Incorporating affectivity into preference elicitation for personalizesd recommendation via spreading activation

Personalized recommender system is an indispensable application and re-shaping the world in e-commerce scopes. Following a brief review of approaches to elucidate personalized recommendation, our research work focuses on exploring a new approach of semantically associated extension by integrating the Spreading Activation model with the knowledge of chromatology to dynamically acquire the information of user preference. We attempt to apply a characteristic sequence consisted of color nodes mapping the relationships between user mood preference and item feature and illustrated the proposed approach through an instantiation of movie recommendation. This paper presents a novel insight into exploitation of rich repository of the domain-specific knowledge to elicit optimum recommendation for user.