Recommending the Most Encompassing Opposing and Endorsing Arguments in Debates

TL;DR

This paper proposes methods for recommending the most comprehensive opposing and supporting arguments in debates within a DirectDemocracyP2P platform, using weighted bipartite graphs to improve decision-making and argument presentation.

Contribution

It introduces a novel approach to argument recommendation in digital democratic platforms by leveraging weighted bipartite graphs for selecting and summarizing arguments.

Findings

Effective recommendation of justifications for new voters.

Compact summaries covering majority of known arguments.

Improved argument retrieval accuracy.

Abstract

Arguments are essential objects in DirectDemocracyP2P, where they can occur both in association with signatures for petitions, or in association with other debated decisions, such as bug sorting by importance. The arguments of a signer on a given issue are grouped into one single justification, are classified by the type of signature (e.g., supporting or opposing), and can be subject to various types of threading. Given the available inputs, the two addressed problems are: (i) how to recommend the best justification, of a given type, to a new voter, (ii) how to recommend a compact list of justifications subsuming the majority of known arguments for (or against) an issue. We investigate solutions based on weighted bipartite graphs.