Search (6 results, page 1 of 1)

0.015186245 = product of:
  0.03037249 = sum of:
    0.03037249 = sum of:
      0.0054123 = weight(_text_:a in 2752) [ClassicSimilarity], result of:
        0.0054123 = score(doc=2752,freq=8.0), product of:
          0.053105544 = queryWeight, product of:
            1.153047 = idf(docFreq=37942, maxDocs=44218)
            0.046056706 = queryNorm
          0.10191591 = fieldWeight in 2752, product of:
            2.828427 = tf(freq=8.0), with freq of:
              8.0 = termFreq=8.0
            1.153047 = idf(docFreq=37942, maxDocs=44218)
            0.03125 = fieldNorm(doc=2752)
      0.02496019 = weight(_text_:22 in 2752) [ClassicSimilarity], result of:
        0.02496019 = score(doc=2752,freq=2.0), product of:
          0.16128273 = queryWeight, product of:
            3.5018296 = idf(docFreq=3622, maxDocs=44218)
            0.046056706 = queryNorm
          0.15476047 = fieldWeight in 2752, product of:
            1.4142135 = tf(freq=2.0), with freq of:
              2.0 = termFreq=2.0
            3.5018296 = idf(docFreq=3622, maxDocs=44218)
            0.03125 = fieldNorm(doc=2752)
  0.5 = coord(1/2)

Abstract

We report data fusion experiments carried out on the four best-performing retrieval models from TREC 5. Three were conceptually/algorithmically very different from one another; one was algorithmically similar to one of the former. The objective of the test was to observe the performance of the 11 logical data fusion combinations compared to the performance of the four individual models and their intermediate fusions when following the principle of polyrepresentation. This principle is based on cognitive IR perspective (Ingwersen & Järvelin, 2005) and implies that each retrieval model is regarded as a representation of a unique interpretation of information retrieval (IR). It predicts that only fusions of very different, but equally good, IR models may outperform each constituent as well as their intermediate fusions. Two kinds of experiments were carried out. One tested restricted fusions, which entails that only the inner disjoint overlap documents between fused models are ranked. The second set of experiments was based on traditional data fusion methods. The experiments involved the 30 TREC 5 topics that contain more than 44 relevant documents. In all tests, the Borda and CombSUM scoring methods were used. Performance was measured by precision and recall, with document cutoff values (DCVs) at 100 and 15 documents, respectively. Results show that restricted fusions made of two, three, or four cognitively/algorithmically very different retrieval models perform significantly better than do the individual models at DCV100. At DCV15, however, the results of polyrepresentative fusion were less predictable. The traditional fusion method based on polyrepresentation principles demonstrates a clear picture of performance at both DCV levels and verifies the polyrepresentation predictions for data fusion in IR. Data fusion improves retrieval performance over their constituent IR models only if the models all are quite conceptually/algorithmically dissimilar and equally and well performing, in that order of importance.

Date

22. 3.2009 18:48:28

Type

a

0.0029000505 = product of:
  0.005800101 = sum of:
    0.005800101 = product of:
      0.011600202 = sum of:
        0.011600202 = weight(_text_:a in 3088) [ClassicSimilarity], result of:
          0.011600202 = score(doc=3088,freq=12.0), product of:
            0.053105544 = queryWeight, product of:
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.046056706 = queryNorm
            0.21843673 = fieldWeight in 3088, product of:
              3.4641016 = tf(freq=12.0), with freq of:
                12.0 = termFreq=12.0
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.0546875 = fieldNorm(doc=3088)
      0.5 = coord(1/2)
  0.5 = coord(1/2)

Abstract

In this article, we define webometrics within the framework of informetric studies and bibliometrics, as belonging to library and information science, and as associated with cybermetrics as a generic subfield. We develop a consistent and detailed link typology and terminology and make explicit the distinction among different Web node levels when using the proposed conceptual framework. As a consequence, we propose a novel diagram notation to fully appreciate and investigate link structures between Web nodes in webometric analyses. We warn against taking the analogy between citation analyses and link analyses too far.

Type

a

0.0018909799 = product of:
  0.0037819599 = sum of:
    0.0037819599 = product of:
      0.0075639198 = sum of:
        0.0075639198 = weight(_text_:a in 2117) [ClassicSimilarity], result of:
          0.0075639198 = score(doc=2117,freq=10.0), product of:
            0.053105544 = queryWeight, product of:
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.046056706 = queryNorm
            0.14243183 = fieldWeight in 2117, product of:
              3.1622777 = tf(freq=10.0), with freq of:
                10.0 = termFreq=10.0
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.0390625 = fieldNorm(doc=2117)
      0.5 = coord(1/2)
  0.5 = coord(1/2)

Abstract

The principle of polyrepresentation offers a theoretical framework for handling multiple contexts in information retrieval (IR). This paper presents an empirical laboratory study of polyrepresentation in restricted mode of the information space with focus on inter and intra-document features. The Cystic Fibrosis test collection indexed in the best match system InQuery constitutes the experimental setting. Overlaps between five functionally and/or cognitively different document representations are identified. Supporting the principle of polyrepresentation, results show that in general overlaps generated by three or four representations of different nature have higher precision than those generated from two representations or the single fields. This result pertains to both structured and unstructured query mode in best match retrieval, however, with the latter query mode demonstrating higher performance. The retrieval overlaps containing search keys from the bibliographic references provide the best retrieval performance and minor MeSH terms the worst. It is concluded that a highly structured query language is necessary when implementing the principle of polyrepresentation in a best match IR system because the principle is inherently Boolean. Finally a re-ranking test shows promising results when search results are re-ranked according to precision obtained in the overlaps whilst re-ranking by citations seems less useful when integrated into polyrepresentative applications.

Type

a

0.0016913437 = product of:
  0.0033826875 = sum of:
    0.0033826875 = product of:
      0.006765375 = sum of:
        0.006765375 = weight(_text_:a in 3091) [ClassicSimilarity], result of:
          0.006765375 = score(doc=3091,freq=8.0), product of:
            0.053105544 = queryWeight, product of:
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.046056706 = queryNorm
            0.12739488 = fieldWeight in 3091, product of:
              2.828427 = tf(freq=8.0), with freq of:
                8.0 = termFreq=8.0
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.0390625 = fieldNorm(doc=3091)
      0.5 = coord(1/2)
  0.5 = coord(1/2)

Abstract

Because of the increasing presence of scientific publications an the Web, combined with the existing difficulties in easily verifying and retrieving these publications, research an techniques and methods for retrieval of scientific Web publications is called for. In this article, we report an the initial steps taken toward the construction of a test collection of scientific Web publications within the subject domain of plant biology. The steps reported are those of data gathering and data analysis aiming at identifying characteristics of scientific Web publications. The data used in this article were generated based an specifically selected domain topics that are searched for in three publicly accessible search engines (Google, AlITheWeb, and AItaVista). A sample of the retrieved hits was analyzed with regard to how various publication attributes correlated with the scientific quality of the content and whether this information could be employed to harvest, filter, and rank Web publications. The attributes analyzed were inlinks, outlinks, bibliographic references, file format, language, search engine overlap, structural position (according to site structure), and the occurrence of various types of metadata. As could be expected, the ranked output differs between the three search engines. Apparently, this is caused by differences in ranking algorithms rather than the databases themselves. In fact, because scientific Web content in this subject domain receives few inlinks, both AItaVista and AlITheWeb retrieved a higher degree of accessible scientific content than Google. Because of the search engine cutoffs of accessible URLs, the feasibility of using search engine output for Web content analysis is also discussed.

Type

a

0.0016913437 = product of:
  0.0033826875 = sum of:
    0.0033826875 = product of:
      0.006765375 = sum of:
        0.006765375 = weight(_text_:a in 4545) [ClassicSimilarity], result of:
          0.006765375 = score(doc=4545,freq=8.0), product of:
            0.053105544 = queryWeight, product of:
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.046056706 = queryNorm
            0.12739488 = fieldWeight in 4545, product of:
              2.828427 = tf(freq=8.0), with freq of:
                8.0 = termFreq=8.0
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.0390625 = fieldNorm(doc=4545)
      0.5 = coord(1/2)
  0.5 = coord(1/2)

Abstract

This article presents a novel user-oriented interface for generalised informetric analysis and demonstrates how informetric calculations can easily and declaratively be specified through advanced data modelling techniques. The interface is declarative and at a high level. Therefore it is easy to use, flexible and extensible. It enables end users to perform basic informetric ad hoc calculations easily and often with much less effort than in contemporary online retrieval systems. It also provides several fruitful generalisations of typical informetric measurements like impact factors. These are based on substituting traditional foci of analysis, for instance journals, by other object types, such as authors, organisations or countries. In the interface, bibliographic data are modelled as complex objects (non-first normal form relations) and terminological and citation networks involving transitive relationships are modelled as binary relations for deductive processing. The interface is flexible, because it makes it easy to switch focus between various object types for informetric calculations, e.g. from authors to institutions. Moreover, it is demonstrated that all informetric data can easily be broken down by criteria that foster advanced analysis, e.g. by years or content-bearing attributes. Such modelling allows flexible data aggregation along many dimensions. These salient features emerge from the query interface's general data restructuring and aggregation capabilities combined with transitive processing capabilities. The features are illustrated by means of sample queries and results in the article.

Type

a

0.001674345 = product of:
  0.00334869 = sum of:
    0.00334869 = product of:
      0.00669738 = sum of:
        0.00669738 = weight(_text_:a in 3901) [ClassicSimilarity], result of:
          0.00669738 = score(doc=3901,freq=4.0), product of:
            0.053105544 = queryWeight, product of:
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.046056706 = queryNorm
            0.12611452 = fieldWeight in 3901, product of:
              2.0 = tf(freq=4.0), with freq of:
                4.0 = termFreq=4.0
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.0546875 = fieldNorm(doc=3901)
      0.5 = coord(1/2)
  0.5 = coord(1/2)

Abstract

The domain of user-oriented and cognitive information retrieval (IR) is first discussed, followed by a discussion on the dimensions and types of models one may build for the domain. The focus of the present entry is on the models of user-oriented and cognitive IR, not on their empirical applications. Several models with different emphases on user-oriented and cognitive IR are presented-ranging from overall approaches and relevance models to procedural models, cognitive models, and task-based models. The present entry does not discuss empirical findings based on the models.

Type

a