Computational Model for Webpage Aesthetics using SVM

Abstract

Computational model for webpage aesthetics prediction helps designer to determine usability and to improve it. It has been reported that positional geometry of the webpage objects are primarily important for aesthetics computation. In this paper, we propose a computational model for predicting webpage aesthetics based on the positional geometry features of webpage objects. We have considered the best known 13 features that affect aesthetics. By varying these 13 features, we have designed 52 interfaces and rated them by 100 users in a 5 point Likerts scale. Our 1 dimensional ANOVA study on users rating shows, 9 out of the 13 features are important for webpage aesthetics. Based on these 9 features, we created a computational model for webpage aesthetics prediction. Our computational model works based on Support Vector Machine (SVM). To judge the efficacy of our model, we considered 10 popular webpages, and got them rated by 80 users. Experimental results show that our computational model can predict webpage aesthetics with an accuracy of 90%.