Analyzing User Behavior to Rank Desktop Items

Existing desktop search applications, trying to keep up with the rapidly increasing storage capacities of our hard disks, are an important step towards more efficient personal information management, yet they offer an incomplete solution. While their indexing functionalities in terms of different file types they are able to cope with are impressive, their ranking capabilities are basic, and rely only on textual retrieval measures, comparable to the first generation of web search engines. In this paper we propose to connect semantically related desktop items by exploiting usage analysis information about sequences of accesses to local resources, as well as about each user’s local resource organization structures. We investigate and evaluate in detail the possibilities to translate this information into a desktop linkage structure, and we propose several algorithms that exploit these newly created links in order to efficiently rank desktop items. Finally, we empirically show that the access based links lead to ranking results comparable with TFxIDF ranking, and significantly surpass TFxIDF when used in combination with it, making them a very valuable source of input to desktop search ranking algorithms.