An Emotion Dimensional Model Based on Social Tags: Crossing Folksonomies and Enhancing Recommendations.

In this paper we present an emotion computational model based on social tags. The model is built upon an automatically generated lexicon that describes emotions by means of synonym and antonym terms, and that is linked to multiple domain-specific emotion folksonomies extracted from entertainment social tagging systems. Using these cross-domain folksonomies, we develop a number of methods that automatically transform tag-based item profiles into emotion-oriented item profiles. To validate our model we report results from a user study that show a high precision of our methods to infer the emotions evoked by items in the movie and music domains, and results from an offline evaluation that show accuracy improvements on model-based recommender systems that incorporate the extracted item emotional information.