Document (#34288)

Author

Khoo, C.S.G.
Ou, S.

Title

Machine versus human clustering of concepts across documents

Source

Culture and identity in knowledge organization: Proceedings of the Tenth International ISKO Conference 5-8 August 2008, Montreal, Canada. Ed. by Clément Arsenault and Joseph T. Tennis

Imprint

Würzburg : Ergon Verlag

Year

2008

Pages

S.333-339

Series

Advances in knowledge organization; vol.11

Content

An automated method for clustering terms/concepts from a set of documents on the same topic was developed for the purpose of multidocument summarization. The clustering method makes use of a combination of lexical overlap between multiword terms, syntactic constraints and semantic consideration based on a manually constructed taxonomy to generate hierarchically organized clusters of terms. This study evaluates the machine-generated clusters by calculating the proportion of overlap with two sets of human-generated clusters for 15 topics. It was found that the overlap between machine-generated clusters and individual human-generated clusters are higher than that between two human-generated clusters. A quailtative analysis of the human clustering found that clusters formed are either semantic-conceptual based or lexical based (similar to machine clustering). The semantic-conceptual based clusters that were formed tended to be different for different human coders. This has raised questions about whether machine-generated clustering can be evaluated by comparing with human clustering.

Footnote

Vgl. unter: http://www.ergon-verlag.de/isko_ko/tocs/0497f79b0c0b3ed06/0497f79b0c0b5550a/index.php.

Theme

Automatisches Klassifizieren

Similar documents (author)

1. Khoo, C.S.G.; Poo, D.C.C.: ¬An expert system approach to online catalog subject searching (1994) 6.11

   6.1113977 = sum of:
     6.1113977 = sum of:
       2.7258348 = weight(author_txt:khoo in 7303) [ClassicSimilarity], result of:
         2.7258348 = score(doc=7303,freq=1.0), product of:
           0.6544083 = queryWeight, product of:
             8.330686 = idf(docFreq=27, maxDocs=42740)
             0.07855395 = queryNorm
           4.165343 = fieldWeight in 7303, product of:
             1.0 = tf(freq=1.0), with freq of:
               1.0 = termFreq=1.0
             8.330686 = idf(docFreq=27, maxDocs=42740)
             0.5 = fieldNorm(doc=7303)
       3.385563 = weight(author_txt:c.s.g in 7303) [ClassicSimilarity], result of:
         3.385563 = score(doc=7303,freq=1.0), product of:
           0.7561414 = queryWeight, product of:
             1.0749224 = boost
             8.954841 = idf(docFreq=14, maxDocs=42740)
             0.07855395 = queryNorm
           4.4774203 = fieldWeight in 7303, product of:
             1.0 = tf(freq=1.0), with freq of:
               1.0 = termFreq=1.0
             8.954841 = idf(docFreq=14, maxDocs=42740)
             0.5 = fieldNorm(doc=7303)
   

2. Chaudhry, A.S.; Khoo, C.S.G..: ¬A survey of the top-level categories in the structure of corporate Websites (2008) 6.11

   6.1113977 = sum of:
     6.1113977 = sum of:
       2.7258348 = weight(author_txt:khoo in 4260) [ClassicSimilarity], result of:
         2.7258348 = score(doc=4260,freq=1.0), product of:
           0.6544083 = queryWeight, product of:
             8.330686 = idf(docFreq=27, maxDocs=42740)
             0.07855395 = queryNorm
           4.165343 = fieldWeight in 4260, product of:
             1.0 = tf(freq=1.0), with freq of:
               1.0 = termFreq=1.0
             8.330686 = idf(docFreq=27, maxDocs=42740)
             0.5 = fieldNorm(doc=4260)
       3.385563 = weight(author_txt:c.s.g in 4260) [ClassicSimilarity], result of:
         3.385563 = score(doc=4260,freq=1.0), product of:
           0.7561414 = queryWeight, product of:
             1.0749224 = boost
             8.954841 = idf(docFreq=14, maxDocs=42740)
             0.07855395 = queryNorm
           4.4774203 = fieldWeight in 4260, product of:
             1.0 = tf(freq=1.0), with freq of:
               1.0 = termFreq=1.0
             8.954841 = idf(docFreq=14, maxDocs=42740)
             0.5 = fieldNorm(doc=4260)
   

3. Poo, D.C.C.; Khoo, C.S.G.: Online Catalog Subject Searching (2009) 6.11

   6.1113977 = sum of:
     6.1113977 = sum of:
       2.7258348 = weight(author_txt:khoo in 852) [ClassicSimilarity], result of:
         2.7258348 = score(doc=852,freq=1.0), product of:
           0.6544083 = queryWeight, product of:
             8.330686 = idf(docFreq=27, maxDocs=42740)
             0.07855395 = queryNorm
           4.165343 = fieldWeight in 852, product of:
             1.0 = tf(freq=1.0), with freq of:
               1.0 = termFreq=1.0
             8.330686 = idf(docFreq=27, maxDocs=42740)
             0.5 = fieldNorm(doc=852)
       3.385563 = weight(author_txt:c.s.g in 852) [ClassicSimilarity], result of:
         3.385563 = score(doc=852,freq=1.0), product of:
           0.7561414 = queryWeight, product of:
             1.0749224 = boost
             8.954841 = idf(docFreq=14, maxDocs=42740)
             0.07855395 = queryNorm
           4.4774203 = fieldWeight in 852, product of:
             1.0 = tf(freq=1.0), with freq of:
               1.0 = termFreq=1.0
             8.954841 = idf(docFreq=14, maxDocs=42740)
             0.5 = fieldNorm(doc=852)
   

4. Sun, G.; Khoo, C.S.G.: ¬A framework to represent variables and values in social science research data sets to support data curation and reuse (2018) 6.11

   6.1113977 = sum of:
     6.1113977 = sum of:
       2.7258348 = weight(author_txt:khoo in 745) [ClassicSimilarity], result of:
         2.7258348 = score(doc=745,freq=1.0), product of:
           0.6544083 = queryWeight, product of:
             8.330686 = idf(docFreq=27, maxDocs=42740)
             0.07855395 = queryNorm
           4.165343 = fieldWeight in 745, product of:
             1.0 = tf(freq=1.0), with freq of:
               1.0 = termFreq=1.0
             8.330686 = idf(docFreq=27, maxDocs=42740)
             0.5 = fieldNorm(doc=745)
       3.385563 = weight(author_txt:c.s.g in 745) [ClassicSimilarity], result of:
         3.385563 = score(doc=745,freq=1.0), product of:
           0.7561414 = queryWeight, product of:
             1.0749224 = boost
             8.954841 = idf(docFreq=14, maxDocs=42740)
             0.07855395 = queryNorm
           4.4774203 = fieldWeight in 745, product of:
             1.0 = tf(freq=1.0), with freq of:
               1.0 = termFreq=1.0
             8.954841 = idf(docFreq=14, maxDocs=42740)
             0.5 = fieldNorm(doc=745)
   

5. Khoo, C.S.G.; Wan, K.-W.: ¬A simple relevancy-ranking strategy for an interface to Boolean OPACs (2004) 5.35

   5.347473 = sum of:
     5.347473 = sum of:
       2.3851056 = weight(author_txt:khoo in 3510) [ClassicSimilarity], result of:
         2.3851056 = score(doc=3510,freq=1.0), product of:
           0.6544083 = queryWeight, product of:
             8.330686 = idf(docFreq=27, maxDocs=42740)
             0.07855395 = queryNorm
           3.644675 = fieldWeight in 3510, product of:
             1.0 = tf(freq=1.0), with freq of:
               1.0 = termFreq=1.0
             8.330686 = idf(docFreq=27, maxDocs=42740)
             0.4375 = fieldNorm(doc=3510)
       2.9623675 = weight(author_txt:c.s.g in 3510) [ClassicSimilarity], result of:
         2.9623675 = score(doc=3510,freq=1.0), product of:
           0.7561414 = queryWeight, product of:
             1.0749224 = boost
             8.954841 = idf(docFreq=14, maxDocs=42740)
             0.07855395 = queryNorm
           3.9177427 = fieldWeight in 3510, product of:
             1.0 = tf(freq=1.0), with freq of:
               1.0 = termFreq=1.0
             8.954841 = idf(docFreq=14, maxDocs=42740)
             0.4375 = fieldNorm(doc=3510)
   

Similar documents (content)

1. Huang, L.; Milne, D.; Frank, E.; Witten, I.H.: Learning a concept-based document similarity measure (2012) 0.40

   0.4001165 = sum of:
     0.4001165 = product of:
       0.70020384 = sum of:
         0.09900025 = weight(abstract_txt:documents in 2373) [ClassicSimilarity], result of:
           0.09900025 = score(doc=2373,freq=2.0), product of:
             0.21773107 = queryWeight, product of:
               4.115389 = idf(docFreq=1895, maxDocs=42740)
               0.05290656 = queryNorm
             0.45469052 = fieldWeight in 2373, product of:
               1.4142135 = tf(freq=2.0), with freq of:
                 2.0 = termFreq=2.0
               4.115389 = idf(docFreq=1895, maxDocs=42740)
               0.078125 = fieldNorm(doc=2373)
         0.10651262 = weight(abstract_txt:human in 2373) [ClassicSimilarity], result of:
           0.10651262 = score(doc=2373,freq=1.0), product of:
             0.28803167 = queryWeight, product of:
               1.1501644 = boost
               4.7333736 = idf(docFreq=1021, maxDocs=42740)
               0.05290656 = queryNorm
             0.36979482 = fieldWeight in 2373, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               4.7333736 = idf(docFreq=1021, maxDocs=42740)
               0.078125 = fieldNorm(doc=2373)
         0.15281083 = weight(abstract_txt:machine in 2373) [ClassicSimilarity], result of:
           0.15281083 = score(doc=2373,freq=1.0), product of:
             0.3663889 = queryWeight, product of:
               1.2972119 = boost
               5.3385315 = idf(docFreq=557, maxDocs=42740)
               0.05290656 = queryNorm
             0.41707277 = fieldWeight in 2373, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               5.3385315 = idf(docFreq=557, maxDocs=42740)
               0.078125 = fieldNorm(doc=2373)
         0.34188014 = weight(abstract_txt:clustering in 2373) [ClassicSimilarity], result of:
           0.34188014 = score(doc=2373,freq=2.0), product of:
             0.49744543 = queryWeight, product of:
               1.5115151 = boost
               6.220473 = idf(docFreq=230, maxDocs=42740)
               0.05290656 = queryNorm
             0.68727165 = fieldWeight in 2373, product of:
               1.4142135 = tf(freq=2.0), with freq of:
                 2.0 = termFreq=2.0
               6.220473 = idf(docFreq=230, maxDocs=42740)
               0.078125 = fieldNorm(doc=2373)
       0.5714286 = coord(4/7)
   

2. Zheng, H.-T.; Borchert, C.; Kim, H.-G.: Exploiting corpus-related ontologies for conceptualizing document corpora (2009) 0.38

   0.38126832 = sum of:
     0.38126832 = product of:
       0.6672195 = sum of:
         0.07920021 = weight(abstract_txt:documents in 166) [ClassicSimilarity], result of:
           0.07920021 = score(doc=166,freq=2.0), product of:
             0.21773107 = queryWeight, product of:
               4.115389 = idf(docFreq=1895, maxDocs=42740)
               0.05290656 = queryNorm
             0.36375242 = fieldWeight in 166, product of:
               1.4142135 = tf(freq=2.0), with freq of:
                 2.0 = termFreq=2.0
               4.115389 = idf(docFreq=1895, maxDocs=42740)
               0.0625 = fieldNorm(doc=166)
         0.20382963 = weight(abstract_txt:concepts in 166) [ClassicSimilarity], result of:
           0.20382963 = score(doc=166,freq=7.0), product of:
             0.2693137 = queryWeight, product of:
               1.1121645 = boost
               4.576989 = idf(docFreq=1194, maxDocs=42740)
               0.05290656 = queryNorm
             0.7568484 = fieldWeight in 166, product of:
               2.6457512 = tf(freq=7.0), with freq of:
                 7.0 = termFreq=7.0
               4.576989 = idf(docFreq=1194, maxDocs=42740)
               0.0625 = fieldNorm(doc=166)
         0.110685535 = weight(abstract_txt:across in 166) [ClassicSimilarity], result of:
           0.110685535 = score(doc=166,freq=1.0), product of:
             0.34290472 = queryWeight, product of:
               1.2549503 = boost
               5.1646085 = idf(docFreq=663, maxDocs=42740)
               0.05290656 = queryNorm
             0.32278803 = fieldWeight in 166, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               5.1646085 = idf(docFreq=663, maxDocs=42740)
               0.0625 = fieldNorm(doc=166)
         0.2735041 = weight(abstract_txt:clustering in 166) [ClassicSimilarity], result of:
           0.2735041 = score(doc=166,freq=2.0), product of:
             0.49744543 = queryWeight, product of:
               1.5115151 = boost
               6.220473 = idf(docFreq=230, maxDocs=42740)
               0.05290656 = queryNorm
             0.5498173 = fieldWeight in 166, product of:
               1.4142135 = tf(freq=2.0), with freq of:
                 2.0 = termFreq=2.0
               6.220473 = idf(docFreq=230, maxDocs=42740)
               0.0625 = fieldNorm(doc=166)
       0.5714286 = coord(4/7)
   

3. Golub, K.: Automatic subject indexing of text (2019) 0.32

   0.32139507 = sum of:
     0.32139507 = product of:
       0.56244135 = sum of:
         0.056003 = weight(abstract_txt:documents in 1269) [ClassicSimilarity], result of:
           0.056003 = score(doc=1269,freq=1.0), product of:
             0.21773107 = queryWeight, product of:
               4.115389 = idf(docFreq=1895, maxDocs=42740)
               0.05290656 = queryNorm
             0.2572118 = fieldWeight in 1269, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               4.115389 = idf(docFreq=1895, maxDocs=42740)
               0.0625 = fieldNorm(doc=1269)
         0.110685535 = weight(abstract_txt:across in 1269) [ClassicSimilarity], result of:
           0.110685535 = score(doc=1269,freq=1.0), product of:
             0.34290472 = queryWeight, product of:
               1.2549503 = boost
               5.1646085 = idf(docFreq=663, maxDocs=42740)
               0.05290656 = queryNorm
             0.32278803 = fieldWeight in 1269, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               5.1646085 = idf(docFreq=663, maxDocs=42740)
               0.0625 = fieldNorm(doc=1269)
         0.122248664 = weight(abstract_txt:machine in 1269) [ClassicSimilarity], result of:
           0.122248664 = score(doc=1269,freq=1.0), product of:
             0.3663889 = queryWeight, product of:
               1.2972119 = boost
               5.3385315 = idf(docFreq=557, maxDocs=42740)
               0.05290656 = queryNorm
             0.33365822 = fieldWeight in 1269, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               5.3385315 = idf(docFreq=557, maxDocs=42740)
               0.0625 = fieldNorm(doc=1269)
         0.2735041 = weight(abstract_txt:clustering in 1269) [ClassicSimilarity], result of:
           0.2735041 = score(doc=1269,freq=2.0), product of:
             0.49744543 = queryWeight, product of:
               1.5115151 = boost
               6.220473 = idf(docFreq=230, maxDocs=42740)
               0.05290656 = queryNorm
             0.5498173 = fieldWeight in 1269, product of:
               1.4142135 = tf(freq=2.0), with freq of:
                 2.0 = termFreq=2.0
               6.220473 = idf(docFreq=230, maxDocs=42740)
               0.0625 = fieldNorm(doc=1269)
       0.5714286 = coord(4/7)
   

4. Baker, T.: Languages for Dublin Core (1998) 0.31

   0.31455448 = sum of:
     0.31455448 = product of:
       0.44037628 = sum of:
         0.035001878 = weight(abstract_txt:documents in 3258) [ClassicSimilarity], result of:
           0.035001878 = score(doc=3258,freq=1.0), product of:
             0.21773107 = queryWeight, product of:
               4.115389 = idf(docFreq=1895, maxDocs=42740)
               0.05290656 = queryNorm
             0.16075738 = fieldWeight in 3258, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               4.115389 = idf(docFreq=1895, maxDocs=42740)
               0.0390625 = fieldNorm(doc=3258)
         0.092242636 = weight(abstract_txt:human in 3258) [ClassicSimilarity], result of:
           0.092242636 = score(doc=3258,freq=3.0), product of:
             0.28803167 = queryWeight, product of:
               1.1501644 = boost
               4.7333736 = idf(docFreq=1021, maxDocs=42740)
               0.05290656 = queryNorm
             0.3202517 = fieldWeight in 3258, product of:
               1.7320508 = tf(freq=3.0), with freq of:
                 3.0 = termFreq=3.0
               4.7333736 = idf(docFreq=1021, maxDocs=42740)
               0.0390625 = fieldNorm(doc=3258)
         0.09783311 = weight(abstract_txt:across in 3258) [ClassicSimilarity], result of:
           0.09783311 = score(doc=3258,freq=2.0), product of:
             0.34290472 = queryWeight, product of:
               1.2549503 = boost
               5.1646085 = idf(docFreq=663, maxDocs=42740)
               0.05290656 = queryNorm
             0.285307 = fieldWeight in 3258, product of:
               1.4142135 = tf(freq=2.0), with freq of:
                 2.0 = termFreq=2.0
               5.1646085 = idf(docFreq=663, maxDocs=42740)
               0.0390625 = fieldNorm(doc=3258)
         0.07640541 = weight(abstract_txt:machine in 3258) [ClassicSimilarity], result of:
           0.07640541 = score(doc=3258,freq=1.0), product of:
             0.3663889 = queryWeight, product of:
               1.2972119 = boost
               5.3385315 = idf(docFreq=557, maxDocs=42740)
               0.05290656 = queryNorm
             0.20853639 = fieldWeight in 3258, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               5.3385315 = idf(docFreq=557, maxDocs=42740)
               0.0390625 = fieldNorm(doc=3258)
         0.13889326 = weight(abstract_txt:versus in 3258) [ClassicSimilarity], result of:
           0.13889326 = score(doc=3258,freq=1.0), product of:
             0.54573315 = queryWeight, product of:
               1.5831788 = boost
               6.515396 = idf(docFreq=171, maxDocs=42740)
               0.05290656 = queryNorm
             0.25450766 = fieldWeight in 3258, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               6.515396 = idf(docFreq=171, maxDocs=42740)
               0.0390625 = fieldNorm(doc=3258)
       0.71428573 = coord(5/7)
   

5. Losee, R.M.; Church Jr., L.: Are two document clusters better than one? : the cluster performance question for information retrieval (2005) 0.30

   0.30318996 = sum of:
     0.30318996 = product of:
       0.70744324 = sum of:
         0.08400451 = weight(abstract_txt:documents in 4271) [ClassicSimilarity], result of:
           0.08400451 = score(doc=4271,freq=1.0), product of:
             0.21773107 = queryWeight, product of:
               4.115389 = idf(docFreq=1895, maxDocs=42740)
               0.05290656 = queryNorm
             0.3858177 = fieldWeight in 4271, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               4.115389 = idf(docFreq=1895, maxDocs=42740)
               0.09375 = fieldNorm(doc=4271)
         0.2900949 = weight(abstract_txt:clustering in 4271) [ClassicSimilarity], result of:
           0.2900949 = score(doc=4271,freq=1.0), product of:
             0.49744543 = queryWeight, product of:
               1.5115151 = boost
               6.220473 = idf(docFreq=230, maxDocs=42740)
               0.05290656 = queryNorm
             0.58316934 = fieldWeight in 4271, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               6.220473 = idf(docFreq=230, maxDocs=42740)
               0.09375 = fieldNorm(doc=4271)
         0.33334383 = weight(abstract_txt:versus in 4271) [ClassicSimilarity], result of:
           0.33334383 = score(doc=4271,freq=1.0), product of:
             0.54573315 = queryWeight, product of:
               1.5831788 = boost
               6.515396 = idf(docFreq=171, maxDocs=42740)
               0.05290656 = queryNorm
             0.6108184 = fieldWeight in 4271, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               6.515396 = idf(docFreq=171, maxDocs=42740)
               0.09375 = fieldNorm(doc=4271)
       0.42857143 = coord(3/7)