Reexamination on potential for personalization in web search

  • Authors:
  • Daren Li;Muyun Yang;Haoliang Qi;Sheng Li;Tiejun Zhao

  • Affiliations:
  • Harbin Institute of Technology;Harbin Institute of Technology;Heilongjiang Institute of Technology;Harbin Institute of Technology;Harbin Institute of Technology

  • Venue:
  • COLING '10 Proceedings of the 23rd International Conference on Computational Linguistics: Posters
  • Year:
  • 2010

Quantified Score

Hi-index 0.00

Visualization

Abstract

Various strategies have been proposed to enhance web search through utilizing individual user information. However, considering the well acknowledged recurring queries and repetitive clicks among users, it is still an open issue whether using individual user information is a proper direction of efforts in improving the web search. In this paper, we first quantitatively demonstrate that individual user information is more beneficial than common user information. Then we statistically compare the benefit of individual and common user information through Kappa statistic. Finally, we calculate potential for personalization to present an overview of what queries can benefit more from individual user information. All these analyses are conducted on both English AOL log and Chinese Sogou log, and a bilingual perspective statistics consistently confirms our findings.