A data mining-based method for the incremental update of supporting personalized information filtering

Information filtering is an area of research that develops tools for discriminating between relevant and irrelevant information. Users first give descriptions about what they need, i.e., user profiles represented by a set of keywords, to start the services. A profile index is built on these profiles. Then, the Web page will be recommended to the users whose profiles belong to the filtered results. Therefore, a critical issue of the information filtering service is how to index the user profiles for an efficient matching process. Among previous proposed methods, Wu and Chen's graph-based index method can expect to minimize the storage space. However, when the users often change their interests, the index structure of Wu and Chen's method needs to be reconstructed, resulting in the high update cost. Therefore, in this paper, we propose a data mining-based method for the incremental update of the index structure, the updatabte tree, to reduce the update cost. In fact, each keyword could have a weight representing the degree of importance to a user. We apply this feature to distinguish between long-term and short-term interests. By making use of the property that the short-term interest has a higher probability to be changed than the long-term one, our proposed method can locally update the short-term interest, resulting in the low update cost. According to our experimental results, our method really can reduce the update cost as needed by Wu and Chen's method.