Empirical Aesthetics

Leveraging Instagram data to compute a measure of Aesthetic Appeal

“3,058 people like this.” In the digital age, people very commonly indicate their preferences by clicking a Like button. The data generated on the world’s largest photo-sharing platform Instagram potentially represents a vast, freely accessible resource for research in the ﬁeld of visual aesthetics. We compiled a photo database using images of different Instagram accounts that fullﬁl several criteria (e.g., large followership, consistent content, regular posting habit). Our database consists of about 100.000 photographs with the corresponding liking data generated by the Instagram community. It contains different genres, ranging from architecture, landscapes, artworks, black and white photography, documentary photography to animal portraits. We developed a method to “normalize” Instagram Likes which resulted in the so-called Image Aesthetic Appeal (IAA) score. The IAA score was validated as a measure of the aesthetic appeal of images (Thömmes & Hübner, in press). With such a measure at hand it becomes possible to study low-level features of “good” image composition based on large datasets.
This project illustrates the potential of using Instagram data to compute a measure of aesthetic appeal and provides a fruitful methodological basis for future research. If you are interested in using our database please don’t hesitate to get in touch!

Thömmes, K., & Hübner, R. (2020). Why people press "Like": A new measure for aesthetic appeal derived from Instagram data. Psychology of Aesthetics, Creativity, and the Arts. <doi> <pdf>

Thömmes, K., & Hübner, R. (2018). Instagram likes for architectural photos can be predicted by quantitative balance measures and curvature. Frontiers in Psychology, 9. <Open Access>

Leveraging Instagram data to compute a measure of Aesthetic Appeal

Related Articles

Related Posters