Quality Evaluation of Search Results by Typicality and Speciality of Terms Extracted from Wikipedia

  • Authors:

  • Makoto Nakatani;Adam Jatowt;Hiroaki Ohshima;Katsumi Tanaka

  • Affiliations:

  • Department of Social Informatics, Graduate School of Informatics, Kyoto University, Kyoto, Japan 606-8501;Department of Social Informatics, Graduate School of Informatics, Kyoto University, Kyoto, Japan 606-8501;Department of Social Informatics, Graduate School of Informatics, Kyoto University, Kyoto, Japan 606-8501;Department of Social Informatics, Graduate School of Informatics, Kyoto University, Kyoto, Japan 606-8501

  • Venue:
  • DASFAA '09 Proceedings of the 14th International Conference on Database Systems for Advanced Applications
  • Year:
  • 2009

Quantified Score

Hi-index 0.01

Visualization

Abstract

In Web search, it is often difficult for users to judge which page they should choose among search results and which page provides high quality and credible content. For example, some results may describe query topics from narrow or inclined viewpoints or they may contain only shallow information. While there are many factors influencing quality perception of search results, we propose two important aspects that determine their usefulness, "topic coverage" and "topic detailedness". "Topic coverage" means the extent to which a page covers typical topics related to query terms. On the other hand, "topic detailedness" measures how many special topics are discussed in a Web page. We propose a method to discover typical topic terms and special topics terms for a search query by using the information gained from the structural features of Wikipedia, the free encyclopedia. Moreover, we propose an application to calculate topic coverage and topic detailedness of Web search results by using terms extracted from Wikipedia.