Expected search length: A single measure of retrieval effectiveness based on the weak ordering action of retrieval systems

作者: William S. Cooper

DOI: 10.1002/ASI.5090190108

关键词:

摘要: A measure of document retrieval system performance called the “expected search length reduction factor” is defined and compared with indicators, such as precision recall, that have been suggested by other workers. The new based on calculations expected number irrelevant documents in collection which would to be searched through before desired relevant could found. Its advantages are: (1) it provides a single index for property attempts measure; (2) allows gradations status, mathematical concept “weak ordering”; (3) evaluates relative random searching; (4) takes into account amount material requester.

参考文章(6)
D. R. Swanson, Searching Natural Language Text by Computer Science. ,vol. 132, pp. 1099- 1104 ,(1960) , 10.1126/SCIENCE.132.3434.1099
J. A. Swets, Information Retrieval Systems. Science. ,vol. 141, pp. 245- 250 ,(1963) , 10.1126/SCIENCE.141.3577.245
J. Verhoeff, W. Goffman, Jack Belzer, Inefficiency of the use of Boolean functions for information retrieval systems Communications of the ACM. ,vol. 4, pp. 557- 558 ,(1961) , 10.1145/366853.366861
Patrick Suppes, Introduction to logic ,(1957)
Harry Bornstein, A paradigm for a retrieval effectiveness experiment American Documentation. ,vol. 12, pp. 254- 259 ,(1961) , 10.1002/ASI.5090120403