Searching the Web Through User Information Spaces

Abstract

During the last years web search engines have moved from the simple but inefficient syntactical analysis (first generation) to the more robust and usable web graph analysis (second generation). Much of the current research is focussed on the so-called third generation search engines that, in principle, inject "human characteristics" on how results are obtained and presented to the end user. Approaches exploited towards this direction include (among others): an alteration of PageRank [1] that takes into account user specific characteristics and bias the page ordering using the user preferences (an approach, though, that does not scale well with the number of users). The approach is further exploited in [3], where several PageRanks are computed for a given number of distinct search topics. A similar idea is used in [6], where the PageRank computation takes into account the content of the pages and the query terms the surfer is looking for. In [4], a decomposition of PageRank to basic components is suggested that may be able to scale the different PageRank computations to a bigger number of topics or even distinct users. Another approach to web search is presented in [2], where a rich extension of the web, called semantic web, and the application of searching over this new setting is described.In this work we depart from the above lines of research and propose a new conceptual framework for representing the web and potentially improving search results. In particular, the new framework views the web as a collection of webrelated data collected and semi-organized by individual users inside their information spaces. These data can be explicitly collected (e.g., bookmarks) or implicitly collected (e.g., web-browsing history). Our approach is based on the observation that users act as small crawlers seeking information on the web using various media (search engines, catalogs, word-of-mouth, hyperlinks, direct URL typing, etc). They tend to store and organize important-for-them pages in tree-like structures, referred to as bookmark collections, where the folder names act as tags over the collected URLs. This method of organizing data helps people to recall collected URLs faster, but can also be used as a kind of semantic tagging over the URLs (the path to the URL can be perceived as different ways to communicate the URL itself). This information constitutes part of the user's personal information space and it is indicative of his interests. One might argue that people do not collect bookmarks or that they do not organize them in any reasonable manner. However, as our experiments show, people indeed collect and organize bookmarks under certain patterns that follow power law distributions.

A Collaborative Decentralized Approach to Web Search

“…Finally, in Section X, we discuss related papers and web sites that share common ideas with our work. Preliminary portions of this work appeared in [27], [28].…”