FranceCountry of destination:
In a society dealing with an increasing amount of information, it is difficult to know what to rely on to take a decision. In a collective context, reaching a fair decision requires to identify information that is objective and relevant, or skewed toward personal interests. The aim of this project is to bring several disciplines together, theoretical argumentation, social choice theory and dialogue modelling, in order to address the negative processes of dialogue, such as manipulation or fallacious arguments. The characterization of dialogue protocols preventing or, at least, recognizing harmful moves will ensure an honest and consensual collective decision.
After a Master degree in artificial intelligence during which I had the opportunity to start my research career by studying and formalizing group emotions, I specialized in formal analysis of agents’ interactions during my PhD. My work focused on abstract argumentation, a formalism allowing to reason with inconsistent information, and the changes that argumentation systems might undergo during argumentative interactions between agents.
Since 2014, I hold a research position in the Knowledge Engineering group (UMR IATE, INRA) where my research interest moved toward a deeper understanding of the persuasion processes in human interactions, with a focus on the rational and non-rational evaluation of arguments.
Thanks to the AgreenSkills program at the University of Amsterdam, I had the opportunity to link my work on argumentation and persuasion with social choice theory, a topic focusing on the analysis of collective decisions from a set of individual preferences. More precisely, I am now interested in establishing a formal framework of the deliberation process predating a vote, and under which conditions deliberation may help to output a collectively rational choice in the presence of manipulative persuasion. My long-term intent is to study the different types of interactions in the context of group decision, and to characterize the impact of an individual rhetoric on a collective.
Abdelraouf Hecham, Pierre Bisquert, Madalina Croitoru, 2018. On a Flexible Representation for Defeasible Reasoning Variants. 17th Conference on Autonomous Agents and MultiAgent Systems (AAMAS 2018 - to appear).
Pierre Bisquert, Madalina Croitoru, Nikos Karanikolas, 2017. A Qualitative Decision-Making Approach Overlapping Argumentation and Social Choice. 5th International Conference on Algorithmic Decision Theory (ADT 2017), 344-349.
Pierre Bisquert, Madalina Croitoru, Florence Dupin de Saint-Cyr, Abdelraouf Hecham, 2017. Formalizing Cognitive Acceptance of Arguments: Durum Wheat Selection Interdisciplinary Study. Minds and Machines 27(1): 233-252.
Florence Dupin de Saint-Cyr, Pierre Bisquert, Claudette Cayrol, Marie-Christine Lagasquie-Schiex, 2016. Argumentation Update in YALLA (Yet Another Logic Language for Argumentation). International Journal of Approximate Reasoning 75: 57-92.
Pierre Bisquert, Madalina Croitoru, Florence Dupin de Saint-Cyr, Abdelraouf Hecham, 2016. Substantive Irrationality in Cognitive Systems. 22nd European Conference on Artificial Intelligence (ECAI 2016): 16421643.