Search (5 results, page 1 of 1)

0.023341617 = product of:
  0.046683233 = sum of:
    0.046683233 = product of:
      0.09336647 = sum of:
        0.09336647 = weight(_text_:systems in 2264) [ClassicSimilarity], result of:
          0.09336647 = score(doc=2264,freq=12.0), product of:
            0.16037072 = queryWeight, product of:
              3.0731742 = idf(docFreq=5561, maxDocs=44218)
              0.052184064 = queryNorm
            0.58219147 = fieldWeight in 2264, product of:
              3.4641016 = tf(freq=12.0), with freq of:
                12.0 = termFreq=12.0
              3.0731742 = idf(docFreq=5561, maxDocs=44218)
              0.0546875 = fieldNorm(doc=2264)
      0.5 = coord(1/2)
  0.5 = coord(1/2)

Abstract

State of the art review of information retrieval systems, defined as systems retrieving documents a sopposed to numerical data. Explains the classic Cranfield studies that have served as a standard for retrieval testing since the 1960s and discusses the Cranfield model and its relevance based measures of retrieval effectiveness. Details sosme of the problems with the Cranfield instruments and issues of validity and reliability, generalizability, usefulness and basic concepts. Discusses the evaluation of the Internet search engines in light of the Cranfield model, noting the very real differences between batch systems (Cranfield) and interactive systems (Internet). Because the Internet collection is not fixed, it is impossible to determine recall as a measure of retrieval effectiveness. considers future directions in evaluating information retrieval systems

0.015401474 = product of:
  0.030802948 = sum of:
    0.030802948 = product of:
      0.061605897 = sum of:
        0.061605897 = weight(_text_:systems in 7963) [ClassicSimilarity], result of:
          0.061605897 = score(doc=7963,freq=4.0), product of:
            0.16037072 = queryWeight, product of:
              3.0731742 = idf(docFreq=5561, maxDocs=44218)
              0.052184064 = queryNorm
            0.38414678 = fieldWeight in 7963, product of:
              2.0 = tf(freq=4.0), with freq of:
                4.0 = termFreq=4.0
              3.0731742 = idf(docFreq=5561, maxDocs=44218)
              0.0625 = fieldNorm(doc=7963)
      0.5 = coord(1/2)
  0.5 = coord(1/2)

Abstract

Reports the preliminary results of an investigation into the effectiveness of colinked descriptors, a new concept and technique suitable for incorporating into the design of interfaces for information retrieval. The idea is borrowed from the analogous idea in bibliometrics-cocited references. Preliminary results suggest that the technique is extremely effective. As a retrieval technique, colinked descriptors can easily be incorporated into information retrieval interfaces, front-end systems, or standalone, pre-search systems

0.014140441 = product of:
  0.028280882 = sum of:
    0.028280882 = product of:
      0.056561764 = sum of:
        0.056561764 = weight(_text_:22 in 3035) [ClassicSimilarity], result of:
          0.056561764 = score(doc=3035,freq=2.0), product of:
            0.1827397 = queryWeight, product of:
              3.5018296 = idf(docFreq=3622, maxDocs=44218)
              0.052184064 = queryNorm
            0.30952093 = fieldWeight in 3035, product of:
              1.4142135 = tf(freq=2.0), with freq of:
                2.0 = termFreq=2.0
              3.5018296 = idf(docFreq=3622, maxDocs=44218)
              0.0625 = fieldNorm(doc=3035)
      0.5 = coord(1/2)
  0.5 = coord(1/2)

Date

22. 2.1999 16:56:06

0.008167865 = product of:
  0.01633573 = sum of:
    0.01633573 = product of:
      0.03267146 = sum of:
        0.03267146 = weight(_text_:systems in 4216) [ClassicSimilarity], result of:
          0.03267146 = score(doc=4216,freq=2.0), product of:
            0.16037072 = queryWeight, product of:
              3.0731742 = idf(docFreq=5561, maxDocs=44218)
              0.052184064 = queryNorm
            0.2037246 = fieldWeight in 4216, product of:
              1.4142135 = tf(freq=2.0), with freq of:
                2.0 = termFreq=2.0
              3.0731742 = idf(docFreq=5561, maxDocs=44218)
              0.046875 = fieldNorm(doc=4216)
      0.5 = coord(1/2)
  0.5 = coord(1/2)

Abstract

This article introduces a new concept and technique for information retrieval called 'colinked descriptors'. Borrowed from an analogous idea in bibliometrics - cocited references - colinked descriptors provide a theory and method for identifying search terms that, by hypothesis, will be superior to those entered initially by a searcher. The theory suggests a means of moving automatically from 2 or more initial search terms, to other terms that should be superior in retrieval performance to the 2 original terms. A research project designed to test this colinked descriptor hypothesis is reported. The results suggest that the approach is effective, although methodological problems in testing the idea are reported. Algorithms to generate colinked descriptors can be incorporated easily into system interfaces, front-end or pre-search systems, or help software, in any database that employs a thesaurus. The potential use of colinked descriptors is a strong argument for building richer and more complex thesauri that reflect as many legitimate links among descriptors as possible

0.0068065543 = product of:
  0.013613109 = sum of:
    0.013613109 = product of:
      0.027226217 = sum of:
        0.027226217 = weight(_text_:systems in 3004) [ClassicSimilarity], result of:
          0.027226217 = score(doc=3004,freq=2.0), product of:
            0.16037072 = queryWeight, product of:
              3.0731742 = idf(docFreq=5561, maxDocs=44218)
              0.052184064 = queryNorm
            0.1697705 = fieldWeight in 3004, product of:
              1.4142135 = tf(freq=2.0), with freq of:
                2.0 = termFreq=2.0
              3.0731742 = idf(docFreq=5561, maxDocs=44218)
              0.0390625 = fieldNorm(doc=3004)
      0.5 = coord(1/2)
  0.5 = coord(1/2)

Abstract

The purpose of this article is to bring attention to the problem of variations in relevance assessments and the effects that these may have on measures of retrieval effectiveness. Through an analytical review of the literature, I show that despite known wide variations in relevance assessments in experimental test collections, their effects on the measurement of retrieval performance are almost completely unstudied. I will further argue that what we know about tha many variables that have been found to affect relevance assessments under experimental conditions, as well as our new understanding of psychological, situational, user-based relevance, point to a single conclusion. We can no longer rest the evaluation of information retrieval systems on the assumption that such variations do not significantly affect the measurement of information retrieval performance. A series of thourough, rigorous, and extensive tests is needed, of precisely how, and under what conditions, variations in relevance assessments do, and do not, affect measures of retrieval performance. We need to develop approaches to evaluation that are sensitive to these variations and to human factors and individual differences more generally. Our approaches to evaluation must reflect the real world of real users