Predicting the Artworks Beauty: Elements of Predictive Aesthetics

This paper presents the findings of an experiment conducted in an innovative way through the use of the most popular social network: Facebook. Exploiting the-system of "like" and "share", on which this online platform is based, thousands of artwork images were submitted to a sample of over 10,000 users worldwide. Through the metrics analysis related to the aesthetic choices expressed by the users, it was observed that viewers are inclined to react in the same way towards certain visual stimuli coming from the artworks: some compositional elements inside the artworks are able to drive the aesthetic preferences towards some artworks rather than others. Therefore it may be possible to predict the aesthetic reactions from the public introducing specific responsive elements inside the artworks, able to influence beforehand the aesthetic preferences.