Predicting the impact of advertisements on web pages aesthetic impressions

FENU, GIANNI;Fadda G;SPANO, LUCIO DAVIDE

2014-01-01

---

Abstract

In this paper we study the impact of advertisements on a predictive model for web pages impressions, calculated according to a set of features on the rendered page images. We analysed the effects on two different predictors, the colourfulness and the visual complexity. We compared the prediction against ground-truth values, obtained through a user study. We conclude that the prediction model behaves correctly for the complexity, but it is not able to predict the increase on the colourfulness ratings.