Two PhD positions in Argumentation Theory, Sorbonne University & Artois University (France)

Two fully funded PhD thesis in argumentation theory
Place: Sorbonne University & Artois University (France)
Starting date: September / October 2023
Duration : 3 years

The ANR project AGGREEY (An argumentation-based platform for e-democracy) studies e-democracy and aims at proposing tools based on AI and argumentation theory in order to improve the quality of public debate. As online argumentation systems become increasingly prevalent, the volume of arguments and options within these systems continues to grow. This presents a significant challenge for human analysts, who struggle to manually track changes, understand the various 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 be identified and processed, those two theses will aim to focus on several problems. The first thesis will focus on the problem of votes on arguments. Currently, there is no approach in the literature that can handle votes in an elaborated way. The existing proposal is to calculate the ratio of positive and negative votes and use this as a single number. The goal is to explore more ways to represent and take into account the votes and understand the nuances of the voting process. Also, we want to take into account the votes of the users in order to maximise social welfare. In other words, we want to develop methods that start from the users’ votes and transfer this information to the extensions, i.e. the sets of acceptable arguments. Thus, based on the votes of a user, the system estimates her/his preferred extension. The goal is to develop an algorithm that selects the extension that maximises the satisfaction of all voters.

The other thesis will have the objective to investigate how formal argumentation theory and computational social choice can be exploited to guarantee a fairer representation and regulation of debates. In particular the PhD student will work on two research questions. First, how to propose a better summary of the coherent points of view by proposing new semantics that guarantee the diversity of points of view (e.g. diversity of the sources). Second, how to obtain a better organization of the debate by proposing and studying different comment sorting policies.

Project website: https://aggreey.github.io/

To apply, send your CV and your grades to aurelie.beynier at lip6.fr, jerome.delobelle at u-paris.fr, konieczny at cril.fr, nicolas.maudet at lip6.fr and vesic at cril.fr.