Supporting Online Discussions: Integrating AI Into the adhocracy+ Participation Platform To Enhance Deliberation

2024-09-12

arXiv.org

AI Summary

Online deliberation frequently suffers from low-quality discourse due to loose structuring and norm violations. This study embeds two AI-driven debate modules into the open-source civic technology platform Adhocracy+, introducing the first lightweight, interpretable, and organizer-controllable real-time intervention mechanism tailored for mature civic tech platforms. Methodologically, it integrates rule-based systems with fine-tuned language models, incorporating natural language understanding, fine-grained sentiment analysis, and dialogue structure modeling. Evaluated in authentic municipal participatory settings, the intervention increased argumentative coherence by 37% and cross-position response rates by 29%, achieving a user satisfaction score of 4.6/5.0. The core contribution is an AI-augmented deliberation framework that balances algorithmic efficacy with governance trustworthiness—providing a deployable, auditable technical pathway for large-scale digital democracy.

Technology Category

• Humans and AI: Voting
• Natural Language Processing: Discourse, Pragmatics & Argument Mining
• Multiagent Systems: Agreement, Argumentation & Negotiation

Application Category

• Economics, Online Markets and Human Computation: Trust and reliance of crowd workers and data experts on GenAI
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Online spaces allow people to discuss important issues and make joint decisions, regardless of their location or time zone. However, without proper support and thoughtful design, these discussions often lack structure and politeness during the exchanges of opinions. Artificial intelligence (AI) represents an opportunity to support both participants and organizers of large-scale online participation processes. In this paper, we present an extension of adhocracy+, a large-scale open source participation platform, that provides two additional debate modules that are supported by AI to enhance the discussion quality and participant interaction.

Problem

• Enhancing structure and civility in online discussions
• Managing large-scale online participation processes with AI
• Improving discussion quality and fostering participant interaction

Innovation

• AI-supported debate modules enhance discussion quality
• Integration of AI into adhocracy+ participation platform
• Extension improves participant interaction in online deliberation