A social tag-based dimensional model of emotions: Building cross-domain folksonomies

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, which may be exploited by adaptation and personalization systems. To validate our model, we show that its representation of a number of core emotions is in accordance with the well known psychological circumplex model of affect. We also 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.