Personality Based User Similarity Measure for a Collaborative Recommender System

We propose a novel approach for calculating the user similarity for collaborative filtering recommender systems that is based on the big five personality model. Experimental results showed that the performance of the proposed measures is either equal or better (depending on the measure under evaluation) than the ratings based measures used in stateof-the-art collaborative recommender systems. This makes the proposed approach, with its benefits in terms of computational complexity, for calculating user similarities a very promising one for future collaborative recommender systems that will be more affect-oriented.

[1]  P. Lang.  International affective picture system (IAPS) : affective ratings of pictures and instruction manual , 2005 .

[2]  Charles S. Carver,et al.  Action, Emotion, and Personality: Emerging Conceptual Integration , 2000 .

[3]  Eric Horvitz,et al.  Collaborative Filtering by Personality Diagnosis: A Hybrid Memory and Model-Based Approach , 2000, UAI.

[4]  S. Srivastava,et al.  The Big Five Trait taxonomy: History, measurement, and theoretical perspectives. , 1999 .

[5]  R. McCrae,et al.  An introduction to the five-factor model and its applications. , 1992, Journal of personality.

[6]  Judith Masthoff,et al.  In pursuit of satisfaction and the prevention of embarrassment: affective state in group recommender systems , 2006, User Modeling and User-Adapted Interaction.

[7]  Suh-Yin Lee,et al.  Emotion-based music recommendation by affinity discovery from film music , 2009, Expert Syst. Appl..

[8]  Zhihong Zeng,et al.  A Survey of Affect Recognition Methods: Audio, Visual, and Spontaneous Expressions , 2009, IEEE Trans. Pattern Anal. Mach. Intell..

[9]  George Lekakos,et al.  Improving the prediction accuracy of recommendation algorithms: Approaches anchored on human factors , 2006, Interact. Comput..

[10]  Emmanuelle Zech,et al.  Predicting cognitive and social consequences of emotional episodes : the contribution of emotional intensity, the Five Factor Model, and alexithymia , 2000 .

[11]  Jurij F. Tasic,et al.  Optimisation of combined collaborative recommender systems , 2007 .

[12]  Nicu Sebe,et al.  Content-based multimedia information retrieval: State of the art and challenges , 2006, TOMCCAP.

[13]  R. Davidson.  Toward a Biology of Personality and Emotion , 2001, Annals of the New York Academy of Sciences.

[14]  Rosalind W. Picard,et al.  Evaluating affective interactions: Alternatives to asking what users feel , 2005 .

[15]  Josep Lluís de la Rosa i Esteva,et al.  Managing Emotions in Smart User Models for Recommender Systems , 2004, ICEIS.

[16]  Jonathan L. Herlocker,et al.  Evaluating collaborative filtering recommender systems , 2004, TOIS.

[17]  J. Russell,et al.  Relating the Five-Factor Model of Personality to a Circumplex Model of Affect , 2002 .

[18]  Marian Stewart Bartlett,et al.  Classifying Facial Actions , 1999, IEEE Trans. Pattern Anal. Mach. Intell..