International Business Machines Corporation
Online site prediction and mitigation

Abstract:

Using natural language analysis of content at URLs accessed by a user, content metadata is generated. From the content metadata and from activity information associated with a set of URLs accessed by the user, a class model is generated that represents a probability that content referenced by a URL will distract the user. Using the class model to analyze content referenced by a received URL, a probability is forecasted that the content referenced by the received URL will distract the user.