• Funding : ANR
  • Start year :
  • 2023

The ANR AGGREEY project (An Argumentation-based Platform for E-Democracy) focuses on the study of participatory democracy and aims to provide AI-based tools and argumentation theory to enhance the quality of public debate. As online argumentation systems become increasingly prevalent, the volume of arguments and options they contain continues to grow. This presents a significant challenge for human analysts who strive to manually keep track of changes, understand different arguments and their relationships, and make sense of the vast amount of information. To address this challenge, AGGREEY proposes to use artificial intelligence and argumentation theory to study these systems. Among the numerous pieces of information to identify and process, this thesis will focus on the issue of votes on arguments. Currently, there is no comprehensive approach in the literature for handling votes in a sophisticated manner. The existing proposal involves calculating the ratio of positive and negative votes and treating it as a single number. The goal is to explore alternative ways of representing and considering votes and understanding the nuances of the voting process. We also aim to take into account user votes to maximize social welfare. In other words, we want to develop methods that start from user votes and transfer this information to extensions, which are sets of acceptable arguments. Thus, based on a user’s votes, the system calculates their preferred extension. The objective is to develop an algorithm that selects the extension that maximizes the satisfaction of all voters.