Search (162 results, page 2 of 9)

0.004142815 = product of:
  0.012428444 = sum of:
    0.012428444 = product of:
      0.024856888 = sum of:
        0.024856888 = weight(_text_:of in 7209) [ClassicSimilarity], result of:
          0.024856888 = score(doc=7209,freq=18.0), product of:
            0.06850986 = queryWeight, product of:
              1.5637573 = idf(docFreq=25162, maxDocs=44218)
              0.043811057 = queryNorm
            0.36282203 = fieldWeight in 7209, product of:
              4.2426405 = tf(freq=18.0), with freq of:
                18.0 = termFreq=18.0
              1.5637573 = idf(docFreq=25162, maxDocs=44218)
              0.0546875 = fieldNorm(doc=7209)
      0.5 = coord(1/2)
  0.33333334 = coord(1/3)

Abstract

The Nordic WAIS/WWW project sponsored by NORDINFO is a joint project between Lund University Library and the National Technological Library of Denmark. It aims to improve the existing networked information discovery and retrieval tools Wide Area Information System (WAIS) and World Wide Web (WWW), and to move towards unifying WWW and WAIS. Details current results focusing on the WAIS side of the project. Describes research into automatic indexing and classification of WAIS sources, development of an orientation tool for WAIS, and development of a WAIS index of WWW resources

Source

Internet world and document delivery world international 94: Proceedings of the 2nd Annual Conference, London, May 1994

0.0041003237 = product of:
  0.01230097 = sum of:
    0.01230097 = product of:
      0.02460194 = sum of:
        0.02460194 = weight(_text_:of in 1054) [ClassicSimilarity], result of:
          0.02460194 = score(doc=1054,freq=24.0), product of:
            0.06850986 = queryWeight, product of:
              1.5637573 = idf(docFreq=25162, maxDocs=44218)
              0.043811057 = queryNorm
            0.3591007 = fieldWeight in 1054, product of:
              4.8989797 = tf(freq=24.0), with freq of:
                24.0 = termFreq=24.0
              1.5637573 = idf(docFreq=25162, maxDocs=44218)
              0.046875 = fieldNorm(doc=1054)
      0.5 = coord(1/2)
  0.33333334 = coord(1/3)

Abstract

This article presents the results of research into the automatic selection of Library of Congress Classification numbers based on the titles and subject headings in MARC records. The method used in this study was based on partial match retrieval techniques using various elements of new recors (i.e., those to be classified) as "queries", and a test database of classification clusters generated from previously classified MARC records. Sixty individual methods for automatic classification were tested on a set of 283 new records, using all combinations of four different partial match methods, five query types, and three representations of search terms. The results indicate that if the best method for a particular case can be determined, then up to 86% of the new records may be correctly classified. The single method with the best accuracy was able to select the correct classification for about 46% of the new records.

Source

Journal of the American Society for Information Science. 43(1992), S.130-148

0.0041003237 = product of:
  0.01230097 = sum of:
    0.01230097 = product of:
      0.02460194 = sum of:
        0.02460194 = weight(_text_:of in 2166) [ClassicSimilarity], result of:
          0.02460194 = score(doc=2166,freq=24.0), product of:
            0.06850986 = queryWeight, product of:
              1.5637573 = idf(docFreq=25162, maxDocs=44218)
              0.043811057 = queryNorm
            0.3591007 = fieldWeight in 2166, product of:
              4.8989797 = tf(freq=24.0), with freq of:
                24.0 = termFreq=24.0
              1.5637573 = idf(docFreq=25162, maxDocs=44218)
              0.046875 = fieldNorm(doc=2166)
      0.5 = coord(1/2)
  0.33333334 = coord(1/3)

Abstract

In 2004, the German National Library began to classify title records of the German National Bibliography according to subject groups based on the divisions of the Dewey Decimal Classification (DDC). Since 2006, all titles of the main series of the German National Bibliography are classified in strict compliance with the DDC. On this basis, an enhanced DDC-based search can be realized - e.g., searching the data of the German National Bibliography for title records using number components of synthesized classification numbers or searching for DDC numbers using unclassified title records. This paper gives an account of the current research and development of the DDC-based search. The work is conducted in the VZG project Colibri that focuses on the automatic analysis of DDC-synthesized numbers and the automatic classification of bibliographic title records.

Source

New pespectives on subject indexing and classification: essays in honour of Magda Heiner-Freiling. Red.: K. Knull-Schlomann, u.a

0.0041003237 = product of:
  0.01230097 = sum of:
    0.01230097 = product of:
      0.02460194 = sum of:
        0.02460194 = weight(_text_:of in 4758) [ClassicSimilarity], result of:
          0.02460194 = score(doc=4758,freq=24.0), product of:
            0.06850986 = queryWeight, product of:
              1.5637573 = idf(docFreq=25162, maxDocs=44218)
              0.043811057 = queryNorm
            0.3591007 = fieldWeight in 4758, product of:
              4.8989797 = tf(freq=24.0), with freq of:
                24.0 = termFreq=24.0
              1.5637573 = idf(docFreq=25162, maxDocs=44218)
              0.046875 = fieldNorm(doc=4758)
      0.5 = coord(1/2)
  0.33333334 = coord(1/3)

Abstract

In this article, we present a study about classification methods for large-scale categorization of product offers on e-shopping web sites. We present a study about the performance of previously proposed approaches and deployed a probabilistic approach to model the classification problem. We also studied an alternative way of modeling information about the description of product offers and investigated the usage of price and store of product offers as features adopted in the classification process. Our experiments used two collections of over a million product offers previously categorized by human editors and taxonomies of hundreds of categories from a real e-shopping web site. In these experiments, our method achieved an improvement of up to 9% in the quality of the categorization in comparison with the best baseline we have found.

Source

Journal of the American Society for Information Science and Technology. 62(2011) no.9, S.1839-1848

0.0040669674 = product of:
  0.012200902 = sum of:
    0.012200902 = product of:
      0.024401804 = sum of:
        0.024401804 = weight(_text_:of in 1048) [ClassicSimilarity], result of:
          0.024401804 = score(doc=1048,freq=34.0), product of:
            0.06850986 = queryWeight, product of:
              1.5637573 = idf(docFreq=25162, maxDocs=44218)
              0.043811057 = queryNorm
            0.35617945 = fieldWeight in 1048, product of:
              5.8309517 = tf(freq=34.0), with freq of:
                34.0 = termFreq=34.0
              1.5637573 = idf(docFreq=25162, maxDocs=44218)
              0.0390625 = fieldNorm(doc=1048)
      0.5 = coord(1/2)
  0.33333334 = coord(1/3)

Abstract

With the increase of information on the Web, it is difficult to find desired information quickly out of the documents retrieved by a search engine. One way to solve this problem is to classify web documents according to various criteria. Most document classification has been focused on a subject or a topic of a document. A genre or a style is another view of a document different from a subject or a topic. The genre is also a criterion to classify documents. In this paper, we suggest multiple sets of features to classify genres of web documents. The basic set of features, which have been proposed in the previous studies, is acquired from the textual properties of documents, such as the number of sentences, the number of a certain word, etc. However, web documents are different from textual documents in that they contain URL and HTML tags within the pages. We introduce new sets of features specific to web documents, which are extracted from URL and HTML tags. The present work is an attempt to evaluate the performance of the proposed sets of features, and to discuss their characteristics. Finally, we conclude which is an appropriate set of features in automatic genre classification of web documents.

0.0040669674 = product of:
  0.012200902 = sum of:
    0.012200902 = product of:
      0.024401804 = sum of:
        0.024401804 = weight(_text_:of in 2194) [ClassicSimilarity], result of:
          0.024401804 = score(doc=2194,freq=34.0), product of:
            0.06850986 = queryWeight, product of:
              1.5637573 = idf(docFreq=25162, maxDocs=44218)
              0.043811057 = queryNorm
            0.35617945 = fieldWeight in 2194, product of:
              5.8309517 = tf(freq=34.0), with freq of:
                34.0 = termFreq=34.0
              1.5637573 = idf(docFreq=25162, maxDocs=44218)
              0.0390625 = fieldNorm(doc=2194)
      0.5 = coord(1/2)
  0.33333334 = coord(1/3)

Abstract

In the Thomson Reuters Web of Science database, the subject categories of a journal are applied to all articles in the journal. However, many articles in multidisciplinary Sciences journals may only be represented by a small number of subject categories. To provide more accurate information on the research areas of articles in such journals, we can classify articles in these journals into subject categories as defined by Web of Science based on their references. For an article in a multidisciplinary sciences journal, the method counts the subject categories in all of the article's references indexed by Web of Science, and uses the most numerous subject categories of the references to determine the most appropriate classification of the article. We used articles in an issue of Proceedings of the National Academy of Sciences (PNAS) to validate the correctness of the method by comparing the obtained results with the categories of the articles as defined by PNAS and their content. This study shows that the method provides more precise search results for the subject category of interest in bibliometric investigations through recognition of articles in multidisciplinary sciences journals whose work relates to a particular subject category.

Object

Web of science

0.003945538 = product of:
  0.0118366135 = sum of:
    0.0118366135 = product of:
      0.023673227 = sum of:
        0.023673227 = weight(_text_:of in 1669) [ClassicSimilarity], result of:
          0.023673227 = score(doc=1669,freq=50.0), product of:
            0.06850986 = queryWeight, product of:
              1.5637573 = idf(docFreq=25162, maxDocs=44218)
              0.043811057 = queryNorm
            0.34554482 = fieldWeight in 1669, product of:
              7.071068 = tf(freq=50.0), with freq of:
                50.0 = termFreq=50.0
              1.5637573 = idf(docFreq=25162, maxDocs=44218)
              0.03125 = fieldNorm(doc=1669)
      0.5 = coord(1/2)
  0.33333334 = coord(1/3)

Abstract

After a short outline of problems, possibilities and difficulties of systematic information retrieval on the Internet and a description of efforts for development in this area, a specification of the terminology for this report is required. Although the process of retrieval is generally seen as an iterative process of browsing and information retrieval and several important services on the net have taken this fact into consideration, the emphasis of this report lays on the general retrieval tools for the whole of Internet. In order to be able to evaluate the differences, possibilities and restrictions of the different services it is necessary to begin with organizing the existing varieties in a typological/ taxonomical survey. The possibilities and weaknesses will be briefly compared and described for the most important services in the categories robot-based WWW-catalogues of different types, list- or form-based catalogues and simultaneous or collected search services respectively. It will however for different reasons not be possible to rank them in order of "best" services. Still more important are the weaknesses and problems common for all attempts of indexing the Internet. The problems of the quality of the input, the technical performance and the general problem of indexing virtual hypertext are shown to be at least as difficult as the different aspects of harvesting, indexing and information retrieval. Some of the attempts made in the area of further development of retrieval services will be mentioned in relation to descriptions of the contents of documents and standardization efforts. Internet harvesting and indexing technology and retrieval software is thoroughly reviewed. Details about all services and software are listed in analytical forms in Annex 1-3.

0.003925761 = product of:
  0.011777283 = sum of:
    0.011777283 = product of:
      0.023554565 = sum of:
        0.023554565 = weight(_text_:of in 1668) [ClassicSimilarity], result of:
          0.023554565 = score(doc=1668,freq=22.0), product of:
            0.06850986 = queryWeight, product of:
              1.5637573 = idf(docFreq=25162, maxDocs=44218)
              0.043811057 = queryNorm
            0.34381276 = fieldWeight in 1668, product of:
              4.690416 = tf(freq=22.0), with freq of:
                22.0 = termFreq=22.0
              1.5637573 = idf(docFreq=25162, maxDocs=44218)
              0.046875 = fieldNorm(doc=1668)
      0.5 = coord(1/2)
  0.33333334 = coord(1/3)

Abstract

This working paper describes the creation of a test database to carry out the automatic classification tasks of the DESIRE II work package D3.6a on. It is an improved version of NetLab's existing "All" Engineering database created after a comparative study of the outcome of two different approaches to collecting the documents. These two methods were selected from seven different general methodologies to build robot-generated subject indices, presented in this paper. We found a surprisingly low overlap between the Engineering link collections we used as seed pages for the robot and subsequently an even more surprisingly low overlap between the resources collected by the two different approaches. That inspite of using basically the same services to start the harvesting process from. A intellectual evaluation of the contents of both databases showed almost exactly the same percentage of relevant documents (77%), indicating that the main difference between those aproaches was the coverage of the resulting database.

0.003925761 = product of:
  0.011777283 = sum of:
    0.011777283 = product of:
      0.023554565 = sum of:
        0.023554565 = weight(_text_:of in 2234) [ClassicSimilarity], result of:
          0.023554565 = score(doc=2234,freq=22.0), product of:
            0.06850986 = queryWeight, product of:
              1.5637573 = idf(docFreq=25162, maxDocs=44218)
              0.043811057 = queryNorm
            0.34381276 = fieldWeight in 2234, product of:
              4.690416 = tf(freq=22.0), with freq of:
                22.0 = termFreq=22.0
              1.5637573 = idf(docFreq=25162, maxDocs=44218)
              0.046875 = fieldNorm(doc=2234)
      0.5 = coord(1/2)
  0.33333334 = coord(1/3)

Abstract

Text Categorization is the process of assigning documents to a set of previously fixed categories. A lot of research is going an with the goal of automating this time-consuming task. Several different algorithms have been applied, and Support Vector Machines (SVM) have shown very good results. In this report, we try to prove that a previous filtering of the words used by SVM in the classification can improve the overall performance. This hypothesis is systematically tested with three different measures of word relevance, an two different corpus (one of them considered in three different splits), and with both local and global vocabularies. The results show that filtering significantly improves the recall of the method, and that also has the effect of significantly improving the overall performance.

Source

Journal of the American Society for Information Science and technology. 55(2004) no.7, S.579-592

0.003925761 = product of:
  0.011777283 = sum of:
    0.011777283 = product of:
      0.023554565 = sum of:
        0.023554565 = weight(_text_:of in 2604) [ClassicSimilarity], result of:
          0.023554565 = score(doc=2604,freq=22.0), product of:
            0.06850986 = queryWeight, product of:
              1.5637573 = idf(docFreq=25162, maxDocs=44218)
              0.043811057 = queryNorm
            0.34381276 = fieldWeight in 2604, product of:
              4.690416 = tf(freq=22.0), with freq of:
                22.0 = termFreq=22.0
              1.5637573 = idf(docFreq=25162, maxDocs=44218)
              0.046875 = fieldNorm(doc=2604)
      0.5 = coord(1/2)
  0.33333334 = coord(1/3)

Abstract

Purpose - Identification of topic changes within a user search session is a key issue in content analysis of search engine user queries. Recently, various studies have focused on new topic identification/session identification of search engine transaction logs, and several problems regarding the estimation of topic shifts and continuations were observed in these studies. This study aims to analyze the reasons for the problems that were encountered as a result of applying automatic new topic identification. Design/methodology/approach - Measures, such as cleaning the data of common words and analyzing the errors of automatic new topic identification, are applied to eliminate the problems in estimating topic shifts and continuations. Findings - The findings show that the resulting errors of automatic new topic identification have a pattern, and further research is required to improve the performance of automatic new topic identification. Originality/value - Improving the performance of automatic new topic identification would be valuable to search engine designers, so that they can develop new clustering and query recommendation algorithms, as well as custom-tailored graphical user interfaces for search engine users.

0.0039058835 = product of:
  0.01171765 = sum of:
    0.01171765 = product of:
      0.0234353 = sum of:
        0.0234353 = weight(_text_:of in 4846) [ClassicSimilarity], result of:
          0.0234353 = score(doc=4846,freq=4.0), product of:
            0.06850986 = queryWeight, product of:
              1.5637573 = idf(docFreq=25162, maxDocs=44218)
              0.043811057 = queryNorm
            0.34207192 = fieldWeight in 4846, product of:
              2.0 = tf(freq=4.0), with freq of:
                4.0 = termFreq=4.0
              1.5637573 = idf(docFreq=25162, maxDocs=44218)
              0.109375 = fieldNorm(doc=4846)
      0.5 = coord(1/2)
  0.33333334 = coord(1/3)

0.0039058835 = product of:
  0.01171765 = sum of:
    0.01171765 = product of:
      0.0234353 = sum of:
        0.0234353 = weight(_text_:of in 7696) [ClassicSimilarity], result of:
          0.0234353 = score(doc=7696,freq=16.0), product of:
            0.06850986 = queryWeight, product of:
              1.5637573 = idf(docFreq=25162, maxDocs=44218)
              0.043811057 = queryNorm
            0.34207192 = fieldWeight in 7696, product of:
              4.0 = tf(freq=16.0), with freq of:
                16.0 = termFreq=16.0
              1.5637573 = idf(docFreq=25162, maxDocs=44218)
              0.0546875 = fieldNorm(doc=7696)
      0.5 = coord(1/2)
  0.33333334 = coord(1/3)

Abstract

Describes an automatic classification system for classifying chemical reactions. A detailed study of the classification of chemical reactions, based on topological and physicochemical features, is followed by an analysis of the hierarchical classification produced by the HORACE algorithm (Hierarchical Organization of Reactions through Attribute and Condition Eduction), which combines both approaches in a synergistic manner. The searching and updating of reaction hierarchies is demonstrated with the hierarchies produced for 2 data sets by the HORACE algorithm. Shows that reaction hierarchies provide an efficient access to reaction information and indicate the main reaction types for a given reaction scheme, define the scope of a reaction type, enable searchers to find unusual reactions, and can help in locating the reactions most relevant for a given problem

Source

Journal of chemical information and computer sciences. 34(1994) no.1, S.74-90

0.0039058835 = product of:
  0.01171765 = sum of:
    0.01171765 = product of:
      0.0234353 = sum of:
        0.0234353 = weight(_text_:of in 5003) [ClassicSimilarity], result of:
          0.0234353 = score(doc=5003,freq=16.0), product of:
            0.06850986 = queryWeight, product of:
              1.5637573 = idf(docFreq=25162, maxDocs=44218)
              0.043811057 = queryNorm
            0.34207192 = fieldWeight in 5003, product of:
              4.0 = tf(freq=16.0), with freq of:
                16.0 = termFreq=16.0
              1.5637573 = idf(docFreq=25162, maxDocs=44218)
              0.0546875 = fieldNorm(doc=5003)
      0.5 = coord(1/2)
  0.33333334 = coord(1/3)

Abstract

Automatic text classification (ATC) is a discipline at the crossroads of information retrieval (IR), machine learning (ML), and computational linguistics (CL), and consists in the realization of text classifiers, i.e. software systems capable of assigning texts to one or more categories, or classes, from a predefined set. Applications range from the automated indexing of scientific articles, to e-mail routing, spam filtering, authorship attribution, and automated survey coding. This article will focus on the ML approach to ATC, whereby a software system (called the learner) automatically builds a classifier for the categories of interest by generalizing from a "training" set of pre-classified texts.

Source

Encyclopedia of language and linguistics. 2nd ed. Ed.: K. Brown. Vol. 14

0.0038202507 = product of:
  0.011460752 = sum of:
    0.011460752 = product of:
      0.022921504 = sum of:
        0.022921504 = weight(_text_:of in 5769) [ClassicSimilarity], result of:
          0.022921504 = score(doc=5769,freq=30.0), product of:
            0.06850986 = queryWeight, product of:
              1.5637573 = idf(docFreq=25162, maxDocs=44218)
              0.043811057 = queryNorm
            0.33457235 = fieldWeight in 5769, product of:
              5.477226 = tf(freq=30.0), with freq of:
                30.0 = termFreq=30.0
              1.5637573 = idf(docFreq=25162, maxDocs=44218)
              0.0390625 = fieldNorm(doc=5769)
      0.5 = coord(1/2)
  0.33333334 = coord(1/3)

Abstract

Statistical association measures have been widely applied in information retrieval research, usually employing a clustering of documents or terms on the basis of their relationships. Applications of the association measures for term clustering include automatic thesaurus construction and query expansion. This research evaluates the similarity of six association measures by comparing the relationship and behavior they demonstrate in various analyses of a test corpus. Analysis techniques include comparisons of highly ranked term pairs and term clusters, analyses of the correlation among the association measures using Pearson's correlation coefficient and MDS mapping, and an analysis of the impact of a term frequency on the association values by means of z-score. The major findings of the study are as follows: First, the most similar association measures are mutual information and Yule's coefficient of colligation Y, whereas cosine and Jaccard coefficients, as well as X**2 statistic and likelihood ratio, demonstrate quite similar behavior for terms with high frequency. Second, among all the measures, the X**2 statistic is the least affected by the frequency of terms. Third, although cosine and Jaccard coefficients tend to emphasize high frequency terms, mutual information and Yule's Y seem to overestimate rare terms

Source

Journal of the American Society for Information Science and technology. 52(2001) no.4, S.283-296

0.0038202507 = product of:
  0.011460752 = sum of:
    0.011460752 = product of:
      0.022921504 = sum of:
        0.022921504 = weight(_text_:of in 2624) [ClassicSimilarity], result of:
          0.022921504 = score(doc=2624,freq=30.0), product of:
            0.06850986 = queryWeight, product of:
              1.5637573 = idf(docFreq=25162, maxDocs=44218)
              0.043811057 = queryNorm
            0.33457235 = fieldWeight in 2624, product of:
              5.477226 = tf(freq=30.0), with freq of:
                30.0 = termFreq=30.0
              1.5637573 = idf(docFreq=25162, maxDocs=44218)
              0.0390625 = fieldNorm(doc=2624)
      0.5 = coord(1/2)
  0.33333334 = coord(1/3)

Abstract

This paper reports a study in automatic sentiment classification, i.e., automatically classifying documents as expressing positive or negative Sentiments/opinions. The study investigates the effectiveness of using SVM (Support Vector Machine) an various text features to classify product reviews into recommended (positive Sentiment) and not recommended (negative sentiment). Compared with traditional topical classification, it was hypothesized that syntactic and semantic processing of text would be more important for sentiment classification. In the first part of this study, several different approaches, unigrams (individual words), selected words (such as verb, adjective, and adverb), and words labelled with part-of-speech tags were investigated. A sample of 1,800 various product reviews was retrieved from Review Centre (www.reviewcentre.com) for the study. 1,200 reviews were used for training, and 600 for testing. Using SVM, the baseline unigram approach obtained an accuracy rate of around 76%. The use of selected words obtained a marginally better result of 77.33%. Error analysis suggests various approaches for improving classification accuracy: use of negation phrase, making inference from superficial words, and solving the problem of comments an parts. The second part of the study that is in progress investigates the use of negation phrase through simple linguistic processing to improve classification accuracy. This approach increased the accuracy rate up to 79.33%.

Source

Knowledge organization and the global information society: Proceedings of the 8th International ISKO Conference 13-16 July 2004, London, UK. Ed.: I.C. McIlwaine

0.0038202507 = product of:
  0.011460752 = sum of:
    0.011460752 = product of:
      0.022921504 = sum of:
        0.022921504 = weight(_text_:of in 3121) [ClassicSimilarity], result of:
          0.022921504 = score(doc=3121,freq=30.0), product of:
            0.06850986 = queryWeight, product of:
              1.5637573 = idf(docFreq=25162, maxDocs=44218)
              0.043811057 = queryNorm
            0.33457235 = fieldWeight in 3121, product of:
              5.477226 = tf(freq=30.0), with freq of:
                30.0 = termFreq=30.0
              1.5637573 = idf(docFreq=25162, maxDocs=44218)
              0.0390625 = fieldNorm(doc=3121)
      0.5 = coord(1/2)
  0.33333334 = coord(1/3)

Abstract

The delineation of coordinates is fundamental for the cartography of science, and accurate and credible classification of scientific knowledge presents a persistent challenge in this regard. We present a map of Finnish science based on unsupervised-learning classification, and discuss the advantages and disadvantages of this approach vis-à-vis those generated by human reasoning. We conclude that from theoretical and practical perspectives there exist several challenges for human reasoning-based classification frameworks of scientific knowledge, as they typically try to fit new-to-the-world knowledge into historical models of scientific knowledge, and cannot easily be deployed for new large-scale data sets. Automated classification schemes, in contrast, generate classification models only from the available text corpus, thereby identifying credibly novel bodies of knowledge. They also lend themselves to versatile large-scale data analysis, and enable a range of Big Data possibilities. However, we also argue that it is neither possible nor fruitful to declare one or another method a superior approach in terms of realism to classify scientific knowledge, and we believe that the merits of each approach are dependent on the practical objectives of analysis.

Source

Journal of the Association for Information Science and Technology. 67(2016) no.10, S.2464-2476

0.003743066 = product of:
  0.0112291975 = sum of:
    0.0112291975 = product of:
      0.022458395 = sum of:
        0.022458395 = weight(_text_:of in 316) [ClassicSimilarity], result of:
          0.022458395 = score(doc=316,freq=20.0), product of:
            0.06850986 = queryWeight, product of:
              1.5637573 = idf(docFreq=25162, maxDocs=44218)
              0.043811057 = queryNorm
            0.32781258 = fieldWeight in 316, product of:
              4.472136 = tf(freq=20.0), with freq of:
                20.0 = termFreq=20.0
              1.5637573 = idf(docFreq=25162, maxDocs=44218)
              0.046875 = fieldNorm(doc=316)
      0.5 = coord(1/2)
  0.33333334 = coord(1/3)

Abstract

Information retrieval over the Internet increasingly requires the filtering of thousands of heterogeneous information sources. Important sources of information include not only traditional databases with structured data and queries, but also increasing numbers of non-traditional, semi- or unstructured collections such as Web sites, FTP archives, etc. As the number and variability of sources increases, new ways of automatically summarizing, discovering, and selecting collections relevant to a user's query are needed. One such method involves the use of classification schemes, such as the Library of Congress Classification (LCC) [10], within which a collection may be represented based on its content, irrespective of the structure of the actual data or documents. For such a system to be useful in a large-scale distributed environment, it must be easy to use for both collection managers and users. As a result, it must be possible to classify documents automatically within a classification scheme. Furthermore, there must be a straightforward and intuitive interface with which the user may use the scheme to assist in information retrieval (IR).

0.003743066 = product of:
  0.0112291975 = sum of:
    0.0112291975 = product of:
      0.022458395 = sum of:
        0.022458395 = weight(_text_:of in 2218) [ClassicSimilarity], result of:
          0.022458395 = score(doc=2218,freq=20.0), product of:
            0.06850986 = queryWeight, product of:
              1.5637573 = idf(docFreq=25162, maxDocs=44218)
              0.043811057 = queryNorm
            0.32781258 = fieldWeight in 2218, product of:
              4.472136 = tf(freq=20.0), with freq of:
                20.0 = termFreq=20.0
              1.5637573 = idf(docFreq=25162, maxDocs=44218)
              0.046875 = fieldNorm(doc=2218)
      0.5 = coord(1/2)
  0.33333334 = coord(1/3)

Abstract

This paper addresses the problem of automatically assigning a Library of Congress Classification (LCC) to a work given its set of Library of Congress Subject Headings (LCSH). LCCs are organized in a tree: The root node of this hierarchy comprises all possible topics, and leaf nodes correspond to the most specialized topic areas defined. We describe a procedure that, given a resource identified by its LCSH, automatically places that resource in the LCC hierarchy. The procedure uses machine learning techniques and training data from a large library catalog to learn a model that maps from sets of LCSH to classifications from the LCC tree. We present empirical results for our technique showing its accuracy an an independent collection of 50,000 LCSH/LCC pairs.

Source

Journal of the American Society for Information Science and technology. 55(2004) no.3, S.214-227

0.003743066 = product of:
  0.0112291975 = sum of:
    0.0112291975 = product of:
      0.022458395 = sum of:
        0.022458395 = weight(_text_:of in 2035) [ClassicSimilarity], result of:
          0.022458395 = score(doc=2035,freq=20.0), product of:
            0.06850986 = queryWeight, product of:
              1.5637573 = idf(docFreq=25162, maxDocs=44218)
              0.043811057 = queryNorm
            0.32781258 = fieldWeight in 2035, product of:
              4.472136 = tf(freq=20.0), with freq of:
                20.0 = termFreq=20.0
              1.5637573 = idf(docFreq=25162, maxDocs=44218)
              0.046875 = fieldNorm(doc=2035)
      0.5 = coord(1/2)
  0.33333334 = coord(1/3)

Abstract

We investigate how, and to what extent, morphological complexity of the language influences text classification using support vector machines (SVM). The Croatian-English parallel corpus provides the basis for direct comparison of two languages of radically different morphological complexity. We quantified, compared, and statistically tested the effects of morphological normalisation on SVM classifier performance based on a series of parallel experiments on both languages, carried over a large scale of different feature subset sizes obtained by different feature selection methods, and applying different levels of morphological normalisation. We also quantified the trade-off between feature space size and performance for different levels of morphological normalisation, and compared the results for both languages. Our experiments have shown that the improvements in SVM classifier performance is statistically significant; they are greater for small and medium number of features, especially for Croatian, whereas for large number of features the improvements are rather small and may be negligible in practice for both languages.

0.003743066 = product of:
  0.0112291975 = sum of:
    0.0112291975 = product of:
      0.022458395 = sum of:
        0.022458395 = weight(_text_:of in 2697) [ClassicSimilarity], result of:
          0.022458395 = score(doc=2697,freq=20.0), product of:
            0.06850986 = queryWeight, product of:
              1.5637573 = idf(docFreq=25162, maxDocs=44218)
              0.043811057 = queryNorm
            0.32781258 = fieldWeight in 2697, product of:
              4.472136 = tf(freq=20.0), with freq of:
                20.0 = termFreq=20.0
              1.5637573 = idf(docFreq=25162, maxDocs=44218)
              0.046875 = fieldNorm(doc=2697)
      0.5 = coord(1/2)
  0.33333334 = coord(1/3)

Abstract

Text classifiers automatically classify documents into appropriate concepts for different applications. Most classification approaches use flat classifiers that treat each concept as independent, even when the concept space is hierarchically structured. In contrast, hierarchical text classification exploits the structural relationships between the concepts. In this article, we explore the effectiveness of hierarchical classification for a large concept hierarchy. Since the quality of the classification is dependent on the quality and quantity of the training data, we evaluate the use of documents selected from subconcepts to address the sparseness of training data for the top-level classifiers and the use of document relationships to identify the most representative training documents. By selecting training documents using structural and similarity relationships, we achieve a statistically significant improvement of 39.8% (from 54.5-76.2%) in the accuracy of the hierarchical classifier over that of the flat classifier for a large, three-level concept hierarchy.

Source

Journal of the American Society for Information Science and Technology. 60(2009) no.1, S.47-58