Subgroup Discovery among Personal Homepages

This paper discusses our algorithm for finding subgroups among personal homepages. Assuming that personal homepages usually carry personal information, we have developed an algorithm that allows us to automatically find potential patterns from them. For example, when the algorithm is applied to personal homepages at some school, we can approximate the ratio between the number of students interested in information science and that of students interested in social science. In the experiment, we successfully created subgroups that showed characteristics of the school. Also, we found relations between subgroups that are important for enhancing human activity.