Retriever: an agent for intelligent information recovery
Dimitris Fragoudis, SPIRIDON D. LIKOTHANASSIS · Journal of the Association for Information Systems · 1999
With the exponential growth of the Internet and the volume of information published over it, searching for information of interest has become a very difficult and time-consuming task. Search engines, although they have been developed to help people cope with all of this information, have many shortcomings. In this paper, we present our ongoing work on Retriever, an autonomous agent that executes user-queries and returns high quality results to the user. Retriever utilizes existing search engines to obtain the starting points for its subsequent autonomous exploration of the Web. It then conducts a self-training process, in order to learn the query domain and increase its efficiency. When the query domain is learned, the agent expands the original query, reforms its search strategy, and goes out looking for the documents requested by the user.