Abstract
Making a choice that equally satisfies all group members is challenging and time-consuming. In fact, group decision making is a complicated and time-consuming process that may involve group members with different preferences and personalities. To deal with this challenge, novel types of group recommender systems are emerging. The main objective of our research is to develop technologies that can help groups to make justifiable and fair choices, in a short amount of time (limited costs). We are therefore addressing three questions related to group recommender systems: (i) how to predict a group choice by leveraging data related to the group dynamic, (ii) how to design a conversational system that can help groups to make better choices, and (iii) how to support groups while the state of the group and the group/system interaction is evolving. We believe that a conversational group recommender system can use the predicted group choice to interact more effectively with the group. But, in order to do that the system should understand the dynamic of the group and in particular how the group preferences evolve during the group discussion. The conversational group recommender system should use this information to support the groups in different dynamically evolving states. Our research attempts to address these questions.