Representative Ranking for Deliberation in the Public Sphere

2025-03-19

AI Summary

Online comment sections hold potential for fostering public discourse but often suffer from toxic content and algorithmic ranking that simultaneously amplify polarization and suppress diverse viewpoints, thereby degrading discussion quality and representativeness. This paper introduces the first comment-ranking framework to incorporate the social choice-theoretic fairness constraint of *Justified Representation* (JR), jointly optimizing for conversational quality—measured via a politeness classifier—and viewpoint inclusivity—ensured by JR’s guarantee of fair visibility for substantively distinct, legitimate perspectives. We formulate this as a multi-objective ranking optimization problem and propose a principled solution balancing both objectives. Empirical evaluation demonstrates that our approach significantly improves viewpoint diversity while preserving—or even enhancing—key user engagement metrics, including dwell time and interaction quality. This work establishes a novel paradigm for algorithmic governance that reconciles ethical interpretability with practical efficacy.

Technology Category

• Machine Learning: Learning Preferences or Rankings
• Knowledge Representation and Reasoning: Preferences
• Computer Vision: Bias, Fairness & Privacy

Application Category

• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Economics, Online Markets and Human Computation: Fairness, privacy, and diversity in economic environments

Abstract

Online comment sections, such as those on news sites or social media, have the potential to foster informal public deliberation, However, this potential is often undermined by the frequency of toxic or low-quality exchanges that occur in these settings. To combat this, platforms increasingly leverage algorithmic ranking to facilitate higher-quality discussions, e.g., by using civility classifiers or forms of prosocial ranking. Yet, these interventions may also inadvertently reduce the visibility of legitimate viewpoints, undermining another key aspect of deliberation: representation of diverse views. We seek to remedy this problem by introducing guarantees of representation into these methods. In particular, we adopt the notion of justified representation (JR) from the social choice literature and incorporate a JR constraint into the comment ranking setting. We find that enforcing JR leads to greater inclusion of diverse viewpoints while still being compatible with optimizing for user engagement or other measures of conversational quality.

Problem

• Address toxic exchanges in online comment sections
• Balance quality and diversity in algorithmic ranking
• Ensure representation of diverse views in deliberation

Innovation

• Incorporates justified representation (JR) constraint
• Balances diversity and engagement in rankings
• Uses social choice theory for comment ranking