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.
Predicting the impact of advertisements on web pages aesthetic impressions
FENU, GIANNI;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.
File in questo prodotto:
| File | Dimensione | Formato | |
|---|---|---|---|
|
kicss2014 (1).pdf
Solo gestori archivio
Tipologia:
versione editoriale (VoR)
Dimensione
566.68 kB
Formato
Adobe PDF
|
566.68 kB | Adobe PDF | Visualizza/Apri Richiedi una copia |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
