Performance Evaluation of Selected Search Engines

Abstract

Search Engines have become an integral part of daily internet usage. The search engine is the first stop for web users when they are looking for a product. Information retrieval may be viewed as a problem of classifying items into one of two classes corresponding to interesting and uninteresting items respectively. A natural performance metric in this context is classification accuracy, defined as the fraction of the system's interesting/uninteresting predictions that agree with the user's assessments. On the other hand, the field of information retrieval has two classical performance evaluation metrics: precision, the fraction of the items retrieved by the system that are interesting to the user, and recall, the fraction of the items of interest to the user that are retrieved by the system. Measuring the information retrieval effectiveness of World Wide Web search engines is costly because of human relevance judgments involved. However, both for business enterprises and people it is important to know the most effective Web search engines, since such search engines help their users find higher number of relevant Web pages with less effort. Furthermore, this information can be used for several practical purposes. This study evaluates the performance of three Web search engines. A set of measurements is proposed for evaluating Web search engine performance.