Investigation of the role of similarity measure and ranking algorithm in mining social networks
Journal of Information Science
Hi-index | 0.00 |
Link analysis has been used to enhance retrieval resultsof the web search for years. PageRank and HITS arethe two well-known algorithms widely used by most researchers.The former analyzes the web links off-line, butdoes not consider either web topics or user's query. Thelatter judges the web page on-line according to the user'squery. Here we propose a novel algorithm, called "Topic-Centric",which also performs link analysis of web pagesoff-line. The authoritativeness of web pages is calculatedin accordance with the web topics. To test the effectiveness,we apply the proposed algorithm to re-rank the search resultsgiven by a traditional retrieval system. Preliminaryexperiments using standard web collections, though inconclusive,show interesting retrieval results.