CONICET | Buscador de Institutos y Recursos Humanos

Structured Abstract: Purpose: This paper proposes an approach to generate recommendations for groups on the basis of social factors extracted from a social network. Group recommendation techniques traditionally assumed users as independent individuals, ignoring the effects of social interaction and relationships among users. In this work we analyze those social factors, available in social networks, in the light of sociological theories, which endorse individuals? influenceability within a group. Design/methodology/approach: The approach proposed is based on the creation of a group model in two stages: identifying the items representative of the majority?s preferences, analyzing members? similarity; extracting potential influence from members? interaction in social network to predict a group?s opinion for each item. Findings: The promising results obtained when evaluating the approach on the movie domain, support that individual opinions tend to be accommodated to group satisfaction, evidencing the incidence of the aforementioned factors in collective behavior, as endorsed by sociological research. What is more, findings suggest that these factors have dissimilar impact on group satisfaction. Originality/value: The results obtained provide clues about how social influence exerted within groups could alter individuals? opinions when a group has a common goal. There is limited research in this area exploring social influence in group recommendation; thus, the originality of this perspective lies in the use of sociological theoretical basis to explain social influence in groups of users, and the flexibility of the approach to be applied in any domain. Our findings could be helpful for group recommender systems developers both at research and commercial levels.