Document (#39469)

Author

Kasprzik, A.

Title

Automatisierte und semiautomatisierte Klassifizierung : eine Analyse aktueller Projekte

Source

Perspektive Bibliothek. 3(2014) H.1, S.85-110

Year

2014

Abstract

Das sprunghafte Anwachsen der Menge digital verfügbarer Dokumente gepaart mit dem Zeit- und Personalmangel an wissenschaftlichen Bibliotheken legt den Einsatz von halb- oder vollautomatischen Verfahren für die verbale und klassifikatorische Inhaltserschließung nahe. Nach einer kurzen allgemeinen Einführung in die gängige Methodik beleuchtet dieser Artikel eine Reihe von Projekten zur automatisierten Klassifizierung aus dem Zeitraum 2007-2012 und aus dem deutschsprachigen Raum. Ein Großteil der vorgestellten Projekte verwendet Methoden des Maschinellen Lernens aus der Künstlichen Intelligenz, arbeitet meist mit angepassten Versionen einer kommerziellen Software und bezieht sich in der Regel auf die Dewey Decimal Classification (DDC). Als Datengrundlage dienen Metadatensätze, Abstracs, Inhaltsverzeichnisse und Volltexte in diversen Datenformaten. Die abschließende Analyse enthält eine Anordnung der Projekte nach einer Reihe von verschiedenen Kriterien und eine Zusammenfassung der aktuellen Lage und der größten Herausfordungen für automatisierte Klassifizierungsverfahren.

Content

Vgl.: https://journals.ub.uni-heidelberg.de/index.php/bibliothek/article/view/14022.

Theme

Automatisches Indexieren
Automatisches Klassifizieren

Similar documents (author)

1. Kasprzik, A.: Implementierung eines Hierarchisierungsalgorithmus' für die Konstanzer Systematik : Projektbericht (2013) 5.93

   5.927861 = sum of:
     5.927861 = weight(author_txt:kasprzik in 3275) [ClassicSimilarity], result of:
       5.927861 = fieldWeight in 3275, product of:
         1.0 = tf(freq=1.0), with freq of:
           1.0 = termFreq=1.0
         9.484578 = idf(docFreq=8, maxDocs=43556)
         0.625 = fieldNorm(doc=3275)
   

2. Kasprzik, A.: Vorläufer der Internationalen Katalogisierungsprinzipien (2014) 5.93

   5.927861 = sum of:
     5.927861 = weight(author_txt:kasprzik in 3617) [ClassicSimilarity], result of:
       5.927861 = fieldWeight in 3617, product of:
         1.0 = tf(freq=1.0), with freq of:
           1.0 = termFreq=1.0
         9.484578 = idf(docFreq=8, maxDocs=43556)
         0.625 = fieldNorm(doc=3617)
   

3. Kasprzik, A.: Voraussetzungen und Anwendungspotentiale einer präzisen Sacherschließung aus Sicht der Wissenschaft (2018) 5.93

   5.927861 = sum of:
     5.927861 = weight(author_txt:kasprzik in 1481) [ClassicSimilarity], result of:
       5.927861 = fieldWeight in 1481, product of:
         1.0 = tf(freq=1.0), with freq of:
           1.0 = termFreq=1.0
         9.484578 = idf(docFreq=8, maxDocs=43556)
         0.625 = fieldNorm(doc=1481)
   

4. Kasprzik, A.; Kett, J.: Vorschläge für eine Weiterentwicklung der Sacherschließung und Schritte zur fortgesetzten strukturellen Aufwertung der GND (2018) 4.74

   4.742289 = sum of:
     4.742289 = weight(author_txt:kasprzik in 885) [ClassicSimilarity], result of:
       4.742289 = fieldWeight in 885, product of:
         1.0 = tf(freq=1.0), with freq of:
           1.0 = termFreq=1.0
         9.484578 = idf(docFreq=8, maxDocs=43556)
         0.5 = fieldNorm(doc=885)
   

5. Auer, S.; Kasprzik, A.; Sens, I.: Von dokumentenbasierten zu wissensbasierten Informationsflüssen : Die Rolle wissenschaftlicher Bibliotheken im Transformationsprozess. Teil 1: Vor einer Revolution der wissenschaftlichen Kommunikation (2019) 3.56

   3.556717 = sum of:
     3.556717 = weight(author_txt:kasprzik in 1527) [ClassicSimilarity], result of:
       3.556717 = fieldWeight in 1527, product of:
         1.0 = tf(freq=1.0), with freq of:
           1.0 = termFreq=1.0
         9.484578 = idf(docFreq=8, maxDocs=43556)
         0.375 = fieldNorm(doc=1527)
   

Similar documents (content)

1. Oberhauser, O.: Automatisches Klassifizieren : Verfahren zur Erschließung elektronischer Dokumente (2004) 0.16

   0.16159876 = sum of:
     0.16159876 = product of:
       0.67332816 = sum of:
         0.08520934 = weight(abstract_txt:klassifikatorische in 3485) [ClassicSimilarity], result of:
           0.08520934 = score(doc=3485,freq=1.0), product of:
             0.17938073 = queryWeight, product of:
               1.0797908 = boost
               8.68607 = idf(docFreq=19, maxDocs=43556)
               0.0191255 = queryNorm
             0.47501948 = fieldWeight in 3485, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               8.68607 = idf(docFreq=19, maxDocs=43556)
               0.0546875 = fieldNorm(doc=3485)
         0.05069787 = weight(abstract_txt:analyse in 3485) [ClassicSimilarity], result of:
           0.05069787 = score(doc=3485,freq=1.0), product of:
             0.15987754 = queryWeight, product of:
               1.441652 = boost
               5.7984805 = idf(docFreq=358, maxDocs=43556)
               0.0191255 = queryNorm
             0.3171044 = fieldWeight in 3485, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               5.7984805 = idf(docFreq=358, maxDocs=43556)
               0.0546875 = fieldNorm(doc=3485)
         0.04577109 = weight(abstract_txt:einer in 3485) [ClassicSimilarity], result of:
           0.04577109 = score(doc=3485,freq=4.0), product of:
             0.10769583 = queryWeight, product of:
               1.4491448 = boost
               3.8857448 = idf(docFreq=2430, maxDocs=43556)
               0.0191255 = queryNorm
             0.42500335 = fieldWeight in 3485, product of:
               2.0 = tf(freq=4.0), with freq of:
                 4.0 = termFreq=4.0
               3.8857448 = idf(docFreq=2430, maxDocs=43556)
               0.0546875 = fieldNorm(doc=3485)
         0.022386208 = weight(abstract_txt:eine in 3485) [ClassicSimilarity], result of:
           0.022386208 = score(doc=3485,freq=1.0), product of:
             0.11680408 = queryWeight, product of:
               1.7426523 = boost
               3.5045679 = idf(docFreq=3558, maxDocs=43556)
               0.0191255 = queryNorm
             0.19165605 = fieldWeight in 3485, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               3.5045679 = idf(docFreq=3558, maxDocs=43556)
               0.0546875 = fieldNorm(doc=3485)
         0.20633787 = weight(abstract_txt:klassifizierung in 3485) [ClassicSimilarity], result of:
           0.20633787 = score(doc=3485,freq=2.0), product of:
             0.32347217 = queryWeight, product of:
               2.05062 = boost
               8.247815 = idf(docFreq=30, maxDocs=43556)
               0.0191255 = queryNorm
             0.63788444 = fieldWeight in 3485, product of:
               1.4142135 = tf(freq=2.0), with freq of:
                 2.0 = termFreq=2.0
               8.247815 = idf(docFreq=30, maxDocs=43556)
               0.0546875 = fieldNorm(doc=3485)
         0.2629258 = weight(abstract_txt:projekte in 3485) [ClassicSimilarity], result of:
           0.2629258 = score(doc=3485,freq=5.0), product of:
             0.3206689 = queryWeight, product of:
               2.5005803 = boost
               6.705069 = idf(docFreq=144, maxDocs=43556)
               0.0191255 = queryNorm
             0.8199292 = fieldWeight in 3485, product of:
               2.236068 = tf(freq=5.0), with freq of:
                 5.0 = termFreq=5.0
               6.705069 = idf(docFreq=144, maxDocs=43556)
               0.0546875 = fieldNorm(doc=3485)
       0.24 = coord(6/25)
   

2. Oberhauser, O.: Automatisches Klassifizieren : Entwicklungsstand - Methodik - Anwendungsbereiche (2005) 0.16

   0.16159876 = sum of:
     0.16159876 = product of:
       0.67332816 = sum of:
         0.08520934 = weight(abstract_txt:klassifikatorische in 1161) [ClassicSimilarity], result of:
           0.08520934 = score(doc=1161,freq=1.0), product of:
             0.17938073 = queryWeight, product of:
               1.0797908 = boost
               8.68607 = idf(docFreq=19, maxDocs=43556)
               0.0191255 = queryNorm
             0.47501948 = fieldWeight in 1161, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               8.68607 = idf(docFreq=19, maxDocs=43556)
               0.0546875 = fieldNorm(doc=1161)
         0.05069787 = weight(abstract_txt:analyse in 1161) [ClassicSimilarity], result of:
           0.05069787 = score(doc=1161,freq=1.0), product of:
             0.15987754 = queryWeight, product of:
               1.441652 = boost
               5.7984805 = idf(docFreq=358, maxDocs=43556)
               0.0191255 = queryNorm
             0.3171044 = fieldWeight in 1161, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               5.7984805 = idf(docFreq=358, maxDocs=43556)
               0.0546875 = fieldNorm(doc=1161)
         0.04577109 = weight(abstract_txt:einer in 1161) [ClassicSimilarity], result of:
           0.04577109 = score(doc=1161,freq=4.0), product of:
             0.10769583 = queryWeight, product of:
               1.4491448 = boost
               3.8857448 = idf(docFreq=2430, maxDocs=43556)
               0.0191255 = queryNorm
             0.42500335 = fieldWeight in 1161, product of:
               2.0 = tf(freq=4.0), with freq of:
                 4.0 = termFreq=4.0
               3.8857448 = idf(docFreq=2430, maxDocs=43556)
               0.0546875 = fieldNorm(doc=1161)
         0.022386208 = weight(abstract_txt:eine in 1161) [ClassicSimilarity], result of:
           0.022386208 = score(doc=1161,freq=1.0), product of:
             0.11680408 = queryWeight, product of:
               1.7426523 = boost
               3.5045679 = idf(docFreq=3558, maxDocs=43556)
               0.0191255 = queryNorm
             0.19165605 = fieldWeight in 1161, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               3.5045679 = idf(docFreq=3558, maxDocs=43556)
               0.0546875 = fieldNorm(doc=1161)
         0.20633787 = weight(abstract_txt:klassifizierung in 1161) [ClassicSimilarity], result of:
           0.20633787 = score(doc=1161,freq=2.0), product of:
             0.32347217 = queryWeight, product of:
               2.05062 = boost
               8.247815 = idf(docFreq=30, maxDocs=43556)
               0.0191255 = queryNorm
             0.63788444 = fieldWeight in 1161, product of:
               1.4142135 = tf(freq=2.0), with freq of:
                 2.0 = termFreq=2.0
               8.247815 = idf(docFreq=30, maxDocs=43556)
               0.0546875 = fieldNorm(doc=1161)
         0.2629258 = weight(abstract_txt:projekte in 1161) [ClassicSimilarity], result of:
           0.2629258 = score(doc=1161,freq=5.0), product of:
             0.3206689 = queryWeight, product of:
               2.5005803 = boost
               6.705069 = idf(docFreq=144, maxDocs=43556)
               0.0191255 = queryNorm
             0.8199292 = fieldWeight in 1161, product of:
               2.236068 = tf(freq=5.0), with freq of:
                 5.0 = termFreq=5.0
               6.705069 = idf(docFreq=144, maxDocs=43556)
               0.0546875 = fieldNorm(doc=1161)
       0.24 = coord(6/25)
   

3. Panzer, M.: Semantische Integration heterogener und unterschiedlichsprachiger Wissensorganisationssysteme : CrissCross und jenseits (2008) 0.09

   0.094555065 = sum of:
     0.094555065 = product of:
       0.39397946 = sum of:
         0.098650225 = weight(abstract_txt:verbale in 1333) [ClassicSimilarity], result of:
           0.098650225 = score(doc=1333,freq=1.0), product of:
             0.15592475 = queryWeight, product of:
               1.0067213 = boost
               8.098284 = idf(docFreq=35, maxDocs=43556)
               0.0191255 = queryNorm
             0.6326784 = fieldWeight in 1333, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               8.098284 = idf(docFreq=35, maxDocs=43556)
               0.078125 = fieldNorm(doc=1333)
         0.11422217 = weight(abstract_txt:automatisierten in 1333) [ClassicSimilarity], result of:
           0.11422217 = score(doc=1333,freq=1.0), product of:
             0.17192931 = queryWeight, product of:
               1.0571258 = boost
               8.503749 = idf(docFreq=23, maxDocs=43556)
               0.0191255 = queryNorm
             0.6643554 = fieldWeight in 1333, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               8.503749 = idf(docFreq=23, maxDocs=43556)
               0.078125 = fieldNorm(doc=1333)
         0.030760951 = weight(abstract_txt:nach in 1333) [ClassicSimilarity], result of:
           0.030760951 = score(doc=1333,freq=1.0), product of:
             0.09033573 = queryWeight, product of:
               1.0836686 = boost
               4.358632 = idf(docFreq=1514, maxDocs=43556)
               0.0191255 = queryNorm
             0.34051812 = fieldWeight in 1333, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               4.358632 = idf(docFreq=1514, maxDocs=43556)
               0.078125 = fieldNorm(doc=1333)
         0.07242553 = weight(abstract_txt:analyse in 1333) [ClassicSimilarity], result of:
           0.07242553 = score(doc=1333,freq=1.0), product of:
             0.15987754 = queryWeight, product of:
               1.441652 = boost
               5.7984805 = idf(docFreq=358, maxDocs=43556)
               0.0191255 = queryNorm
             0.4530063 = fieldWeight in 1333, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               5.7984805 = idf(docFreq=358, maxDocs=43556)
               0.078125 = fieldNorm(doc=1333)
         0.032693636 = weight(abstract_txt:einer in 1333) [ClassicSimilarity], result of:
           0.032693636 = score(doc=1333,freq=1.0), product of:
             0.10769583 = queryWeight, product of:
               1.4491448 = boost
               3.8857448 = idf(docFreq=2430, maxDocs=43556)
               0.0191255 = queryNorm
             0.30357382 = fieldWeight in 1333, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               3.8857448 = idf(docFreq=2430, maxDocs=43556)
               0.078125 = fieldNorm(doc=1333)
         0.04522697 = weight(abstract_txt:eine in 1333) [ClassicSimilarity], result of:
           0.04522697 = score(doc=1333,freq=2.0), product of:
             0.11680408 = queryWeight, product of:
               1.7426523 = boost
               3.5045679 = idf(docFreq=3558, maxDocs=43556)
               0.0191255 = queryNorm
             0.3872037 = fieldWeight in 1333, product of:
               1.4142135 = tf(freq=2.0), with freq of:
                 2.0 = termFreq=2.0
               3.5045679 = idf(docFreq=3558, maxDocs=43556)
               0.078125 = fieldNorm(doc=1333)
       0.24 = coord(6/25)
   

4. Müller, C.; Sternitzke, N.; Stratmann, R.; Parschik, T.: Kataloganreicherung und Zeitschriftenerschließung mit MyBib eDoc und C-3 am Ibero-Amerikanischen Institut, Preußischer Kulturbesitz : Neue Verfahren zur Optimierung der bibliografischen Nachweissituation in einer großen Spezialbibliothek (2010) 0.09

   0.09242085 = sum of:
     0.09242085 = product of:
       0.3850869 = sum of:
         0.068533294 = weight(abstract_txt:automatisierten in 497) [ClassicSimilarity], result of:
           0.068533294 = score(doc=497,freq=1.0), product of:
             0.17192931 = queryWeight, product of:
               1.0571258 = boost
               8.503749 = idf(docFreq=23, maxDocs=43556)
               0.0191255 = queryNorm
             0.3986132 = fieldWeight in 497, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               8.503749 = idf(docFreq=23, maxDocs=43556)
               0.046875 = fieldNorm(doc=497)
         0.122384325 = weight(abstract_txt:inhaltsverzeichnisse in 497) [ClassicSimilarity], result of:
           0.122384325 = score(doc=497,freq=3.0), product of:
             0.17546572 = queryWeight, product of:
               1.0679425 = boost
               8.59076 = idf(docFreq=21, maxDocs=43556)
               0.0191255 = queryNorm
             0.6974828 = fieldWeight in 497, product of:
               1.7320508 = tf(freq=3.0), with freq of:
                 3.0 = termFreq=3.0
               8.59076 = idf(docFreq=21, maxDocs=43556)
               0.046875 = fieldNorm(doc=497)
         0.07303658 = weight(abstract_txt:gängige in 497) [ClassicSimilarity], result of:
           0.07303658 = score(doc=497,freq=1.0), product of:
             0.17938073 = queryWeight, product of:
               1.0797908 = boost
               8.68607 = idf(docFreq=19, maxDocs=43556)
               0.0191255 = queryNorm
             0.40715957 = fieldWeight in 497, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               8.68607 = idf(docFreq=19, maxDocs=43556)
               0.046875 = fieldNorm(doc=497)
         0.026101533 = weight(abstract_txt:nach in 497) [ClassicSimilarity], result of:
           0.026101533 = score(doc=497,freq=2.0), product of:
             0.09033573 = queryWeight, product of:
               1.0836686 = boost
               4.358632 = idf(docFreq=1514, maxDocs=43556)
               0.0191255 = queryNorm
             0.2889392 = fieldWeight in 497, product of:
               1.4142135 = tf(freq=2.0), with freq of:
                 2.0 = termFreq=2.0
               4.358632 = idf(docFreq=1514, maxDocs=43556)
               0.046875 = fieldNorm(doc=497)
         0.03397622 = weight(abstract_txt:einer in 497) [ClassicSimilarity], result of:
           0.03397622 = score(doc=497,freq=3.0), product of:
             0.10769583 = queryWeight, product of:
               1.4491448 = boost
               3.8857448 = idf(docFreq=2430, maxDocs=43556)
               0.0191255 = queryNorm
             0.31548315 = fieldWeight in 497, product of:
               1.7320508 = tf(freq=3.0), with freq of:
                 3.0 = termFreq=3.0
               3.8857448 = idf(docFreq=2430, maxDocs=43556)
               0.046875 = fieldNorm(doc=497)
         0.06105494 = weight(abstract_txt:reihe in 497) [ClassicSimilarity], result of:
           0.06105494 = score(doc=497,freq=1.0), product of:
             0.20055772 = queryWeight, product of:
               1.6146798 = boost
               6.4944167 = idf(docFreq=178, maxDocs=43556)
               0.0191255 = queryNorm
             0.30442578 = fieldWeight in 497, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               6.4944167 = idf(docFreq=178, maxDocs=43556)
               0.046875 = fieldNorm(doc=497)
       0.24 = coord(6/25)
   

5. Kaizik, A.; Gödert, W.; Milanesi, C.: Erfahrungen und Ergebnisse aus der Evaluierung des EU-Projektes EULER im Rahmen des an der FH Köln angesiedelten Projektes EJECT (Evaluation von Subject Gateways des World Wide Web (2001) 0.08

   0.077613324 = sum of:
     0.077613324 = product of:
       0.38806662 = sum of:
         0.10186433 = weight(abstract_txt:methodik in 799) [ClassicSimilarity], result of:
           0.10186433 = score(doc=799,freq=1.0), product of:
             0.1592934 = queryWeight, product of:
               1.017538 = boost
               8.185295 = idf(docFreq=32, maxDocs=43556)
               0.0191255 = queryNorm
             0.6394762 = fieldWeight in 799, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               8.185295 = idf(docFreq=32, maxDocs=43556)
               0.078125 = fieldNorm(doc=799)
         0.07242553 = weight(abstract_txt:analyse in 799) [ClassicSimilarity], result of:
           0.07242553 = score(doc=799,freq=1.0), product of:
             0.15987754 = queryWeight, product of:
               1.441652 = boost
               5.7984805 = idf(docFreq=358, maxDocs=43556)
               0.0191255 = queryNorm
             0.4530063 = fieldWeight in 799, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               5.7984805 = idf(docFreq=358, maxDocs=43556)
               0.078125 = fieldNorm(doc=799)
         0.05662703 = weight(abstract_txt:einer in 799) [ClassicSimilarity], result of:
           0.05662703 = score(doc=799,freq=3.0), product of:
             0.10769583 = queryWeight, product of:
               1.4491448 = boost
               3.8857448 = idf(docFreq=2430, maxDocs=43556)
               0.0191255 = queryNorm
             0.52580523 = fieldWeight in 799, product of:
               1.7320508 = tf(freq=3.0), with freq of:
                 3.0 = termFreq=3.0
               3.8857448 = idf(docFreq=2430, maxDocs=43556)
               0.078125 = fieldNorm(doc=799)
         0.10175824 = weight(abstract_txt:reihe in 799) [ClassicSimilarity], result of:
           0.10175824 = score(doc=799,freq=1.0), product of:
             0.20055772 = queryWeight, product of:
               1.6146798 = boost
               6.4944167 = idf(docFreq=178, maxDocs=43556)
               0.0191255 = queryNorm
             0.5073763 = fieldWeight in 799, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               6.4944167 = idf(docFreq=178, maxDocs=43556)
               0.078125 = fieldNorm(doc=799)
         0.055391498 = weight(abstract_txt:eine in 799) [ClassicSimilarity], result of:
           0.055391498 = score(doc=799,freq=3.0), product of:
             0.11680408 = queryWeight, product of:
               1.7426523 = boost
               3.5045679 = idf(docFreq=3558, maxDocs=43556)
               0.0191255 = queryNorm
             0.47422573 = fieldWeight in 799, product of:
               1.7320508 = tf(freq=3.0), with freq of:
                 3.0 = termFreq=3.0
               3.5045679 = idf(docFreq=3558, maxDocs=43556)
               0.078125 = fieldNorm(doc=799)
       0.2 = coord(5/25)