Search (37 results, page 2 of 2)

0.0018033426 = product of:
  0.010820055 = sum of:
    0.010820055 = weight(_text_:in in 6032) [ClassicSimilarity], result of:
      0.010820055 = score(doc=6032,freq=6.0), product of:
        0.059380736 = queryWeight, product of:
          1.3602545 = idf(docFreq=30841, maxDocs=44218)
          0.043654136 = queryNorm
        0.1822149 = fieldWeight in 6032, product of:
          2.4494898 = tf(freq=6.0), with freq of:
            6.0 = termFreq=6.0
          1.3602545 = idf(docFreq=30841, maxDocs=44218)
          0.0546875 = fieldNorm(doc=6032)
  0.16666667 = coord(1/6)

Abstract

Theories of aboutness and theories of subject analysis and of related concepts such as topicality are often isolated from each other in the literature of information science (IS) and related disciplines. In IS it is important to consider the nature and meaning of these concepts, which is closely related to theoretical and metatheoretical issues in information retrieval (IR). A theory of IR must specify which concepts should be regarded as synonymous concepts and explain how the meaning of the nonsynonymous concepts should be defined

0.0018033426 = product of:
  0.010820055 = sum of:
    0.010820055 = weight(_text_:in in 5187) [ClassicSimilarity], result of:
      0.010820055 = score(doc=5187,freq=6.0), product of:
        0.059380736 = queryWeight, product of:
          1.3602545 = idf(docFreq=30841, maxDocs=44218)
          0.043654136 = queryNorm
        0.1822149 = fieldWeight in 5187, product of:
          2.4494898 = tf(freq=6.0), with freq of:
            6.0 = termFreq=6.0
          1.3602545 = idf(docFreq=30841, maxDocs=44218)
          0.0546875 = fieldNorm(doc=5187)
  0.16666667 = coord(1/6)

Abstract

Chen arranged with an Art History instructor to require 20 medieval art images in papers received from 29 students. Participants completed a self administered presearch and postsearch questionnaire, and were interviewed after questionnaire analysis, in order to collect both the keywords and phrases they planned to use, and those actually used. Three MLIS student reviewers then mapped the queries to Enser and McGregor's four categories, Jorgensen's 12 classes, and Fidel's 12 feature data and object poles providing a degree of match on a seven point scale (one not at all to 7 exact). The reviewers give highest scores to Enser and McGregor;'s categories. Modifications to both the Enser and McGregor and Jorgensen schemes are suggested

0.0018033426 = product of:
  0.010820055 = sum of:
    0.010820055 = weight(_text_:in in 1024) [ClassicSimilarity], result of:
      0.010820055 = score(doc=1024,freq=6.0), product of:
        0.059380736 = queryWeight, product of:
          1.3602545 = idf(docFreq=30841, maxDocs=44218)
          0.043654136 = queryNorm
        0.1822149 = fieldWeight in 1024, product of:
          2.4494898 = tf(freq=6.0), with freq of:
            6.0 = termFreq=6.0
          1.3602545 = idf(docFreq=30841, maxDocs=44218)
          0.0546875 = fieldNorm(doc=1024)
  0.16666667 = coord(1/6)

Abstract

The paper discusses the notion of steps in indexing and reveals that the document-centered approach to indexing is prevalent and argues that the document-centered approach is problematic because it blocks out context-dependent factors in the indexing process. A domain-centered approach to indexing is presented as an alternative and the paper discusses how this approach includes a broader range of analyses and how it requires a new set of actions from using this approach; analysis of the domain, users and indexers. The paper concludes that the two-step procedure to indexing is insufficient to explain the indexing process and suggests that the domain-centered approach offers a guide for indexers that can help them manage the complexity of indexing.

0.0016629322 = product of:
  0.009977593 = sum of:
    0.009977593 = weight(_text_:in in 837) [ClassicSimilarity], result of:
      0.009977593 = score(doc=837,freq=10.0), product of:
        0.059380736 = queryWeight, product of:
          1.3602545 = idf(docFreq=30841, maxDocs=44218)
          0.043654136 = queryNorm
        0.16802745 = fieldWeight in 837, product of:
          3.1622777 = tf(freq=10.0), with freq of:
            10.0 = termFreq=10.0
          1.3602545 = idf(docFreq=30841, maxDocs=44218)
          0.0390625 = fieldNorm(doc=837)
  0.16666667 = coord(1/6)

Abstract

Purpose - To provide a better-informed view of the extent of the semantic gap in image retrieval, and the limited potential for bridging it offered by current semantic image retrieval techniques. Design/methodology/approach - Within an ongoing project, a broad spectrum of operational image retrieval activity has been surveyed, and, from a number of collaborating institutions, a test collection assembled which comprises user requests, the images selected in response to those requests, and their associated metadata. This has provided the evidence base upon which to make informed observations on the efficacy of cutting-edge automatic annotation techniques which seek to integrate the text-based and content-based image retrieval paradigms. Findings - Evidence from the real-world practice of image retrieval highlights the existence of a generic-specific continuum of object identification, and the incidence of temporal, spatial, significance and abstract concept facets, manifest in textual indexing and real-query scenarios but often having no directly visible presence in an image. These factors combine to limit the functionality of current semantic image retrieval techniques, which interpret only visible features at the generic extremity of the generic-specific continuum. Research limitations/implications - The project is concerned with the traditional image retrieval environment in which retrieval transactions are conducted on still images which form part of managed collections. The possibilities offered by ontological support for adding functionality to automatic annotation techniques are considered. Originality/value - The paper offers fresh insights into the challenge of migrating content-based image retrieval from the laboratory to the operational environment, informed by newly-assembled, comprehensive, live data.

0.0014873719 = product of:
  0.008924231 = sum of:
    0.008924231 = weight(_text_:in in 1590) [ClassicSimilarity], result of:
      0.008924231 = score(doc=1590,freq=8.0), product of:
        0.059380736 = queryWeight, product of:
          1.3602545 = idf(docFreq=30841, maxDocs=44218)
          0.043654136 = queryNorm
        0.15028831 = fieldWeight in 1590, product of:
          2.828427 = tf(freq=8.0), with freq of:
            8.0 = termFreq=8.0
          1.3602545 = idf(docFreq=30841, maxDocs=44218)
          0.0390625 = fieldNorm(doc=1590)
  0.16666667 = coord(1/6)

Abstract

The paper considers indexing an activity that deals with linguistic entities. It rests an the assumption that a theory of indexing should be based an a philosophy of language, because indexing is concerned with the linguistic representation of meaning. The paper consists of four sections: It begins with some basic considerations an the nature of indexing and the requirements for a theory an this; it is followed by a short review of the use of Wittgenstein's philosophy in LIS-literature; next is an analysis of Wittgenstein's work Philosophical Investigations; finally, we deduce a theory of indexing from this philosophy. Considering an indexing theory a theory of meaning entails that, for the purpose of retrieval, indexing is a representation of meaning. Therefore, an indexing theory is concerned with how words are used in the linguistic context. Furthermore, the indexing process is a communicative process containing an interpretative element. Through the philosophy of the later Wittgenstein, it is shown that language and meaning are publicly constituted entities. Since they form the basis of indexing, a theory hereof must take into account that no single actor can define the meaning of documents. Rather this is decided by the social, historical and linguistic context in which the document is produced, distributed and exchanged. Indexing must clarify and reflect these contexts.

Source

Advances in classification research, vol.10: proceedings of the 10th ASIS SIG/CR Classification Research Workshop. Ed.: Albrechtsen, H. u. J.E. Mai

0.0014873719 = product of:
  0.008924231 = sum of:
    0.008924231 = weight(_text_:in in 4702) [ClassicSimilarity], result of:
      0.008924231 = score(doc=4702,freq=8.0), product of:
        0.059380736 = queryWeight, product of:
          1.3602545 = idf(docFreq=30841, maxDocs=44218)
          0.043654136 = queryNorm
        0.15028831 = fieldWeight in 4702, product of:
          2.828427 = tf(freq=8.0), with freq of:
            8.0 = termFreq=8.0
          1.3602545 = idf(docFreq=30841, maxDocs=44218)
          0.0390625 = fieldNorm(doc=4702)
  0.16666667 = coord(1/6)

Abstract

Purpose - An empirical study has shown that the real process of subject cataloging does not correspond entirely to theoretical descriptions in textbooks and international standards. The purpose of this is paper is to address the issue of whether it be possible for catalogers who have not received formal training to perform subject cataloging in a different way to their trained colleagues. Design/methodology/approach - A qualitative study was conducted in 2001 among five Slovenian public library catalogers. The resulting model is compared to previous findings. Findings - First, all catalogers attempted to determine what the book was about. While the American catalogers tried to understand the topic and the author's intent, the Slovenian catalogers appeared to focus on the topic only. Slovenian and American academic library catalogers did not demonstrate any anticipation of possible uses that users might have of the book, while this was important for American public library catalogers. All catalogers used existing records to build new ones and/or to search for subject headings. The verification of subject representation with the indexing language was the last step in the subject cataloging process of American catalogers, often skipped by Slovenian catalogers. Research limitations/implications - The small and convenient sample limits the findings. Practical implications - Comparison of subject cataloging processes of Slovenian and American catalogers, two different groups, is important because they both contribute to OCLC's WorldCat database. If the cataloging community is building a universal catalog and approaches to subject description are different, then the resulting subject representations might also be different. Originality/value - This is one of the very few empirical studies of subject cataloging and indexing.

0.0014873719 = product of:
  0.008924231 = sum of:
    0.008924231 = weight(_text_:in in 1863) [ClassicSimilarity], result of:
      0.008924231 = score(doc=1863,freq=8.0), product of:
        0.059380736 = queryWeight, product of:
          1.3602545 = idf(docFreq=30841, maxDocs=44218)
          0.043654136 = queryNorm
        0.15028831 = fieldWeight in 1863, product of:
          2.828427 = tf(freq=8.0), with freq of:
            8.0 = termFreq=8.0
          1.3602545 = idf(docFreq=30841, maxDocs=44218)
          0.0390625 = fieldNorm(doc=1863)
  0.16666667 = coord(1/6)

Abstract

This research explores the use of genre as a document descriptor in order to improve the effectiveness of Web searching. A major issue to be resolved is the identification of what document categories should be used as genres. As genre is a kind of folk typology, document categories must enjoy widespread recognition by their intended user groups in order to qualify as genres. Three user studies were conducted to develop a genre palette and show that it is recognizable to users. (Palette is a term used to denote a classification, attributable to Karlgren, Bretan, Dewe, Hallberg, and Wolkert, 1998.) To simplify the users' classification task, it was decided to focus on Web pages from the edu domain. The first study was a survey of user terminology for Web pages. Three participants separated 100 Web page printouts into stacks according to genre, assigning names and definitions to each genre. The second study aimed to refine the resulting set of 48 (often conceptually and lexically similar) genre names and definitions into a smaller palette of user-preferred terminology. Ten participants classified the same 100 Web pages. A set of five principles for creating a genre palette from individuals' sortings was developed, and the list of 48 was trimmed to 18 genres. The third study aimed to show that users would agree on the genres of Web pages when choosing from the genre palette. In an online experiment in which 257 participants categorized a new set of 55 pages using the 18 genres, on average, over 70% agreed on the genre of each page. Suggestions for improving the genre palette and future directions for the work are discussed.

0.0013303459 = product of:
  0.007982075 = sum of:
    0.007982075 = weight(_text_:in in 2653) [ClassicSimilarity], result of:
      0.007982075 = score(doc=2653,freq=10.0), product of:
        0.059380736 = queryWeight, product of:
          1.3602545 = idf(docFreq=30841, maxDocs=44218)
          0.043654136 = queryNorm
        0.13442196 = fieldWeight in 2653, product of:
          3.1622777 = tf(freq=10.0), with freq of:
            10.0 = termFreq=10.0
          1.3602545 = idf(docFreq=30841, maxDocs=44218)
          0.03125 = fieldNorm(doc=2653)
  0.16666667 = coord(1/6)

Content

1. Introduction The document at hand is often regarded as the most important entity for analysis in the indexing situation. The indexer's focus is directed to the "entity and its faithful description" (Soergel, 1985, 227) and the indexer is advised to "stick to the text and the author's claims" (Lancaster, 2003, 37). The indexer's aim is to establish the subject matter based an an analysis of the document with the goal of representing the document as truthfully as possible and to ensure the subject representation's validity by remaining neutral and objective. To help indexers with their task they are guided towards particular and important attributes of the document that could help them determine the document's subject matter. The exact attributes the indexer is recommended to examine varies, but typical examples are: the title, the abstract, the table of contents, chapter headings, chapter subheadings, preface, introduction, foreword, the text itself, bibliographical references, index entries, illustrations, diagrams, and tables and their captions. The exact recommendations vary according to the type of document that is being indexed (monographs vs. periodical articles, for instance). It is clear that indexers should provide faithful descriptions, that indexers should represent the author's claims, and that the document's attributes are helpful points of analysis. However, indexers need much more guidance when determining the subject than simply the documents themselves. One approach that could be taken to handle the Situation is a useroriented approach in which it is argued that the indexer should ask, "how should I make this document ... visible to potential users? What terms should I use to convey its knowledge to those interested?" (Albrechtsen, 1993, 222). The basic idea is that indexers need to have the users' information needs and terminology in mind when determining the subject matter of documents as well as when selecting index terms.

Series

Advances in knowledge organization; vol.9

0.0012881019 = product of:
  0.007728611 = sum of:
    0.007728611 = weight(_text_:in in 2122) [ClassicSimilarity], result of:
      0.007728611 = score(doc=2122,freq=6.0), product of:
        0.059380736 = queryWeight, product of:
          1.3602545 = idf(docFreq=30841, maxDocs=44218)
          0.043654136 = queryNorm
        0.1301535 = fieldWeight in 2122, product of:
          2.4494898 = tf(freq=6.0), with freq of:
            6.0 = termFreq=6.0
          1.3602545 = idf(docFreq=30841, maxDocs=44218)
          0.0390625 = fieldNorm(doc=2122)
  0.16666667 = coord(1/6)

Abstract

Although images are visual information sources with little or no text associated with them, users still tend to use text to describe images and formulate queries. This is because digital libraries and search engines provide mostly text query options and rely on text annotations for representation and retrieval of the semantic content of images. While the main focus of image research is on indexing and retrieval of individual images, the general topic of image browsing and indexing, and retrieval of groups of images has not been adequately investigated. Comparisons of descriptions of individual images as well as labels of groups of images supplied by users using cognitive models are scarce. This work fills this gap. Using the basic level theory as a framework, a comparison of the descriptions of individual images and labels assigned to groups of images by 180 participants in three studies found a marked difference in their level of abstraction. Results confirm assertions by previous researchers in LIS and other fields that groups of images are labeled using more superordinate level terms while individual image descriptions are mainly at the basic level. Implications for design of image browsing interfaces, taxonomies, thesauri, and similar tools are discussed.

0.0012881019 = product of:
  0.007728611 = sum of:
    0.007728611 = weight(_text_:in in 3618) [ClassicSimilarity], result of:
      0.007728611 = score(doc=3618,freq=6.0), product of:
        0.059380736 = queryWeight, product of:
          1.3602545 = idf(docFreq=30841, maxDocs=44218)
          0.043654136 = queryNorm
        0.1301535 = fieldWeight in 3618, product of:
          2.4494898 = tf(freq=6.0), with freq of:
            6.0 = termFreq=6.0
          1.3602545 = idf(docFreq=30841, maxDocs=44218)
          0.0390625 = fieldNorm(doc=3618)
  0.16666667 = coord(1/6)

Abstract

Purpose - The purpose of this paper is to examine the art historical antecedents of providing subject access to images. After reviewing the assumptions and limitations inherent in the most prevalent descriptive method, the paper seeks to introduce a new model that allows for more comprehensive representation of visually-based cultural materials. Design/methodology/approach - The paper presents a literature-based conceptual analysis, taking Panofsky's theory of iconography and iconology as the starting-point. Panofsky's conceptual model, while appropriate for art created in the Western academic tradition, ignores or misrepresents work from other eras or cultures. Continued dependence on Panofskian descriptive methods limits the functionality and usefulness of image representation systems. Findings - The paper recommends the development of a more precise and inclusive descriptive model for art objects, which is based on the premise that art is not another sort of text, and should not be interpreted as such. Practical implications - The paper provides suggestions for the development of representation models that will enhance the description of non-textual artifacts. Originality/value - The paper addresses issues in information science, the history of art, and computer science, and suggests that a new descriptive model would be of great value to both humanist and social science scholars.

0.0012620769 = product of:
  0.0075724614 = sum of:
    0.0075724614 = weight(_text_:in in 1958) [ClassicSimilarity], result of:
      0.0075724614 = score(doc=1958,freq=4.0), product of:
        0.059380736 = queryWeight, product of:
          1.3602545 = idf(docFreq=30841, maxDocs=44218)
          0.043654136 = queryNorm
        0.12752387 = fieldWeight in 1958, product of:
          2.0 = tf(freq=4.0), with freq of:
            4.0 = termFreq=4.0
          1.3602545 = idf(docFreq=30841, maxDocs=44218)
          0.046875 = fieldNorm(doc=1958)
  0.16666667 = coord(1/6)

Abstract

Information search and retrieval interactions usually involve information content in the form of document collections, information retrieval systems and interfaces, and the user. To fully understand information search and retrieval interactions between users' cognitive space and the information space, researchers need to turn to cognitive models and theories. In this article, the authors use one of these theories, the basic level theory. Use of the basic level theory to understand human categorization is both appropriate and essential to user-centered design of taxonomies, ontologies, browsing interfaces, and other indexing tools and systems. Analyses of data from two studies involving free sorting by 105 participants of 100 images were conducted. The types of categories formed and category labels were examined. Results of the analyses indicate that image category labels generally belong to superordinate to the basic level, and are generic and interpretive. Implications for research on theories of cognition and categorization, and design of image indexing, retrieval and browsing systems are discussed.

0.0011898974 = product of:
  0.0071393843 = sum of:
    0.0071393843 = weight(_text_:in in 639) [ClassicSimilarity], result of:
      0.0071393843 = score(doc=639,freq=2.0), product of:
        0.059380736 = queryWeight, product of:
          1.3602545 = idf(docFreq=30841, maxDocs=44218)
          0.043654136 = queryNorm
        0.120230645 = fieldWeight in 639, product of:
          1.4142135 = tf(freq=2.0), with freq of:
            2.0 = termFreq=2.0
          1.3602545 = idf(docFreq=30841, maxDocs=44218)
          0.0625 = fieldNorm(doc=639)
  0.16666667 = coord(1/6)

Footnote

Bericht von einer Tagung "Genre 2001. Genres and Discourses in Education, Work and Cultural Life: Encounters of Academic Disciplines on Theories and Practices", May 13th to 16th, 2001, Oslo University College, Olso, Norway

0.0010517307 = product of:
  0.006310384 = sum of:
    0.006310384 = weight(_text_:in in 4480) [ClassicSimilarity], result of:
      0.006310384 = score(doc=4480,freq=4.0), product of:
        0.059380736 = queryWeight, product of:
          1.3602545 = idf(docFreq=30841, maxDocs=44218)
          0.043654136 = queryNorm
        0.10626988 = fieldWeight in 4480, product of:
          2.0 = tf(freq=4.0), with freq of:
            4.0 = termFreq=4.0
          1.3602545 = idf(docFreq=30841, maxDocs=44218)
          0.0390625 = fieldNorm(doc=4480)
  0.16666667 = coord(1/6)

Abstract

This paper explains at least some of the major problems related to the subject indexing process and proposes a new approach to understanding the process, which is ordinarily described as a process that takes a number of steps. The subject is first determined, then it is described in a few sentences and, lastly, the description of the subject is converted into the indexing language. It is argued that this typical approach characteristically lacks an understanding of what the central nature of the process is. Indexing is not a neutral and objective representation of a document's subject matter but the representation of an interpretation of a document for future use. Semiotics is offered here as a framework for understanding the "interpretative" nature of the subject indexing process. By placing this process within Peirce's semiotic framework of ideas and terminology, a more detailed description of the process is offered which shows that the uncertainty generally associated with this process is created by the fact that the indexer goes through a number of steps and creates the subject matter of the document during this process. The creation of the subject matter is based on the indexer's social and cultural context. The paper offers an explanation of what occurs in the indexing process and suggests that there is only little certainty to its result.

0.0010517307 = product of:
  0.006310384 = sum of:
    0.006310384 = weight(_text_:in in 2347) [ClassicSimilarity], result of:
      0.006310384 = score(doc=2347,freq=4.0), product of:
        0.059380736 = queryWeight, product of:
          1.3602545 = idf(docFreq=30841, maxDocs=44218)
          0.043654136 = queryNorm
        0.10626988 = fieldWeight in 2347, product of:
          2.0 = tf(freq=4.0), with freq of:
            4.0 = termFreq=4.0
          1.3602545 = idf(docFreq=30841, maxDocs=44218)
          0.0390625 = fieldNorm(doc=2347)
  0.16666667 = coord(1/6)

Abstract

Purpose - If an information retrieval system is going to be of value to the user then it must give meaning to the information which matches the meaning given to it by the user. The meaning given to music varies according to who is interpreting it - the author/composer, the performer, cataloguer or the listener - and this affects how music is organized and retrieved. This paper aims to examine the meaning of music, how meaning is communicated and suggests this may affect music retrieval. Design/methodology/approach - Musicology is used to define music and examine its functions leading to a discussion of how music has been organised and described. Various ways of establishing the meaning of music are reviewed, focussing on established musical analysis techniques. It is suggested that traditional methods are of limited use with digitised popular music. A discussion of semiotics and a review of semiotic analysis in western art music leads to a discussion of semiotics of popular music and examines ideas of Middleton, Stefani and Tagg. Findings - Agreeing that music exists when communication takes place, a discussion of selected communication models leads to the proposal of a revised version of Tagg's model, adjusting it to include listener feedback. Originality/value - The outcome of the analysis is a revised version of Tagg's communication model, adapted to reflect user feedback. It is suggested that this revised communication model reflects the way in which meaning is given to music.

0.0010411602 = product of:
  0.006246961 = sum of:
    0.006246961 = weight(_text_:in in 5497) [ClassicSimilarity], result of:
      0.006246961 = score(doc=5497,freq=2.0), product of:
        0.059380736 = queryWeight, product of:
          1.3602545 = idf(docFreq=30841, maxDocs=44218)
          0.043654136 = queryNorm
        0.10520181 = fieldWeight in 5497, product of:
          1.4142135 = tf(freq=2.0), with freq of:
            2.0 = termFreq=2.0
          1.3602545 = idf(docFreq=30841, maxDocs=44218)
          0.0546875 = fieldNorm(doc=5497)
  0.16666667 = coord(1/6)

Abstract

The principle of specificity for subject headings provides a clear advantage to many researchers for the precision it brings to subject searching. However, for some researchers very specific subject headings hinder an efficient and comprehensive search. An appropriate broader heading, especially when made narrower in scope by the addition of subheadings, can benefit researchers by providing generic access to their topic. Assigning both specific and generic subject headings to a work would enhance the subject accessibility for the diverse approaches and research needs of different catalog users. However, it can be difficult for catalogers to assign broader terms consistently to different works and without consistency the gathering function of those terms may not be realized.

8.9242304E-4 = product of:
  0.005354538 = sum of:
    0.005354538 = weight(_text_:in in 4471) [ClassicSimilarity], result of:
      0.005354538 = score(doc=4471,freq=2.0), product of:
        0.059380736 = queryWeight, product of:
          1.3602545 = idf(docFreq=30841, maxDocs=44218)
          0.043654136 = queryNorm
        0.09017298 = fieldWeight in 4471, product of:
          1.4142135 = tf(freq=2.0), with freq of:
            2.0 = termFreq=2.0
          1.3602545 = idf(docFreq=30841, maxDocs=44218)
          0.046875 = fieldNorm(doc=4471)
  0.16666667 = coord(1/6)

Abstract

Analysis of user viewing and query-matching behavior furnishes additional evidence that the relevance of retrieved images for system users may arise from descriptions of objects and content-based elements that are not evident or not even present in the image. This investigation looks at how users assign pre-determined query terms to retrieved images, as well as looking at a post-retrieval process of image engagement to user cognitive assessments of meaningful terms. Additionally, affective/emotion-based query terms appear to be an important descriptive category for image retrieval. A system for capturing (eliciting) human interpretations derived from cognitive engagements with viewed images could further enhance the efficiency of image retrieval systems stemming from traditional indexing methods and technology-based content extraction algorithms. An approach to such a system is posited.

8.9242304E-4 = product of:
  0.005354538 = sum of:
    0.005354538 = weight(_text_:in in 4570) [ClassicSimilarity], result of:
      0.005354538 = score(doc=4570,freq=2.0), product of:
        0.059380736 = queryWeight, product of:
          1.3602545 = idf(docFreq=30841, maxDocs=44218)
          0.043654136 = queryNorm
        0.09017298 = fieldWeight in 4570, product of:
          1.4142135 = tf(freq=2.0), with freq of:
            2.0 = termFreq=2.0
          1.3602545 = idf(docFreq=30841, maxDocs=44218)
          0.046875 = fieldNorm(doc=4570)
  0.16666667 = coord(1/6)

Abstract

Some collections cover many topics, while others are narrowly focused an a limited number of topics. We introduce the concept of the "scope" of a collection of documents and we compare two ways of measuring lt. These measures are based an the distances between documents. The first uses the overlap of words between pairs of documents. The second measure uses a novel method that calculates the semantic relatedness to pairs of words from the documents. Those values are combined to obtain an overall distance between the documents. The main validation for the measures compared Web pages categorized by Yahoo. Sets of pages sampied from broad categories were determined to have a higher scope than sets derived from subcategories. The measure was significant and confirmed the expected difference in scope. Finally, we discuss other measures related to scope.