Improving Recommendations by Using Personality Traits in User Profiles

Maria Augusta Silveira Netto Nunes (1) , Stefano A. Cerri (1) , Nathalie Blanc (2)

1 SMILE - Système Multi-agent, Interaction, Langage, Evolution
2 EPSYLON - Dynamique des capacités humaines et des conduites de santé

By storing Personality Traits in User Profiles we able Recommender Systems to deduce more interesting recommendations for users acting pro-actively in order to offer for them products/services as a prediction of their future needs and behavior. This paper is proposed as an alternative to improve the robustness of recommendations by using psychological aspects, as Personality Traits. This paper is a part of a PhD ongoing work. It is presented as follow: firstly we give a brief introduction about the importance of using psychological aspects in User Profiles during the decision making process; secondly, we describe studies done in Psychology describing Personality, Traits and Tests in order to formalize how to define, to model and to extract Personality Traits of user to define his identity and to build his Profile; after, we describe how the User Reputation is formalized followed by a brief consideration about Recommender Systems; finally we present our experimentation followed by results and conclusions.

Mots clés: User Psychological Profile; Identity; Reputation; Personality Traits; Recommendation

Domaines: Intelligence artificielle [cs.AI]

Maria Augusta Silveira Netto Nunes, Stefano A. Cerri, Nathalie Blanc. Improving Recommendations by Using Personality Traits in User Profiles. International Conferences on Knowledge Management and New Media Technology, Sep 2008, Graz, Austria, Austria. pp.92-100. ⟨lirmm-00288128⟩