On Improving Wikipedia Search using Article Quality

• Main Authors: HU, Meiqun, LIM, Ee Peng, SUN, Aixin, LAUW, Hady Wirawan, VUONG, Ba-Quy
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2007
• Subjects: Databases and Information Systems; Numerical Analysis and Scientific Computing
• Online Access: https://ink.library.smu.edu.sg/sis_research/1264; https://ink.library.smu.edu.sg/context/sis_research/article/2263/viewcontent/improveWikiSearch.pdf
• Institution: Singapore Management University

Wikipedia is presently the largest free-and-open online encyclopedia collaboratively edited and maintained by volunteers. While Wikipedia offers full-text search to its users, the accuracy of its relevance-based search can be compromised by poor quality articles edited by non-experts and inexperienced contributors. In this paper, we propose a framework that re-ranks Wikipedia search results considering article quality. We develop two quality measurement models, namely Basic and PeerReview, to derive article quality based on co-authoring data gathered from articles' edit history. Compared with Wikipedia's full-text search engine, Google and Wikiseek, our experimental results showed that (i) quality-only ranking produced by PeerReview gives comparable performance to that of Wikipedia and Wikiseek; (ii) PeerReview combined with relevance ranking outperforms Wikipedia's full-text search significantly, delivering search accuracy comparable to Google.