Search (45 results, page 1 of 3)

  • × theme_ss:"Inhaltsanalyse"
  1. Pejtersen, A.M.: Design of a classification scheme for fiction based on an analysis of actual user-librarian communication, and use of the scheme for control of librarians' search strategies (1980) 0.06
    0.05997485 = product of:
      0.1199497 = sum of:
        0.1199497 = sum of:
          0.049157884 = weight(_text_:5 in 5835) [ClassicSimilarity], result of:
            0.049157884 = score(doc=5835,freq=2.0), product of:
              0.15247129 = queryWeight, product of:
                2.9180994 = idf(docFreq=6494, maxDocs=44218)
                0.052250203 = queryNorm
              0.32240748 = fieldWeight in 5835, product of:
                1.4142135 = tf(freq=2.0), with freq of:
                  2.0 = termFreq=2.0
                2.9180994 = idf(docFreq=6494, maxDocs=44218)
                0.078125 = fieldNorm(doc=5835)
          0.07079182 = weight(_text_:22 in 5835) [ClassicSimilarity], result of:
            0.07079182 = score(doc=5835,freq=2.0), product of:
              0.18297131 = queryWeight, product of:
                3.5018296 = idf(docFreq=3622, maxDocs=44218)
                0.052250203 = queryNorm
              0.38690117 = fieldWeight in 5835, product of:
                1.4142135 = tf(freq=2.0), with freq of:
                  2.0 = termFreq=2.0
                3.5018296 = idf(docFreq=3622, maxDocs=44218)
                0.078125 = fieldNorm(doc=5835)
      0.5 = coord(1/2)
    
    Date
    5. 8.2006 13:22:44
  2. Beghtol, C.: Toward a theory of fiction analysis for information storage and retrieval (1992) 0.05
    0.047979876 = product of:
      0.09595975 = sum of:
        0.09595975 = sum of:
          0.039326306 = weight(_text_:5 in 5830) [ClassicSimilarity], result of:
            0.039326306 = score(doc=5830,freq=2.0), product of:
              0.15247129 = queryWeight, product of:
                2.9180994 = idf(docFreq=6494, maxDocs=44218)
                0.052250203 = queryNorm
              0.257926 = fieldWeight in 5830, product of:
                1.4142135 = tf(freq=2.0), with freq of:
                  2.0 = termFreq=2.0
                2.9180994 = idf(docFreq=6494, maxDocs=44218)
                0.0625 = fieldNorm(doc=5830)
          0.05663345 = weight(_text_:22 in 5830) [ClassicSimilarity], result of:
            0.05663345 = score(doc=5830,freq=2.0), product of:
              0.18297131 = queryWeight, product of:
                3.5018296 = idf(docFreq=3622, maxDocs=44218)
                0.052250203 = queryNorm
              0.30952093 = fieldWeight in 5830, 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=5830)
      0.5 = coord(1/2)
    
    Date
    5. 8.2006 13:22:08
  3. Weimer, K.H.: ¬The nexus of subject analysis and bibliographic description : the case of multipart videos (1996) 0.04
    0.035984907 = product of:
      0.071969815 = sum of:
        0.071969815 = sum of:
          0.02949473 = weight(_text_:5 in 6525) [ClassicSimilarity], result of:
            0.02949473 = score(doc=6525,freq=2.0), product of:
              0.15247129 = queryWeight, product of:
                2.9180994 = idf(docFreq=6494, maxDocs=44218)
                0.052250203 = queryNorm
              0.19344449 = fieldWeight in 6525, product of:
                1.4142135 = tf(freq=2.0), with freq of:
                  2.0 = termFreq=2.0
                2.9180994 = idf(docFreq=6494, maxDocs=44218)
                0.046875 = fieldNorm(doc=6525)
          0.042475086 = weight(_text_:22 in 6525) [ClassicSimilarity], result of:
            0.042475086 = score(doc=6525,freq=2.0), product of:
              0.18297131 = queryWeight, product of:
                3.5018296 = idf(docFreq=3622, maxDocs=44218)
                0.052250203 = queryNorm
              0.23214069 = fieldWeight in 6525, product of:
                1.4142135 = tf(freq=2.0), with freq of:
                  2.0 = termFreq=2.0
                3.5018296 = idf(docFreq=3622, maxDocs=44218)
                0.046875 = fieldNorm(doc=6525)
      0.5 = coord(1/2)
    
    Source
    Cataloging and classification quarterly. 22(1996) no.2, S.5-18
  4. Pejtersen, A.M.: Fiction and library classification (1978) 0.03
    0.027807899 = product of:
      0.055615798 = sum of:
        0.055615798 = product of:
          0.111231595 = sum of:
            0.111231595 = weight(_text_:5 in 722) [ClassicSimilarity], result of:
              0.111231595 = score(doc=722,freq=4.0), product of:
                0.15247129 = queryWeight, product of:
                  2.9180994 = idf(docFreq=6494, maxDocs=44218)
                  0.052250203 = queryNorm
                0.72952485 = fieldWeight in 722, product of:
                  2.0 = tf(freq=4.0), with freq of:
                    4.0 = termFreq=4.0
                  2.9180994 = idf(docFreq=6494, maxDocs=44218)
                  0.125 = fieldNorm(doc=722)
          0.5 = coord(1/2)
      0.5 = coord(1/2)
    
    Date
    5. 8.2006 13:27:41
    Source
    Scandinavian public library quarterly. 11(1978), S.5-12
  5. Laffal, J.: ¬A concept analysis of Jonathan Swift's 'Tale of a tub' and 'Gulliver's travels' (1995) 0.02
    0.020855924 = product of:
      0.04171185 = sum of:
        0.04171185 = product of:
          0.0834237 = sum of:
            0.0834237 = weight(_text_:5 in 6362) [ClassicSimilarity], result of:
              0.0834237 = score(doc=6362,freq=4.0), product of:
                0.15247129 = queryWeight, product of:
                  2.9180994 = idf(docFreq=6494, maxDocs=44218)
                  0.052250203 = queryNorm
                0.54714364 = fieldWeight in 6362, product of:
                  2.0 = tf(freq=4.0), with freq of:
                    4.0 = termFreq=4.0
                  2.9180994 = idf(docFreq=6494, maxDocs=44218)
                  0.09375 = fieldNorm(doc=6362)
          0.5 = coord(1/2)
      0.5 = coord(1/2)
    
    Date
    5. 8.2006 10:36:15
    Source
    Computers and the humanities. 29(1995) no.5, S.339-361
  6. Chubin, D.E.; Moitra, S.D.: Content analysis of references : adjunct or alternative to citation counting? (1975) 0.02
    0.019663153 = product of:
      0.039326306 = sum of:
        0.039326306 = product of:
          0.07865261 = sum of:
            0.07865261 = weight(_text_:5 in 5647) [ClassicSimilarity], result of:
              0.07865261 = score(doc=5647,freq=2.0), product of:
                0.15247129 = queryWeight, product of:
                  2.9180994 = idf(docFreq=6494, maxDocs=44218)
                  0.052250203 = queryNorm
                0.515852 = fieldWeight in 5647, product of:
                  1.4142135 = tf(freq=2.0), with freq of:
                    2.0 = termFreq=2.0
                  2.9180994 = idf(docFreq=6494, maxDocs=44218)
                  0.125 = fieldNorm(doc=5647)
          0.5 = coord(1/2)
      0.5 = coord(1/2)
    
    Source
    Social studies of science. 5(1975), S.423-441
  7. Sauperl, A.: Subject determination during the cataloging process : the development of a system based on theoretical principles (2002) 0.02
    0.017992454 = product of:
      0.035984907 = sum of:
        0.035984907 = sum of:
          0.014747365 = weight(_text_:5 in 2293) [ClassicSimilarity], result of:
            0.014747365 = score(doc=2293,freq=2.0), product of:
              0.15247129 = queryWeight, product of:
                2.9180994 = idf(docFreq=6494, maxDocs=44218)
                0.052250203 = queryNorm
              0.096722245 = fieldWeight in 2293, product of:
                1.4142135 = tf(freq=2.0), with freq of:
                  2.0 = termFreq=2.0
                2.9180994 = idf(docFreq=6494, maxDocs=44218)
                0.0234375 = fieldNorm(doc=2293)
          0.021237543 = weight(_text_:22 in 2293) [ClassicSimilarity], result of:
            0.021237543 = score(doc=2293,freq=2.0), product of:
              0.18297131 = queryWeight, product of:
                3.5018296 = idf(docFreq=3622, maxDocs=44218)
                0.052250203 = queryNorm
              0.116070345 = fieldWeight in 2293, product of:
                1.4142135 = tf(freq=2.0), with freq of:
                  2.0 = termFreq=2.0
                3.5018296 = idf(docFreq=3622, maxDocs=44218)
                0.0234375 = fieldNorm(doc=2293)
      0.5 = coord(1/2)
    
    Date
    27. 9.2005 14:22:19
    Footnote
    Rez. in: Knowledge organization 30(2003) no.2, S.114-115 (M. Hudon); "This most interesting contribution to the literature of subject cataloguing originates in the author's doctoral dissertation, prepared under the direction of jerry Saye at the University of North Carolina at Chapel Hill. In seven highly readable chapters, Alenka Sauperl develops possible answers to her principal research question: How do cataloguers determine or identify the topic of a document and choose appropriate subject representations? Specific questions at the source of this research an a process which has not been a frequent object of study include: Where do cataloguers look for an overall sense of what a document is about? How do they get an overall sense of what a document is about, especially when they are not familiar with the discipline? Do they consider only one or several possible interpretations? How do they translate meanings in appropriate and valid class numbers and subject headings? Using a strictly qualitative methodology, Dr. Sauperl's research is a study of twelve cataloguers in reallife situation. The author insists an the holistic rather than purely theoretical understanding of the process she is targeting. Participants in the study were professional cataloguers, with at least one year experience in their current job at one of three large academic libraries in the Southeastern United States. All three libraries have a large central cataloguing department, and use OCLC sources and the same automated system; the context of cataloguing tasks is thus considered to be reasonably comparable. All participants were volunteers in this study which combined two datagathering techniques: the think-aloud method and time-line interviews. A model of the subject cataloguing process was first developed from observations of a group of six cataloguers who were asked to independently perform original cataloguing an three nonfiction, non-serial items selected from materials regularly assigned to them for processing. The model was then used for follow-up interviews. Each participant in the second group of cataloguers was invited to reflect an his/her work process for a recent challenging document they had catalogued. Results are presented in 12 stories describing as many personal approaches to subject cataloguing. From these stories a summarization is offered and a theoretical model of subject cataloguing is developed which, according to the author, represents a realistic approach to subject cataloguing. Stories alternate comments from the researcher and direct quotations from the observed or interviewed cataloguers. Not surprisingly, the participants' stories reveal similarities in the sequence and accomplishment of several tasks in the process of subject cataloguing. Sauperl's proposed model, described in Chapter 5, includes as main stages: 1) Examination of the book and subject identification; 2) Search for subject headings; 3) Classification. Chapter 6 is a hypothetical Gase study, using the proposed model to describe the various stages of cataloguing a hypothetical resource. ...
  8. Beghtol, C.: ¬The classification of fiction : the development of a system based on theoretical principles (1994) 0.01
    0.014900193 = product of:
      0.029800385 = sum of:
        0.029800385 = product of:
          0.05960077 = sum of:
            0.05960077 = weight(_text_:5 in 3413) [ClassicSimilarity], result of:
              0.05960077 = score(doc=3413,freq=6.0), product of:
                0.15247129 = queryWeight, product of:
                  2.9180994 = idf(docFreq=6494, maxDocs=44218)
                  0.052250203 = queryNorm
                0.39089832 = fieldWeight in 3413, product of:
                  2.4494898 = tf(freq=6.0), with freq of:
                    6.0 = termFreq=6.0
                  2.9180994 = idf(docFreq=6494, maxDocs=44218)
                  0.0546875 = fieldNorm(doc=3413)
          0.5 = coord(1/2)
      0.5 = coord(1/2)
    
    Abstract
    The work is an adaptation of the author's dissertation and has the following chapters: (1) background and introduction; (2) a problem in classification theory; (3) previous fiction analysis theories and systems and 'The left hand of darkness'; (4) fiction warrant and critical warrant; (5) experimental fiction analysis system (EFAS); (6) application and evaluation of EFAS. Appendix 1 gives references to fiction analysis systems and appendix 2 lists EFAS coding sheets
    Date
    5. 8.2006 13:11:00
    Footnote
    Rez. in: Knowledge organization 21(1994) no.3, S.165-167 (W. Bies); JASIS 46(1995) no.5, S.389-390 (E.G. Bierbaum); Canadian journal of information and library science 20(1995) nos.3/4, S.52-53 (L. Rees-Potter)
  9. Austin, J.; Pejtersen, A.M.: Fiction retrieval: experimental design and evaluation of a search system based on user's value criteria. Pt.1 (1983) 0.01
    0.014747365 = product of:
      0.02949473 = sum of:
        0.02949473 = product of:
          0.05898946 = sum of:
            0.05898946 = weight(_text_:5 in 142) [ClassicSimilarity], result of:
              0.05898946 = score(doc=142,freq=2.0), product of:
                0.15247129 = queryWeight, product of:
                  2.9180994 = idf(docFreq=6494, maxDocs=44218)
                  0.052250203 = queryNorm
                0.38688898 = fieldWeight in 142, product of:
                  1.4142135 = tf(freq=2.0), with freq of:
                    2.0 = termFreq=2.0
                  2.9180994 = idf(docFreq=6494, maxDocs=44218)
                  0.09375 = fieldNorm(doc=142)
          0.5 = coord(1/2)
      0.5 = coord(1/2)
    
    Date
    5. 8.2006 13:27:26
  10. Pejtersen, A.M.: Design of a computer-aided user-system dialogue based on an analysis of users' search behaviour (1984) 0.01
    0.014747365 = product of:
      0.02949473 = sum of:
        0.02949473 = product of:
          0.05898946 = sum of:
            0.05898946 = weight(_text_:5 in 1044) [ClassicSimilarity], result of:
              0.05898946 = score(doc=1044,freq=2.0), product of:
                0.15247129 = queryWeight, product of:
                  2.9180994 = idf(docFreq=6494, maxDocs=44218)
                  0.052250203 = queryNorm
                0.38688898 = fieldWeight in 1044, product of:
                  1.4142135 = tf(freq=2.0), with freq of:
                    2.0 = termFreq=2.0
                  2.9180994 = idf(docFreq=6494, maxDocs=44218)
                  0.09375 = fieldNorm(doc=1044)
          0.5 = coord(1/2)
      0.5 = coord(1/2)
    
    Date
    5. 8.2006 13:28:00
  11. Pejtersen, A.M.: Implications of users' value perception for the design of knowledge based bibliographic retrieval systems (1985) 0.01
    0.014747365 = product of:
      0.02949473 = sum of:
        0.02949473 = product of:
          0.05898946 = sum of:
            0.05898946 = weight(_text_:5 in 2088) [ClassicSimilarity], result of:
              0.05898946 = score(doc=2088,freq=2.0), product of:
                0.15247129 = queryWeight, product of:
                  2.9180994 = idf(docFreq=6494, maxDocs=44218)
                  0.052250203 = queryNorm
                0.38688898 = fieldWeight in 2088, product of:
                  1.4142135 = tf(freq=2.0), with freq of:
                    2.0 = termFreq=2.0
                  2.9180994 = idf(docFreq=6494, maxDocs=44218)
                  0.09375 = fieldNorm(doc=2088)
          0.5 = coord(1/2)
      0.5 = coord(1/2)
    
    Date
    5. 8.2006 13:28:14
  12. Martindale, C.; McKenzie, D.: On the utility of content analysis in author attribution : 'The federalist' (1995) 0.01
    0.014747365 = product of:
      0.02949473 = sum of:
        0.02949473 = product of:
          0.05898946 = sum of:
            0.05898946 = weight(_text_:5 in 822) [ClassicSimilarity], result of:
              0.05898946 = score(doc=822,freq=2.0), product of:
                0.15247129 = queryWeight, product of:
                  2.9180994 = idf(docFreq=6494, maxDocs=44218)
                  0.052250203 = queryNorm
                0.38688898 = fieldWeight in 822, product of:
                  1.4142135 = tf(freq=2.0), with freq of:
                    2.0 = termFreq=2.0
                  2.9180994 = idf(docFreq=6494, maxDocs=44218)
                  0.09375 = fieldNorm(doc=822)
          0.5 = coord(1/2)
      0.5 = coord(1/2)
    
    Date
    5. 8.2006 10:36:30
  13. Hauff-Hartig, S.: Automatische Transkription von Videos : Fernsehen 3.0: Automatisierte Sentimentanalyse und Zusammenstellung von Kurzvideos mit hohem Aufregungslevel KI-generierte Metadaten: Von der Technologiebeobachtung bis zum produktiven Einsatz (2021) 0.01
    0.0141583625 = product of:
      0.028316725 = sum of:
        0.028316725 = product of:
          0.05663345 = sum of:
            0.05663345 = weight(_text_:22 in 251) [ClassicSimilarity], result of:
              0.05663345 = score(doc=251,freq=2.0), product of:
                0.18297131 = queryWeight, product of:
                  3.5018296 = idf(docFreq=3622, maxDocs=44218)
                  0.052250203 = queryNorm
                0.30952093 = fieldWeight in 251, 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=251)
          0.5 = coord(1/2)
      0.5 = coord(1/2)
    
    Date
    22. 5.2021 12:43:05
  14. Raieli, R.: ¬The semantic hole : enthusiasm and caution around multimedia information retrieval (2012) 0.01
    0.012514343 = product of:
      0.025028685 = sum of:
        0.025028685 = product of:
          0.05005737 = sum of:
            0.05005737 = weight(_text_:22 in 4888) [ClassicSimilarity], result of:
              0.05005737 = score(doc=4888,freq=4.0), product of:
                0.18297131 = queryWeight, product of:
                  3.5018296 = idf(docFreq=3622, maxDocs=44218)
                  0.052250203 = queryNorm
                0.27358043 = fieldWeight in 4888, product of:
                  2.0 = tf(freq=4.0), with freq of:
                    4.0 = termFreq=4.0
                  3.5018296 = idf(docFreq=3622, maxDocs=44218)
                  0.0390625 = fieldNorm(doc=4888)
          0.5 = coord(1/2)
      0.5 = coord(1/2)
    
    Date
    22. 1.2012 13:02:10
    Source
    Knowledge organization. 39(2012) no.1, S.13-22
  15. Pejtersen, A.M.: ¬A new approach to the classification of fiction (1982) 0.01
    0.012289471 = product of:
      0.024578942 = sum of:
        0.024578942 = product of:
          0.049157884 = sum of:
            0.049157884 = weight(_text_:5 in 7240) [ClassicSimilarity], result of:
              0.049157884 = score(doc=7240,freq=2.0), product of:
                0.15247129 = queryWeight, product of:
                  2.9180994 = idf(docFreq=6494, maxDocs=44218)
                  0.052250203 = queryNorm
                0.32240748 = fieldWeight in 7240, product of:
                  1.4142135 = tf(freq=2.0), with freq of:
                    2.0 = termFreq=2.0
                  2.9180994 = idf(docFreq=6494, maxDocs=44218)
                  0.078125 = fieldNorm(doc=7240)
          0.5 = coord(1/2)
      0.5 = coord(1/2)
    
    Date
    5. 8.2006 13:28:50
  16. Vieira, L.: Modèle d'analyse pur une classification du document iconographique (1999) 0.01
    0.012289471 = product of:
      0.024578942 = sum of:
        0.024578942 = product of:
          0.049157884 = sum of:
            0.049157884 = weight(_text_:5 in 6320) [ClassicSimilarity], result of:
              0.049157884 = score(doc=6320,freq=2.0), product of:
                0.15247129 = queryWeight, product of:
                  2.9180994 = idf(docFreq=6494, maxDocs=44218)
                  0.052250203 = queryNorm
                0.32240748 = fieldWeight in 6320, product of:
                  1.4142135 = tf(freq=2.0), with freq of:
                    2.0 = termFreq=2.0
                  2.9180994 = idf(docFreq=6494, maxDocs=44218)
                  0.078125 = fieldNorm(doc=6320)
          0.5 = coord(1/2)
      0.5 = coord(1/2)
    
    Date
    5. 8.2001 14:37:23
  17. Hidderley, R.; Rafferty, P.: Democratic indexing : an approach to the retrieval of fiction (1997) 0.01
    0.012165956 = product of:
      0.024331912 = sum of:
        0.024331912 = product of:
          0.048663825 = sum of:
            0.048663825 = weight(_text_:5 in 1783) [ClassicSimilarity], result of:
              0.048663825 = score(doc=1783,freq=4.0), product of:
                0.15247129 = queryWeight, product of:
                  2.9180994 = idf(docFreq=6494, maxDocs=44218)
                  0.052250203 = queryNorm
                0.31916714 = fieldWeight in 1783, product of:
                  2.0 = tf(freq=4.0), with freq of:
                    4.0 = termFreq=4.0
                  2.9180994 = idf(docFreq=6494, maxDocs=44218)
                  0.0546875 = fieldNorm(doc=1783)
          0.5 = coord(1/2)
      0.5 = coord(1/2)
    
    Date
    5. 9.1996 9:11:11
    5. 8.2006 12:58:57
  18. Solomon, P.: Access to fiction for children : a user-based assessment of options and opportunities (1997) 0.01
    0.012165956 = product of:
      0.024331912 = sum of:
        0.024331912 = product of:
          0.048663825 = sum of:
            0.048663825 = weight(_text_:5 in 5845) [ClassicSimilarity], result of:
              0.048663825 = score(doc=5845,freq=4.0), product of:
                0.15247129 = queryWeight, product of:
                  2.9180994 = idf(docFreq=6494, maxDocs=44218)
                  0.052250203 = queryNorm
                0.31916714 = fieldWeight in 5845, product of:
                  2.0 = tf(freq=4.0), with freq of:
                    4.0 = termFreq=4.0
                  2.9180994 = idf(docFreq=6494, maxDocs=44218)
                  0.0546875 = fieldNorm(doc=5845)
          0.5 = coord(1/2)
      0.5 = coord(1/2)
    
    Date
    5. 9.1996 9:11:11
    5. 8.2006 12:58:08
  19. Naun, C.C.: Objectivity and subject access in the print library (2006) 0.01
    0.012165956 = product of:
      0.024331912 = sum of:
        0.024331912 = product of:
          0.048663825 = sum of:
            0.048663825 = weight(_text_:5 in 236) [ClassicSimilarity], result of:
              0.048663825 = score(doc=236,freq=4.0), product of:
                0.15247129 = queryWeight, product of:
                  2.9180994 = idf(docFreq=6494, maxDocs=44218)
                  0.052250203 = queryNorm
                0.31916714 = fieldWeight in 236, product of:
                  2.0 = tf(freq=4.0), with freq of:
                    4.0 = termFreq=4.0
                  2.9180994 = idf(docFreq=6494, maxDocs=44218)
                  0.0546875 = fieldNorm(doc=236)
          0.5 = coord(1/2)
      0.5 = coord(1/2)
    
    Date
    5. 6.2001 12:25:05
    5. 1.2007 9:38:43
  20. Saif, H.; He, Y.; Fernandez, M.; Alani, H.: Contextual semantics for sentiment analysis of Twitter (2016) 0.01
    0.010642994 = product of:
      0.021285988 = sum of:
        0.021285988 = product of:
          0.042571977 = sum of:
            0.042571977 = weight(_text_:5 in 2667) [ClassicSimilarity], result of:
              0.042571977 = score(doc=2667,freq=6.0), product of:
                0.15247129 = queryWeight, product of:
                  2.9180994 = idf(docFreq=6494, maxDocs=44218)
                  0.052250203 = queryNorm
                0.27921307 = fieldWeight in 2667, product of:
                  2.4494898 = tf(freq=6.0), with freq of:
                    6.0 = termFreq=6.0
                  2.9180994 = idf(docFreq=6494, maxDocs=44218)
                  0.0390625 = fieldNorm(doc=2667)
          0.5 = coord(1/2)
      0.5 = coord(1/2)
    
    Abstract
    Sentiment analysis on Twitter has attracted much attention recently due to its wide applications in both, commercial and public sectors. In this paper we present SentiCircles, a lexicon-based approach for sentiment analysis on Twitter. Different from typical lexicon-based approaches, which offer a fixed and static prior sentiment polarities of words regardless of their context, SentiCircles takes into account the co-occurrence patterns of words in different contexts in tweets to capture their semantics and update their pre-assigned strength and polarity in sentiment lexicons accordingly. Our approach allows for the detection of sentiment at both entity-level and tweet-level. We evaluate our proposed approach on three Twitter datasets using three different sentiment lexicons to derive word prior sentiments. Results show that our approach significantly outperforms the baselines in accuracy and F-measure for entity-level subjectivity (neutral vs. polar) and polarity (positive vs. negative) detections. For tweet-level sentiment detection, our approach performs better than the state-of-the-art SentiStrength by 4-5% in accuracy in two datasets, but falls marginally behind by 1% in F-measure in the third dataset.
    Date
    5. 9.2014 10:18:18
    Source
    Information processing and management. 52(2016) no.1, S.5-19

Languages

  • e 38
  • d 6
  • f 1
  • More… Less…

Types

  • a 38
  • m 5
  • x 2
  • el 1
  • More… Less…