Statistical profiles of highly-rated web sites

We are creating an interactive tool to help non-professional web site builders create high quality de-signs. We have previously reported that quantitative mea-sures of web page structure can predict whether a site will be highly or poorly rated by experts, with accuracies ranging from 67–80%. In this paper we extend that work in several ways. First, we compute a much larger set of measures (157 versus 11), over a much larger collection of pages (5300 vs. 1900), achieving much higher overall accuracy (94 % on av-erage) when contrasting good, average, and poor pages. Sec-ond, we introduce new classes of measures that can make as-sessments at the site level and according to page type (home page, content page, etc.). Finally, we create statistical pro-files of good sites, and apply them to an existing design, showing how that design can be changed to better match high-quality designs