From Argumentation to Deliberation: Perspectivized Stance Vectors for Fine-grained (Dis)agreement Analysis

2025-02-10

AI Summary

This paper addresses the challenge of identifying latent consensus in multi-stakeholder disputes—a key bottleneck impeding the transition from adversarial debate to constructive deliberation. To tackle this, we propose a perspective-decoupled stance modeling framework. We introduce Perspectivized Stance Vectors, the first formal representation that disentangles explicit stance expressions from underlying subjective dimensions—such as attitudes, values, and needs—enabling fine-grained geometric characterization of shared or conflicting perspectives in vector space. The method integrates concept mining, perspective-aware stance classification, and value-sensitive NLP techniques, and defines perspective-modulated (in)consistency metrics to support conflict-resolution pathway identification. Evaluated on a multi-stakeholder controversy dataset, our approach identifies over 37% of latent consensus anchors with high precision, substantially enhancing the operationalizability of deliberative dialogue. This work establishes a novel paradigm for computational argumentation and deliberative AI.

Technology Category

• Natural Language Processing: Discourse, Pragmatics & Argument Mining
• Knowledge Representation and Reasoning: Argumentation
• Multiagent Systems: Agreement, Argumentation & Negotiation

Application Category

• Web Mining and Content Analysis: Sentiment analysis and opinion mining
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

Abstract

Debating over conflicting issues is a necessary first step towards resolving conflicts. However, intrinsic perspectives of an arguer are difficult to overcome by persuasive argumentation skills. Proceeding from a debate to a deliberative process, where we can identify actionable options for resolving a conflict requires a deeper analysis of arguments and the perspectives they are grounded in - as it is only from there that one can derive mutually agreeable resolution steps. In this work we develop a framework for a deliberative analysis of arguments in a computational argumentation setup. We conduct a fine-grained analysis of perspectivized stances expressed in the arguments of different arguers or stakeholders on a given issue, aiming not only to identify their opposing views, but also shared perspectives arising from their attitudes, values or needs. We formalize this analysis in Perspectivized Stance Vectors that characterize the individual perspectivized stances of all arguers on a given issue. We construct these vectors by determining issue- and argument-specific concepts, and predict an arguer's stance relative to each of them. The vectors allow us to measure a modulated (dis)agreement between arguers, structured by perspectives, which allows us to identify actionable points for conflict resolution, as a first step towards deliberation.

Problem

• Develops framework for fine-grained deliberation analysis in computational argumentation
• Measures perspectivized agreement between arguers using stance vectors
• Identifies shared perspectives and actionable conflict resolution points

Innovation

• Perspectivized Stance Vectors for fine-grained analysis
• Issue-specific concept prediction for stance characterization
• Modulated disagreement measurement structured by perspectives