Mimicking Web search engines for expert search

✍ Scribed by Rodrygo L.T. Santos; Craig Macdonald; Iadh Ounis

• Book ID: 113664006
• Publisher: Elsevier Science
• Year: 2011
• Tongue: English
• Weight: 248 KB
• Volume: 47
• Category: Article
• ISSN: 0306-4573
• DOI: 10.1016/j.ipm.2010.11.009

✦ Synopsis

Many enterprise employees may publish content outside their corporate intranet, making the Web a valuable source for identifying company experts. In this article, we thoroughly investigate the usefulness of Web search engines (WSEs) for expert search. In particular, we claim that the ranking of documentary expertise evidence provided by a WSE should also give an indication of the importance of such evidence. To investigate this, we mimic the rankings of seven different WSEs by trying to reproduce their underlying ranking mechanisms in order to search for candidate experts in the TREC CERC collection. Experimental results show that our approach is effective for expert search, and can significantly improve an intranet-based expert search engine. Moreover, when the mimicking of WSEs is further improved by training, expert search performance is also generally enhanced. Finally, we show that WSEs can be mimicked as effectively using only titles and snippets instead of the full content of WSEs’ results, while drastically reducing network costs.