Introduces a novel order statistic, the "adapted Gini index," and relates it to the conventional form of Bradford's law. An alternative index of dispersion is suggested based on the relative entropy of the frequency distribution. A variety of experimental data is reported. (VT)

The indexing depth in several documentation systems is shown to have a mixed Poisson distribution. (PF)

This report summarizes the frequency of use of the 7144 descriptors used for indexing technical reports in the Defense Documentation Center (DDC) collection. The descriptors are arranged alphabetically in the first section and by frequency in the second section. The frequency data cover about 427,000 AD documents spanning the interval from March…

A series of experiments was performed to investigate the effectiveness and utility of automatically classifying documents through the use of multiple discriminant functions. Classification is accomplished by computing the distance from the mean vector of each category to the vector of observed frequencies of a document and assigning the document…

The report very briefly summarizes the research performed during the contract period March 1, 1964, to February 28, 1971. The emphasis of the research was on the discovery and development of techniques for automatically indexing and classifying documents. The research was limited to statistical techniques rather than semantic or syntactic. A…

A collection of twenty-three lexical resources in information science, published in both the United States and Europe between 1960 and 1967, was analyzed with the purpose of tabulating the occurrence of different terms in them. This analysis, accomplished by means of a matrix generated on the IBM System 360 Model 40 computer, quantified the…

An experiment was conducted based on an information service for planners run in conjunction with Geo Abstracts Limited. Forth-eight styles of abstracting journals were produced which, although based on the same source material, differed in depth of coverage, frequency of publication, content of entry, and whether an index was included. One style…

The major advantage of sequential classification, a technique for automatically classifying documents into previously selected categories, is that the entire document need not be processed before it is classified. This method assumes the availability of a priori categories, a selection of keywords representative of these categories, and the a…

The feasibility of using a distance measure, called the Bayesian distance, for automatic sequential document classification was studied. Results indicate that, by observing the variation of this distance measure as keywords are extracted sequentially from a document, the occurrence of noisy keywords may be detected. This property of the distance…

The following topics are included in this document: (1) evaluation of plans for implementation of new systems; (2) macroevaluation of document retrieval systems; (3) microevaluation of retrospective searching; (4) evaluation of document acquisition functions; evluation of indexing and indexing languages; (5) evaluation of document screening; (6)…

A DETAILED ANALYSIS OF THE RETRIEVAL EVALUATION RESULTS OBTAINED WITH THE AUTOMATIC SMART DOCUMENT RETRIEVAL SYSTEM FOR DOCUMENT COLLECTIONS IN THE FIELDS OF AERODYNAMICS, COMPUTER SCIENCE, AND DOCUMENTATION IS GIVEN IN THIS REPORT. THE VARIOUS COMPONENTS OF FULLY AUTOMATIC DOCUMENT RETRIEVAL SYSTEMS ARE DISCUSSED IN DETAIL, INCLUDING THE FORMS OF…