DEGARI 2.0: A diversity-seeking, explainable, and affective art recommender for social inclusion

We present DEGARI 2.0 (Dynamic Emotion Generator And ReclassIfier): an explainable, affective-based, art recommender relying on the commonsense reasoning framework TCL and exploiting ontological model formalizing Plutchik’s theory of emotions. The main novelty this system relies development diversity-seeking affective recommendations obtained by spatial structure ‘wheel emotion’. In particular, such allows to classify suggest, museum users, cultural items able evoke not only very same emotions already experienced or preferred objects (e.g. within a exhibition), but also novel sharing different emotional stances. system’s goal, therefore, is break filter bubble effect open users’ view towards more inclusive empathy-based interpretations content. has been tested, in context EU H2020 SPICE project, community deaf people collection GAM Museum Turin. report results lessons learnt concerning both acceptability perceived explainability received recommendations.