Evaluation of web search engines

• Main Author: Wang, Yali
• Other Authors: Li, Kin F.
• Language: English; en
• Published: 2010
• Subjects: Web search engines; World Wide Web; UVic Subject Index::Sciences and Engineering::Applied Sciences::Computer science
• Online Access: http://hdl.handle.net/1828/2523

Using the proper search engine is crucial for efficient and effective web search. The objective of this thesis is to develop methodologies to evaluate search engines in a systematic and reliable manner. A new model for evaluation and comparison of search engines is proposed. This hierarchical model classifies the most common features found in search engines and search results into groups and subgroups. To illustrate the usefulness of the proposed model, several Chinese search engines are evaluated and compared as a case study. It is also very important to evaluate the performance of a search engine over time. Three performance measurement metrics are formulated for this purpose. Performance results for English and Chinese search engines are represented by histograms for visual inspection. The histograms are classified into groups to facilitate the interpretation of the performance metrics and examination of the associated behaviours of the search engines. An automated classification method is developed that eliminates the subjectivity and ambiguity found in visual classification of the histograms.