Social Influence in Group Recommender Systems

INGRID CHRISTENSEN; SILVIA SCHIAFFINO

Buenos Aires

Conferencia; XV Argentine Symposium on Artificial Intelligence (ASAI 2014) de las 43rd Argentine Conference on Computer Science and Operational Research (JAIIO 2014); 2014

SADIO - Sociedad Argentina de Informática

Purpose ? The purpose of this paper is to propose an approach to generate recommendations for groups on the basis of social factors extracted from a social network. Group recommendation techniques traditionally assumed users were independent individuals, ignoring the effects of social interaction and relationships among users. In this work the authors analyse the social factors available in social networks in the light of sociological theories which endorse individuals? susceptibility to influence within a group. Design/methodology/approach ? The approach proposed is based on the creation of a group model in two stages: identifying the items that are representative of the majority?s preferences, and analysing members? similarity; and extracting potential influence from members? interactions in a social network to predict a group?s opinion on each item. Findings ? The promising results obtained when evaluating the approach in the movie domain suggest that individual opinions tend to be accommodated to group satisfaction, as demonstrated by the incidence of the aforementioned factors in collective behaviour, as endorsed by sociological research. Moreover the findings suggest that these factors have dissimilar impacts 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 recommendations; thus the originality of this perspective lies in the use of sociological theory to explain social influence in groups of users, and the flexibility of the approach to be applied in any domain. The findings could be helpful for group recommender systems developers both at research and commercial levels.