DirectoryRank: ordering pages in web directories

Web Directories are repositories of Web pages organized in a hierarchy of topics and sub-topics. In this paper, we present DirectoryRank, a ranking framework that orders the pages within a given topic according to how informative they are about the topic. Our method works in three steps: first, it processes Web pages within a topic in order to extract structures that are called lexical chains, which are then used for measuring how informative a page is for a particular topic. Then, it measures the relative semantic similarity of the pages within a topic. Finally, the two metrics are combined for ranking all the pages within a topic before presenting them to the users. Categories and Subject Descriptors H.3.3 [Information Search and Retrieval]: information filtering, retrieval models; H.3.m [Information Systems]: Miscellaneous General Terms Algorithms, Design, Experimentation, Measurement Keywords Web Directory, semantic similarity, ranking

• Type: Conference
• Year: 2005
• Where: WIDM
• Authors: Vlassis Krikos, Sofia Stamou, Pavlos Kokosis, Alexandros Ntoulas, Dimitris Christodoulakis
• Keywords: Pages, Semantic Similarity, Web Pages, WIDM 2005