Sciweavers

Share
WWW
2004
ACM

Combining link and content analysis to estimate semantic similarity

9 years 10 months ago
Combining link and content analysis to estimate semantic similarity
Search engines use content and link information to crawl, index, retrieve, and rank Web pages. The correlations between similarity measures based on these cues and on semantic associations between pages therefore crucially affects the performance of any search tool. Here I begin to quantitatively analyze the relationship between content, link, and semantic similarity measures across a massive number of Web page pairs. Maps of semantic similarity across textual and link similarity highlight the potential and limitations of lexical and link analysis for relevance approximation, and provide us with a way to study whether and how text and link based measures should be combined. Categories and Subject Descriptors: H.3.1 [Information Storage and Retrieval]: Content Analysis and Indexing; H.3.3 [Information Storage and Retrieval]: Information Search and Retrieval General Terms: Measurement
Filippo Menczer
Added 22 Nov 2009
Updated 22 Nov 2009
Type Conference
Year 2004
Where WWW
Authors Filippo Menczer
Comments (0)
books