Tell Me What You Like and I’ll Tell You What You Are: Discriminating Visual Preferences on Flickr Data

Abstract

Abstract. The John Ruskin's 19th century adage suggests that personal taste is not merely an absolute set of aesthetic principles valid for everyone: actually, it is a process of interpretation which have also roots in one's life experiences. This aspect represents nowadays a major problem for inferring automatically the quality of a picture. In this paper, instead of trying to solve this age-old problem, we consider an intriguing, orthogonal direction, aimed at discovering how different are the personal tastes. Given a set of preferred images of a user, obtained from Flickr, we extract a pool of low-and high-level features; LASSO regression is then exploited to learn the most discriminative ones, considering a group of 200 random Flickr users. Such aspects can be easily recovered, allowing to understand what is the "what we like" which distinguish us from the others. We then perform multi-class classification, where a test sample is a set of preferred pictures of an unknown user, and the classes are all the users. The results are surprising: given only 1 image as test, we can match the user preferences definitely more than the chance, and with 20 images we reach an nAUC of 91%, considering the cumulative matching characteristic curve. Extensive experiments promote our approach, suggesting new intriguing perspectives in the study of computational aesthetics.

The Pictures We Like Are Our Image: Continuous Mapping of Favorite Pictures into Self-Assessed and Attributed Personality Traits

“…on those points where the image brightness shows discontinuities. Therefore, the feature extraction process adopts the Canny detector [45] to identify the edges and calculate the fraction of pixels in an image that lie on an edge (see Figure 3 for an example of edge extraction in an image).…”

The Eyes of the Beholder: Gender Prediction Using Images Posted in Online Social Networks

“…Their results suggest that digital records of human activities can be used to accurately predict a range of personal attributes such as age, gender, sexual orientation, political orientation, etc. Meanwhile, the work in [20] tried to build the connection between cognitive effects and the consumption of multimedia content. Image features, including both aesthetics and content, are employed to predict online users' personality traits.…”

Unveiling the multimedia unconscious

“…More recently, some works investigated the interplay between observable characteristics of multimedia data and cognition [26,54]. The first work [26] considers images tagged as "favourite" by a certain person as an expression of her aesthetic preferences and shows that, given a certain amount of pictures tagged as "favourite" by a certain individual, it is possible to predict whether the same will happen for another picture or set of pictures.…”

“…The first work [26] considers images tagged as "favourite" by a certain person as an expression of her aesthetic preferences and shows that, given a certain amount of pictures tagged as "favourite" by a certain individual, it is possible to predict whether the same will happen for another picture or set of pictures. The second work [54] investigates the characteristics of abstract paintings that stimulate certain emotional reactions rather than others.…”

“…The second work [54] investigates the characteristics of abstract paintings that stimulate certain emotional reactions rather than others. Both works shift the attention from the bare content of images to their potential role in a communication process, namely a person expressing aesthetic preferences in [26] and a painter eliciting emotions in [54]. However, unlike the perspective advocated in this article, both works take into account only one of the parties involved in the communication process.…”