Predicting Web Interface Quality Assessment Using Support Vector Machine

Abstract

Internet websites are promising as the products for providing services. The key issues related to website engineering are very essential. These websites need to measure and evaluate for quality and for better understanding. Several Metrics were proposed to correspond with items that Web usability guideline associate with good design. In this paper, we investigate empirically the web page quality on the basis of the 16 assessed metrics. We also propose Support Vector Machine (SVM) prediction model to predict the classification of the good web pages and not good web pages. We collect web sites from Webby awards data (2001-2010) and Top Ten PC Magazines. We express the findings of quantitative analysis of web page attributes and how these attributes are calculated. The metrics captured in SVM model can be used to predict the good and the bad of website design.