Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

BCause: Human-AI collaboration to improve hybrid mapping and ideation in argumentation-grounded deliberation

Lucas Anastasiou, Anna De Liddo

TL;DR

The paper tackles the disconnect between public discourse and policy formation by introducing BCause, a hybrid platform that leverages generative AI to transform unstructured discussions into structured, geo-aware deliberations. It combines three innovations—automatic transcript-based argument extraction, geo-deliberation via a Telegram interface, and widget-based smart reporting—within a human-in-the-loop framework to preserve ethical oversight and contextual relevance. Key contributions include an IBIS-inspired argumentative structure with a time-ordered tree, a location-based issue reporting workflow, and a modular reporting dashboard that supports stakeholder-facing outputs. The approach aims to enhance sensemaking and policy influence in hybrid (online and in-person) deliberation spaces, with pilot deployment in Milan and support from Horizon Europe through the ORBIS project to evaluate scalability and governance considerations.

Abstract

Public deliberation, as in open discussion of issues of public concern, often suffers from scattered and shallow discourse, poor sensemaking, and a disconnect from actionable policy outcomes. This paper introduces BCause, a discussion system leveraging generative AI and human-machine collaboration to transform unstructured dialogue around public issues (such as urban living, policy changes, and current socio-economic transformations) into structured, actionable democratic processes. We present three innovations: (i) importing and transforming unstructured transcripts into argumentative discussions, (ii) geo-deliberated problem-sensing via a Telegram bot for local issue reporting, and (iii) smart reporting with customizable widgets (e.g., summaries, topic modelling, policy recommendations, clustered arguments). The system's human-AI partnership preserves critical human participation to ensure ethical oversight, contextual relevance, and creative synthesis.

BCause: Human-AI collaboration to improve hybrid mapping and ideation in argumentation-grounded deliberation

TL;DR

The paper tackles the disconnect between public discourse and policy formation by introducing BCause, a hybrid platform that leverages generative AI to transform unstructured discussions into structured, geo-aware deliberations. It combines three innovations—automatic transcript-based argument extraction, geo-deliberation via a Telegram interface, and widget-based smart reporting—within a human-in-the-loop framework to preserve ethical oversight and contextual relevance. Key contributions include an IBIS-inspired argumentative structure with a time-ordered tree, a location-based issue reporting workflow, and a modular reporting dashboard that supports stakeholder-facing outputs. The approach aims to enhance sensemaking and policy influence in hybrid (online and in-person) deliberation spaces, with pilot deployment in Milan and support from Horizon Europe through the ORBIS project to evaluate scalability and governance considerations.

Abstract

Public deliberation, as in open discussion of issues of public concern, often suffers from scattered and shallow discourse, poor sensemaking, and a disconnect from actionable policy outcomes. This paper introduces BCause, a discussion system leveraging generative AI and human-machine collaboration to transform unstructured dialogue around public issues (such as urban living, policy changes, and current socio-economic transformations) into structured, actionable democratic processes. We present three innovations: (i) importing and transforming unstructured transcripts into argumentative discussions, (ii) geo-deliberated problem-sensing via a Telegram bot for local issue reporting, and (iii) smart reporting with customizable widgets (e.g., summaries, topic modelling, policy recommendations, clustered arguments). The system's human-AI partnership preserves critical human participation to ensure ethical oversight, contextual relevance, and creative synthesis.
Paper Structure (8 sections, 2 figures)

This paper contains 8 sections, 2 figures.

Table of Contents

  1. Introduction
  2. BCause System Overview
  3. GenAI in BCause
  4. Import and Transformation of Unstructured Dialogue
  5. Geo-Deliberated Problem Sensing via Telegram Bot
  6. Smart Reporting with Customisable Widgets
  7. Report Generation and Structure
  8. Discussion

Figures (2)

  • Figure 1: Transcript analysis intermediate steps: (left) configurable parameters for argument extraction, including number of positions per issue, number of arguments per position and argument balance settings, (right) preview panel of the resulting structure
  • Figure 2: Smart reporting interface featuring customizable widgets: (left) widgets with participation metrics and trend analysis, (centre) detailed discussion summary and argument clusters, and (right) available widgets selector menu