Increasing the authoritativeness of web recommendations using PageRank-based approaches

摘要

Purpose - Web content has been widely used for recommending personal webpages. Despite itsrnpopularity, the content-based approach regards a webpage simply as a piece of text, thereby oftenrnresulting in less authoritative recommendations of webpages. This paper aims to propose novelrnapproaches that utilise other sources of information pertaining to webpages to facilitate the automaticrnconstruction of an authoritative web recommender system.rnDesign/methodology/approach - In this research, four approaches that exploit hyperlinkrnstructure, web content and web-usage logs for making recommendations are proposed. Thernproposed approaches have been implemented as a prototype system, called the authoritative webrnrecommender (AWR) system. An evaluation using the web-usage logs and the corresponding pages ofrna university web site was performed.rnFindings - The results from the evaluations using empirical data demonstrate that the four proposedrnapproaches outperform the traditional content-only approach.rnOriginality/value - This paper describes a novel way to combine information retrieval, usagernmining and hyperlink structure analysis techniques to find relevant and authoritative webpages forrnrecommendation.