Subject and citation indexing. Part II: The optimal, cluster‐based retrieval performance of composite representations

Measures of cluster‐based retrieval effectiveness are computed for five composite representations in the cystic fibrosis (CF) Document Collection. The composite representations are constructed from combinations of two subject representations, based on Medical Subject Headings and subheadings, and two citation representations, consisting of the complete list of cited references and a comprehensive list of citations for each document. Experimental retrieval results are presented as a function of the exhaustivity and similarity of the composite representations and reveal consistent patterns from which optimal performance levels can be identified. The optimal performance values provide an assessment of the absolute capacity of each composite representation to associate documents relevant to the same query and discriminate between documents relevant to different queries in single‐link hierarchies. The optimal performance values for all composite representations are completely comparable and are superior to the optimal performance of constituent representations. Optimal performance consistently occurs at low levels of exhaustivity. Exhaustive composite representations that include subject descriptions produce the lowest levels of performance; retrieval results derived from random structures are comparable to the observed results. The effectiveness of the exhaustive representation composed of references and citations is materially superior to the effectiveness of exhaustive composite representations that include subject descriptions. © 1991 John Wiley & Sons, Inc.