A composite framework for supporting user emotion detection based on intelligent taxonomy handling

One of the most relevant issues of a social robot is its capability of catching the attention of a new acquaintance and empathize with her. The first steps towards a system which can be used by a social robot in order to be empathetic are illustrated in this paper. The system can analyze the Twitter ID of the new acquaintance, trying to detect the IAB (Interactive Advertising Bureau) Tier 1 categories that possibly can let arise in him/her a joyful feeling. Furthermore, it can retrieve news about that category and report them to the user, hopefully increasing his/her curiosity towards the system, improving the naturalness of the interaction. Moreover, the system is capable of querying Wikipedia in order to clarify any doubts that may arise in the user. A sample of a possible interaction is reported at the end of the paper.