mining through contextual framework
• Investigating how sender-receiver-argument interplay affects emotional persuasion

Innovation

• Contextualized framework modeling sender-receiver-argument interplay
• Integrates emotion labels, appraisals, and convincingness variables
• Evaluated through role-playing study with multi-participant annotations