Correlation model for user perceived web quality

Abstract

We present a novel correlation model for measuring web quality based on user perception. In contrast to previous methods, our approach is based on correlation analysis of web quality metrics at user-perceived level. Our model has three significant characteristics. First, we extract several web quality metrics which are closely related to user's subjective feelings. Second, by means of Pearson correlation analysis, we acquire five key metrics best reflecting web quality. Third, based on selected web quality metrics, we propose a novel comprehensive assessment model of web quality. We demonstrate the effectiveness of our approach by evaluating comprehensive assessment scores. A series of real-world experiments are conducted to qualitatively evaluate the effectiveness of our model. Results show that our model can be more intuitive to reflect user's quality of experience (QoE).