Towards expert systems for the selection of search keys

Intermediary expert systems are designed to mediate between end-users and complex information retrieval systems. However, since most of these expert systems are based on text analysis rather than on models of hum man searching, they cannot process requestrelated criteria, such as precision or recall requirements. Analysis of the searching behavior of human intermediaries revealed a routine for the selection of search keys-freetext or controlled vocabulary-along a decision tree. Examples of decision rules demonstrate that although further research is required, these rules can be automated to significantly enhance the adaptability of inter. mediary expert systems.