Towards a social robot as interface for tourism recommendations

The popularity of social robots is steadily increasing, mainly due to the interesting impact they have in several application domains. In this paper, we propose the use of Pepper Robot as an interface of a recommender system for tourism. In particular, we used the robot to interact with the users and to provide them with personalized recommendations about hotels, restaurants, and points of interest in the area. The personalization mechanism encoded in the social robot relies on soft biometrics traits automatically recognized by the robot, as age and gender, user interests and personal facets. All these data are used to feed a neural network that returns as output the most suitable recommendations for the target user. To evaluate the effectiveness of the interaction driven by a social robot, we carried out a user study whose goal was to evaluate: (1) how the robot affects the perceived accuracy of the recommendations; (2) how the user experience and the engagement vary by interacting with a social robot instead of a classic web application. Even if there is a large room for improvement, mainly due to the poor speech recognizer integrated in the Pepper, the results showed that the robot can strongly attract people, thanks to its presence and interaction capabilities. These findings encouraged us in performing a larger field study to test the approach in the wild and to understand whether it can increase the acceptance of recommendations in real environments.