Abstract
Group recommender systems aim at supporting a group of users in making decisions when considering a set of alternatives. State of the art solutions aggregate individual preferences acquired before the actual decision making process and suggest items that fit the aggregated model. In this paper, we illustrate a different approach, which is implemented in a system that records and uses the users’ preferences expressed while the group discusses options. The system monitors users’ interactions and offers appropriate directions and recommendations. The system runs on a smartphone and acts as a facilitator to guide and help the group members in coming up with an agreement and a final decision. In order to measure the effectiveness of the proposed technologies we have focussed on usability and perceived recommendation quality. In a controlled live user study, we have measured a high usability score, good user-perceived recommendation quality and choice satisfaction.