An Automatic Page Classification Method to Improve User Experience on the Mobile Web

During the last years there has been an increase in mobile web browsing, fostered by the introduction of 3G mobile networks and highly capable mobile devices that offer enhanced browsing experiences. However, there are still many Web sites that are unaware of mobile presentation. Those Web sites, when accessed from mobile devices, do not allow a satisfactory user experience or may cause failure of the user's device. In this paper we present an automatic classification method capable of predicting if a given web page would provide (or not) a functional user experience in certain mobile environments. Our method could be used, for example, by mobile search engines, ranking pages not only from the point of view of their textual relevancy, but also from the point of view of their adaptability to the target delivery context. Our experimental results show high percentages of success for the method devised.