A model for the evaluation of expansion techniques in information retrieval systems

We describe an evaluation model for expansion systems in information retrieval, that is, systems expanding a user selection of documents in order to provide the user with a larger set of documents sharing the same or related characteristics. Our model leads to a test protocol and practical estimates of the efficiency of an expansion system provided that it is possible for a sample of users to exhaustively scan the content of a subset of the database in order to decide which documents would have been selected by an «ideal» expansion system. This condition is met only by databases whose unit contents can be quickly apprehended, such as still image databases or synthetic bibliographical references. We compare our model with other types of possible indicators, and discuss the precision to which our measure can be estimated, using data from experimentation with an image database system developed by our research team