Search (51 results, page 1 of 3)

0.1050245 = product of:
  0.15753675 = sum of:
    0.13362148 = weight(_text_:book in 2946) [ClassicSimilarity], result of:
      0.13362148 = score(doc=2946,freq=12.0), product of:
        0.2237077 = queryWeight, product of:
          4.414126 = idf(docFreq=1454, maxDocs=44218)
          0.050679956 = queryNorm
        0.5973039 = fieldWeight in 2946, product of:
          3.4641016 = tf(freq=12.0), with freq of:
            12.0 = termFreq=12.0
          4.414126 = idf(docFreq=1454, maxDocs=44218)
          0.0390625 = fieldNorm(doc=2946)
    0.023915261 = product of:
      0.047830522 = sum of:
        0.047830522 = weight(_text_:search in 2946) [ClassicSimilarity], result of:
          0.047830522 = score(doc=2946,freq=4.0), product of:
            0.17614716 = queryWeight, product of:
              3.475677 = idf(docFreq=3718, maxDocs=44218)
              0.050679956 = queryNorm
            0.27153727 = fieldWeight in 2946, product of:
              2.0 = tf(freq=4.0), with freq of:
                4.0 = termFreq=4.0
              3.475677 = idf(docFreq=3718, maxDocs=44218)
              0.0390625 = fieldNorm(doc=2946)
      0.5 = coord(1/2)
  0.6666667 = coord(2/3)

Abstract

In both the social sciences and the humanities, books and monographs play significant roles in research communication. The absence of citations from most books and monographs from the Thomson Reuters/Institute for Scientific Information databases (ISI) has been criticized, but attempts to include citations from or to books in the research evaluation of the social sciences and humanities have not led to widespread adoption. This article assesses whether Google Book Search (GBS) can partially fill this gap by comparing citations from books with citations from journal articles to journal articles in 10 science, social science, and humanities disciplines. Book citations were 31% to 212% of ISI citations and, hence, numerous enough to supplement ISI citations in the social sciences and humanities covered, but not in the sciences (3%-5%), except for computing (46%), due to numerous published conference proceedings. A case study was also made of all 1,923 articles in the 51 information science and library science ISI-indexed journals published in 2003. Within this set, highly book-cited articles tended to receive many ISI citations, indicating a significant relationship between the two types of citation data, but with important exceptions that point to the additional information provided by book citations. In summary, GBS is clearly a valuable new source of citation data for the social sciences and humanities. One practical implication is that book-oriented scholars should consult it for additional citations to their work when applying for promotion and tenure.

0.092593215 = product of:
  0.13888982 = sum of:
    0.12197917 = weight(_text_:book in 966) [ClassicSimilarity], result of:
      0.12197917 = score(doc=966,freq=10.0), product of:
        0.2237077 = queryWeight, product of:
          4.414126 = idf(docFreq=1454, maxDocs=44218)
          0.050679956 = queryNorm
        0.5452614 = fieldWeight in 966, product of:
          3.1622777 = tf(freq=10.0), with freq of:
            10.0 = termFreq=10.0
          4.414126 = idf(docFreq=1454, maxDocs=44218)
          0.0390625 = fieldNorm(doc=966)
    0.016910642 = product of:
      0.033821285 = sum of:
        0.033821285 = weight(_text_:search in 966) [ClassicSimilarity], result of:
          0.033821285 = score(doc=966,freq=2.0), product of:
            0.17614716 = queryWeight, product of:
              3.475677 = idf(docFreq=3718, maxDocs=44218)
              0.050679956 = queryNorm
            0.19200584 = fieldWeight in 966, product of:
              1.4142135 = tf(freq=2.0), with freq of:
                2.0 = termFreq=2.0
              3.475677 = idf(docFreq=3718, maxDocs=44218)
              0.0390625 = fieldNorm(doc=966)
      0.5 = coord(1/2)
  0.6666667 = coord(2/3)

Abstract

This article offers important background information about a new product, the Book Citation Index (BKCI), launched in 2011 by Thomson Reuters. Information is illustrated by some new facts concerning The BKCI's use in bibliometrics, coverage analysis, and a series of idiosyncrasies worthy of further discussion. The BKCI was launched primarily to assist researchers identify useful and relevant research that was previously invisible to them, owing to the lack of significant book content in citation indexes such as the Web of Science. So far, the content of 33,000 books has been added to the desktops of the global research community, the majority in the arts, humanities, and social sciences fields. Initial analyses of the data from The BKCI have indicated that The BKCI, in its current version, should not be used for bibliometric or evaluative purposes. The most significant limitations to this potential application are the high share of publications without address information, the inflation of publication counts, the lack of cumulative citation counts from different hierarchical levels, and inconsistency in citation counts between the cited reference search and the book citation index. However, The BKCI is a first step toward creating a reliable and necessary citation data source for monographs - a very challenging issue, because, unlike journals and conference proceedings, books have specific requirements, and several problems emerge not only in the context of subject classification, but also in their role as cited publications and in citing publications.

Object

Book Citation Index

0.043820105 = product of:
  0.13146031 = sum of:
    0.13146031 = sum of:
      0.07652883 = weight(_text_:search in 1149) [ClassicSimilarity], result of:
        0.07652883 = score(doc=1149,freq=4.0), product of:
          0.17614716 = queryWeight, product of:
            3.475677 = idf(docFreq=3718, maxDocs=44218)
            0.050679956 = queryNorm
          0.43445963 = fieldWeight in 1149, product of:
            2.0 = tf(freq=4.0), with freq of:
              4.0 = termFreq=4.0
            3.475677 = idf(docFreq=3718, maxDocs=44218)
            0.0625 = fieldNorm(doc=1149)
      0.054931477 = weight(_text_:22 in 1149) [ClassicSimilarity], result of:
        0.054931477 = score(doc=1149,freq=2.0), product of:
          0.17747258 = queryWeight, product of:
            3.5018296 = idf(docFreq=3622, maxDocs=44218)
            0.050679956 = queryNorm
          0.30952093 = fieldWeight in 1149, 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=1149)
  0.33333334 = coord(1/3)

Abstract

This paper presents a test of the validity of using Google Scholar to evaluate the publications of researchers by comparing the premises on which its search engine, PageRank, is based, to those of Garfield's theory of citation indexing. It finds that the premises are identical and that PageRank and Garfield's theory of citation indexing validate each other.

Date

17.12.2013 11:02:22

0.030858565 = product of:
  0.09257569 = sum of:
    0.09257569 = weight(_text_:book in 4382) [ClassicSimilarity], result of:
      0.09257569 = score(doc=4382,freq=4.0), product of:
        0.2237077 = queryWeight, product of:
          4.414126 = idf(docFreq=1454, maxDocs=44218)
          0.050679956 = queryNorm
        0.41382432 = fieldWeight in 4382, product of:
          2.0 = tf(freq=4.0), with freq of:
            4.0 = termFreq=4.0
          4.414126 = idf(docFreq=1454, maxDocs=44218)
          0.046875 = fieldNorm(doc=4382)
  0.33333334 = coord(1/3)

Abstract

The purpose of this study is to analyze the relationship between citation ranking and peer evaluation in assessing senior faculty research performance. Other studies typically derive their peer evaluation data directly from referees, often in the form of ranking. This study uses two additional sources of peer evaluation data: citation contant analysis and book review content analysis. 2 main questions are investigated: (a) To what degree does citation ranking correlate with data from citation content analysis, book reviews and peer ranking? (b) Is citation ranking a valif evaluative indicator of research performance of senior faculty members? This study shows that citation ranking can provide a valid indicator for comparative evaluation of senior faculty research performance

0.029093731 = product of:
  0.08728119 = sum of:
    0.08728119 = weight(_text_:book in 3765) [ClassicSimilarity], result of:
      0.08728119 = score(doc=3765,freq=2.0), product of:
        0.2237077 = queryWeight, product of:
          4.414126 = idf(docFreq=1454, maxDocs=44218)
          0.050679956 = queryNorm
        0.39015728 = fieldWeight in 3765, product of:
          1.4142135 = tf(freq=2.0), with freq of:
            2.0 = termFreq=2.0
          4.414126 = idf(docFreq=1454, maxDocs=44218)
          0.0625 = fieldNorm(doc=3765)
  0.33333334 = coord(1/3)

Abstract

A new approach for investigating the correlation between research quality and citation counts is presented and applied to a case study of the relationship between peer evaluations reflected in scholarly book reviews and the citation frequencies of reviewed books. Results of the study designate a J-shaped distribution between the considered variables, presumably caused by a skewed allocation of negative citations. The paper concludes with suggestions for further research.

0.0218203 = product of:
  0.0654609 = sum of:
    0.0654609 = weight(_text_:book in 86) [ClassicSimilarity], result of:
      0.0654609 = score(doc=86,freq=2.0), product of:
        0.2237077 = queryWeight, product of:
          4.414126 = idf(docFreq=1454, maxDocs=44218)
          0.050679956 = queryNorm
        0.29261798 = fieldWeight in 86, product of:
          1.4142135 = tf(freq=2.0), with freq of:
            2.0 = termFreq=2.0
          4.414126 = idf(docFreq=1454, maxDocs=44218)
          0.046875 = fieldNorm(doc=86)
  0.33333334 = coord(1/3)

Abstract

The invention of the citation index was credited to Shepard (1873) and Shapiro described a legal citation index published in 1743. A similar index was embedded in the Talmud 2 centuries earlier (1546). The 1st Hebrew citation index to a printed book is dated 1511. The earliest Hebrew manuscript citation index, ascribed to Maimonides, dates from the 12th century. Considerable knowledge was assumed for users of these tools. The substantial knowledge of their compilers contrats with the semi-automatic production of modern citation indexes. The terms citation, quotation, reference, cross-reference, locator, and concordance are employed inconsistently in publications about Hebrew indexes. There is a lack of citation links between the secondary literature on Hebrew indexes and that of citation analysis

0.0218203 = product of:
  0.0654609 = sum of:
    0.0654609 = weight(_text_:book in 5768) [ClassicSimilarity], result of:
      0.0654609 = score(doc=5768,freq=2.0), product of:
        0.2237077 = queryWeight, product of:
          4.414126 = idf(docFreq=1454, maxDocs=44218)
          0.050679956 = queryNorm
        0.29261798 = fieldWeight in 5768, product of:
          1.4142135 = tf(freq=2.0), with freq of:
            2.0 = termFreq=2.0
          4.414126 = idf(docFreq=1454, maxDocs=44218)
          0.046875 = fieldNorm(doc=5768)
  0.33333334 = coord(1/3)

Abstract

A citation analysis of undergraduate term papers in microeconomics revealed a significant decrease in the frequency of scholarly resources cited between 1996 and 1999. Book citations decreased from 30% to 19%, newspaper citations increased from 7% to 19%, and Web citations increased from 9% to 21%. Web citations checked in 2000 revealed that only 18% of URLs cited in 1996 led to the correct Internet document. For 1999 bibliographies, only 55% of URLs led to the correct document. The authors recommend (1) setting stricter guidelines for acceptable citations in course assignments; (2) creating and maintaining scholarly portals for authoritative Web sites with a commitment to long-term access; and (3) continuing to instruct students how to critically evaluate resources

0.0218203 = product of:
  0.0654609 = sum of:
    0.0654609 = weight(_text_:book in 3848) [ClassicSimilarity], result of:
      0.0654609 = score(doc=3848,freq=2.0), product of:
        0.2237077 = queryWeight, product of:
          4.414126 = idf(docFreq=1454, maxDocs=44218)
          0.050679956 = queryNorm
        0.29261798 = fieldWeight in 3848, product of:
          1.4142135 = tf(freq=2.0), with freq of:
            2.0 = termFreq=2.0
          4.414126 = idf(docFreq=1454, maxDocs=44218)
          0.046875 = fieldNorm(doc=3848)
  0.33333334 = coord(1/3)

Footnote

Vgl.: http://www.tandfonline.com/doi/book/10.1081/E-ELIS3.

0.020572376 = product of:
  0.061717123 = sum of:
    0.061717123 = weight(_text_:book in 2095) [ClassicSimilarity], result of:
      0.061717123 = score(doc=2095,freq=4.0), product of:
        0.2237077 = queryWeight, product of:
          4.414126 = idf(docFreq=1454, maxDocs=44218)
          0.050679956 = queryNorm
        0.27588287 = fieldWeight in 2095, product of:
          2.0 = tf(freq=4.0), with freq of:
            4.0 = termFreq=4.0
          4.414126 = idf(docFreq=1454, maxDocs=44218)
          0.03125 = fieldNorm(doc=2095)
  0.33333334 = coord(1/3)

Abstract

Many authors have posited a social component in citation, the consensus being that the citers and citees often have interpersonal as well as intellectual ties. Evidence for this belief has been rather meager, however, in part because social networks researchers have lacked bibliometric data (e.g., pairwise citation counts from online databases), and citation analysts have lacked sociometric data (e.g., pairwise measures of acquaintanceship). In 1997 Nazer extensively measured personal relationships and communication behaviors in what we call "Globenet," an international group of 16 researchers from seven disciplines that was established in 1993 to study human development. Since Globenet's membership is known, it was possible during 2002 to obtain citation records for all members in databases of the Institute for Scientific Information. This permitted examination of how members cited each other (intercited) in journal articles over the past three decades and in a 1999 book to which they all contributed. It was also possible to explore links between the intercitation data and the social and communication data. Using network-analytic techniques, we look at the growth of intercitation over time, the extent to which it follows disciplinary or interdisciplinary lines, whether it covaries with degrees of acquaintanceship, whether it reflects Globenet's organizational structure, whether it is associated with particular in-group communication patterns, and whether it is related to the cocitation of Globenet members. Results show cocitation to be a powerful predictor of intercitation in the journal articles, while being an editor or co-author is an important predictor in the book. Intellectual ties based an shared content did better as predictors than content-neutral social ties like friendship. However, interciters in Globenet communicated more than did noninterciters.

0.018310493 = product of:
  0.054931477 = sum of:
    0.054931477 = product of:
      0.10986295 = sum of:
        0.10986295 = weight(_text_:22 in 6091) [ClassicSimilarity], result of:
          0.10986295 = score(doc=6091,freq=2.0), product of:
            0.17747258 = queryWeight, product of:
              3.5018296 = idf(docFreq=3622, maxDocs=44218)
              0.050679956 = queryNorm
            0.61904186 = fieldWeight in 6091, product of:
              1.4142135 = tf(freq=2.0), with freq of:
                2.0 = termFreq=2.0
              3.5018296 = idf(docFreq=3622, maxDocs=44218)
              0.125 = fieldNorm(doc=6091)
      0.5 = coord(1/2)
  0.33333334 = coord(1/3)

Date

13. 7.2008 19:53:22

0.018310493 = product of:
  0.054931477 = sum of:
    0.054931477 = product of:
      0.10986295 = sum of:
        0.10986295 = weight(_text_:22 in 4604) [ClassicSimilarity], result of:
          0.10986295 = score(doc=4604,freq=2.0), product of:
            0.17747258 = queryWeight, product of:
              3.5018296 = idf(docFreq=3622, maxDocs=44218)
              0.050679956 = queryNorm
            0.61904186 = fieldWeight in 4604, product of:
              1.4142135 = tf(freq=2.0), with freq of:
                2.0 = termFreq=2.0
              3.5018296 = idf(docFreq=3622, maxDocs=44218)
              0.125 = fieldNorm(doc=4604)
      0.5 = coord(1/2)
  0.33333334 = coord(1/3)

Date

7. 2.2005 14:10:22

0.018183582 = product of:
  0.05455074 = sum of:
    0.05455074 = weight(_text_:book in 3763) [ClassicSimilarity], result of:
      0.05455074 = score(doc=3763,freq=2.0), product of:
        0.2237077 = queryWeight, product of:
          4.414126 = idf(docFreq=1454, maxDocs=44218)
          0.050679956 = queryNorm
        0.2438483 = fieldWeight in 3763, product of:
          1.4142135 = tf(freq=2.0), with freq of:
            2.0 = termFreq=2.0
          4.414126 = idf(docFreq=1454, maxDocs=44218)
          0.0390625 = fieldNorm(doc=3763)
  0.33333334 = coord(1/3)

Footnote

Vgl.: http://www.tandfonline.com/doi/book/10.1081/E-ELIS3.

0.01803802 = product of:
  0.054114055 = sum of:
    0.054114055 = product of:
      0.10822811 = sum of:
        0.10822811 = weight(_text_:search in 1474) [ClassicSimilarity], result of:
          0.10822811 = score(doc=1474,freq=2.0), product of:
            0.17614716 = queryWeight, product of:
              3.475677 = idf(docFreq=3718, maxDocs=44218)
              0.050679956 = queryNorm
            0.6144187 = fieldWeight in 1474, product of:
              1.4142135 = tf(freq=2.0), with freq of:
                2.0 = termFreq=2.0
              3.475677 = idf(docFreq=3718, maxDocs=44218)
              0.125 = fieldNorm(doc=1474)
      0.5 = coord(1/2)
  0.33333334 = coord(1/3)

0.016184341 = product of:
  0.048553023 = sum of:
    0.048553023 = product of:
      0.09710605 = sum of:
        0.09710605 = weight(_text_:22 in 3925) [ClassicSimilarity], result of:
          0.09710605 = score(doc=3925,freq=4.0), product of:
            0.17747258 = queryWeight, product of:
              3.5018296 = idf(docFreq=3622, maxDocs=44218)
              0.050679956 = queryNorm
            0.54716086 = fieldWeight in 3925, product of:
              2.0 = tf(freq=4.0), with freq of:
                4.0 = termFreq=4.0
              3.5018296 = idf(docFreq=3622, maxDocs=44218)
              0.078125 = fieldNorm(doc=3925)
      0.5 = coord(1/2)
  0.33333334 = coord(1/3)

Date

22. 7.2006 15:22:28

0.015783267 = product of:
  0.0473498 = sum of:
    0.0473498 = product of:
      0.0946996 = sum of:
        0.0946996 = weight(_text_:search in 445) [ClassicSimilarity], result of:
          0.0946996 = score(doc=445,freq=2.0), product of:
            0.17614716 = queryWeight, product of:
              3.475677 = idf(docFreq=3718, maxDocs=44218)
              0.050679956 = queryNorm
            0.5376164 = fieldWeight in 445, product of:
              1.4142135 = tf(freq=2.0), with freq of:
                2.0 = termFreq=2.0
              3.475677 = idf(docFreq=3718, maxDocs=44218)
              0.109375 = fieldNorm(doc=445)
      0.5 = coord(1/2)
  0.33333334 = coord(1/3)

0.015125338 = product of:
  0.045376014 = sum of:
    0.045376014 = product of:
      0.09075203 = sum of:
        0.09075203 = weight(_text_:search in 4806) [ClassicSimilarity], result of:
          0.09075203 = score(doc=4806,freq=10.0), product of:
            0.17614716 = queryWeight, product of:
              3.475677 = idf(docFreq=3718, maxDocs=44218)
              0.050679956 = queryNorm
            0.51520574 = fieldWeight in 4806, product of:
              3.1622777 = tf(freq=10.0), with freq of:
                10.0 = termFreq=10.0
              3.475677 = idf(docFreq=3718, maxDocs=44218)
              0.046875 = fieldNorm(doc=4806)
      0.5 = coord(1/2)
  0.33333334 = coord(1/3)

Abstract

Many scientific publications are now available on the World Wide Web for researchers to share research findings. However, they tend to be poorly organised, making the search of relevant publications difficult and time-consuming. Most existing search engines are ineffective in searching these publications, as they do not index Web publications that normally appear in PDF (portable document format) or PostScript formats. Proposes a Web citation-based retrieval system, known as PubSearch, for the retrieval of Web publications. PubSearch indexes Web publications based on citation indices and stores them into a Web Citation Database. The Web Citation Database is then mined to support publication retrieval. Apart from supporting the traditional cited reference search, PubSearch also provides document clustering search and author clustering search. Document clustering groups related publications into clusters, while author clustering categorizes authors into different research areas based on author co-citation analysis.

0.014546866 = product of:
  0.043640595 = sum of:
    0.043640595 = weight(_text_:book in 5797) [ClassicSimilarity], result of:
      0.043640595 = score(doc=5797,freq=2.0), product of:
        0.2237077 = queryWeight, product of:
          4.414126 = idf(docFreq=1454, maxDocs=44218)
          0.050679956 = queryNorm
        0.19507864 = fieldWeight in 5797, product of:
          1.4142135 = tf(freq=2.0), with freq of:
            2.0 = termFreq=2.0
          4.414126 = idf(docFreq=1454, maxDocs=44218)
          0.03125 = fieldNorm(doc=5797)
  0.33333334 = coord(1/3)

Abstract

We here perform an analysis of all 1128 publications produced by scientists during their employment at the University of Texas Institute for Geophysics, a geophysical research laboratory founded in 1972 that currently employs 23 Ph.D.-level scientists. We thus assess research performance using as bibliometric indicators such statistics as publications per year, citations per paper, and cited half-lives. To characterize the research style of individual scientists and to obtain insight into the origin of certain publication-counting discrepancies, we classified the 1128 publications into four categories that differed significantly with respect to statistics such as lifetime citation rates, fraction of papers never-cited after 10 years, and cited half-life. The categories were: mainstream (prestige journal) publications -32.6 lifetime cit/pap, 2.4% never cited, and 6.9 year half-life; archival (other refereed)-12.0 lifetime cit/pap. 21.5% never cited, and 9.5 years half-life; articles published as proceedings of conferences-5.4 lifetime cit/pap, 26.6% never cited, and 5.4 years half-life; and "other" publications (news articles, book reviews, etc.)-4.2 lifetime cit/pap, 57.1% never cited, and 1.9 years half-life. Because determining cited half-lives is highly similar to a well-studied phenomenon in earthquake seismology, which was familiar to us, we thoroughly evaluate five different methods for determining the cited half-life and discuss the robustness and limitations of the various methods. Unfortunately, even when data are numerous the various methods often obtain very different values for the half-life. Our preferred method determines halflife from the ratio of citations appearing in back-to-back 5-year periods. We also evaluate the reliability of the citation count data used for these kinds of analysis and conclude that citation count data are often imprecise. All observations suggest that reported differences in cited half-lives must be quite large to be significant

0.013668711 = product of:
  0.041006133 = sum of:
    0.041006133 = product of:
      0.082012266 = sum of:
        0.082012266 = weight(_text_:search in 8219) [ClassicSimilarity], result of:
          0.082012266 = score(doc=8219,freq=6.0), product of:
            0.17614716 = queryWeight, product of:
              3.475677 = idf(docFreq=3718, maxDocs=44218)
              0.050679956 = queryNorm
            0.46558946 = fieldWeight in 8219, product of:
              2.4494898 = tf(freq=6.0), with freq of:
                6.0 = termFreq=6.0
              3.475677 = idf(docFreq=3718, maxDocs=44218)
              0.0546875 = fieldNorm(doc=8219)
      0.5 = coord(1/2)
  0.33333334 = coord(1/3)

Abstract

Explores the relationship between the number of cited references used in a citation search and retrieval effectiveness. Focuses on analysing in terms of information retrieval effectiveness, the overlap among posting sets retrieved by various combinations of cited references. Findings from three case studies show the more cited references used for a citation search, the better the performance, in terms of retrieving more relevant documents, up to a point of diminishing returns. The overall level of overlap among relevant documents sets was found to be low. If only some of the cited references among many candidates are used for a citation search, a significant proportion of relevant documents may be missed. The characteristics of cited references showed that some variables are good indicators to predict relevance to a given question

0.013528514 = product of:
  0.04058554 = sum of:
    0.04058554 = product of:
      0.08117108 = sum of:
        0.08117108 = weight(_text_:search in 2290) [ClassicSimilarity], result of:
          0.08117108 = score(doc=2290,freq=8.0), product of:
            0.17614716 = queryWeight, product of:
              3.475677 = idf(docFreq=3718, maxDocs=44218)
              0.050679956 = queryNorm
            0.460814 = fieldWeight in 2290, product of:
              2.828427 = tf(freq=8.0), with freq of:
                8.0 = termFreq=8.0
              3.475677 = idf(docFreq=3718, maxDocs=44218)
              0.046875 = fieldNorm(doc=2290)
      0.5 = coord(1/2)
  0.33333334 = coord(1/3)

Abstract

Search results for nine topics in the medical behavioral sciences are reanalyzed to compare the overall perfor-mance of descriptor and citation search strategies in identifying relevant and novel documents. Overlap per- centages between an aggregate "descriptor-based" database (MEDLINE, EXERPTA MEDICA, PSYCINFO) and an aggregate "citation-based" database (SCISEARCH, SOCIAL SCISEARCH) ranged from 1% to 26%, with a median overlap of 8% relevant retrievals found using both search strategies. For seven topics in which both descriptor and citation strategies produced reasonably substantial retrievals, two patterns of search performance and novelty distribution were observed: (1) where descriptor and citation retrieval showed little overlap, novelty retrieval percentages differed by 17-23% between the two strategies; (2) topics with a relatively high percentage retrieval overlap shoed little difference (1-4%) in descriptor and citation novelty retrieval percentages. These results reflect the varying partial congruence of two literature networks and represent two different types of subject relevance

0.011716037 = product of:
  0.03514811 = sum of:
    0.03514811 = product of:
      0.07029622 = sum of:
        0.07029622 = weight(_text_:search in 956) [ClassicSimilarity], result of:
          0.07029622 = score(doc=956,freq=6.0), product of:
            0.17614716 = queryWeight, product of:
              3.475677 = idf(docFreq=3718, maxDocs=44218)
              0.050679956 = queryNorm
            0.39907667 = fieldWeight in 956, product of:
              2.4494898 = tf(freq=6.0), with freq of:
                6.0 = termFreq=6.0
              3.475677 = idf(docFreq=3718, maxDocs=44218)
              0.046875 = fieldNorm(doc=956)
      0.5 = coord(1/2)
  0.33333334 = coord(1/3)

Abstract

Current citation-based document retrieval systems generally offer only limited search facilities, such as author search. In order to facilitate more advanced search functions, we have developed a significantly improved system that employs two novel techniques: Context-based Cluster Analysis (CCA) and Context-based Ontology Generation frAmework (COGA). CCA aims to extract relevant information from clusters originally obtained from disparate clustering methods by building relationships between them. The built relationships are then represented as formal context using the Formal Concept Analysis (FCA) technique. COGA aims to generate ontology from clusters relationship built by CCA. By combining these two techniques, we are able to perform ontology learning from a citation database using clustering results. We have implemented the improved system and have demonstrated its use for finding research domain expertise. We have also conducted performance evaluation on the system and the results are encouraging.