An Affect-Aware Computational Model for supporting decision-making through Recommender Systems

Affects play a crucial role in human decision-making. They concern the personal cognitive and affective characterization of behaviors, and they are the outcomes of an internal reasoning process which is highly influenced by the context of the decisional event. Intelligent systems have recently started to include these aspects in their reasoning processes in order to increase their performance when supporting users during decisional situations. Nevertheless, when emotions are treated merely as additional user features of the classic model of information formalization, they could produce noise in the data and consequently, it could be possible to observe an unexpected reduction the overall system accuracy. The main motivation for this work is strictly linked with the considerations just explained. Nowadays, personalized systems, i.e. systems able to adapt their behavior to user preferences and needs, usually take into account emotional variables as contextual factors, thus implementing the influence-on metaphor according to which emotions are considered as external forces influencing an otherwise non-emotional process. The main challenge from both a user modeling and decision-making perspective is how to represent the whole affective state of the user in terms of emotions, mood, and personality in order to include this information in the user profile to be exploited for personalization.