A Framework for Performance Evaluation of Intelligent Search Agents

摘要

Because of the intelligent search agents (ISAs) can automate the process of searching through and evaluating reams of information on the Web, these agents are becoming increasingly popular in applications such as e-commerce and online businesses worldwide. While efforts have been made recently to develop various ISAs and multi-agents systems, very little is understood and known about the performance evaluation of such agents. A robust framework is required to assist efficient performance evaluation of ISAs. In this paper, we propose aframeworkfor performance evaluation and comparison of ISAs. The proposed framework allows experimentation in which search agents can be evaluated based on a performance metric. This paper provides an in-depth performance evaluation of five selected ISAs to verify the robustness of the framework. The proposed framework is simple and can easily be adapted to applications requiring performance evaluation of similar intelligent agents.