Document (#38108)

Author

Liu, R.-L.

Title

¬A passage extractor for classification of disease aspect information

Source

Journal of the American Society for Information Science and Technology. 64(2013) no.11, S.2265-2277

Year

2013

Abstract

Retrieval of disease information is often based on several key aspects such as etiology, diagnosis, treatment, prevention, and symptoms of diseases. Automatic identification of disease aspect information is thus essential. In this article, I model the aspect identification problem as a text classification (TC) problem in which a disease aspect corresponds to a category. The disease aspect classification problem poses two challenges to classifiers: (a) a medical text often contains information about multiple aspects of a disease and hence produces noise for the classifiers and (b) text classifiers often cannot extract the textual parts (i.e., passages) about the categories of interest. I thus develop a technique, PETC (Passage Extractor for Text Classification), that extracts passages (from medical texts) for the underlying text classifiers to classify. Case studies on thousands of Chinese and English medical texts show that PETC enhances a support vector machine (SVM) classifier in classifying disease aspect information. PETC also performs better than three state-of-the-art classifier enhancement techniques, including two passage extraction techniques for text classifiers and a technique that employs term proximity information to enhance text classifiers. The contribution is of significance to evidence-based medicine, health education, and healthcare decision support. PETC can be used in those application domains in which a text to be classified may have several parts about different categories.

Theme

Automatisches Klassifizieren

Field

Medizin

Similar documents (content)

1. Mengle, S.; Goharian, N.: Passage detection using text classification (2009) 0.36

   0.35716006 = sum of:
     0.35716006 = product of:
       0.99211127 = sum of:
         0.023965774 = weight(abstract_txt:techniques in 3765) [ClassicSimilarity], result of:
           0.023965774 = score(doc=3765,freq=3.0), product of:
             0.055826657 = queryWeight, product of:
               4.5321174 = idf(docFreq=1298, maxDocs=44421)
               0.012318008 = queryNorm
             0.42928907 = fieldWeight in 3765, product of:
               1.7320508 = tf(freq=3.0), with freq of:
                 3.0 = termFreq=3.0
               4.5321174 = idf(docFreq=1298, maxDocs=44421)
               0.0546875 = fieldNorm(doc=3765)
         0.019594489 = weight(abstract_txt:thus in 3765) [ClassicSimilarity], result of:
           0.019594489 = score(doc=3765,freq=1.0), product of:
             0.07040071 = queryWeight, product of:
               1.1229688 = boost
               5.0894265 = idf(docFreq=743, maxDocs=44421)
               0.012318008 = queryNorm
             0.278328 = fieldWeight in 3765, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               5.0894265 = idf(docFreq=743, maxDocs=44421)
               0.0546875 = fieldNorm(doc=3765)
         0.035739645 = weight(abstract_txt:categories in 3765) [ClassicSimilarity], result of:
           0.035739645 = score(doc=3765,freq=3.0), product of:
             0.072869785 = queryWeight, product of:
               1.1424913 = boost
               5.177905 = idf(docFreq=680, maxDocs=44421)
               0.012318008 = queryNorm
             0.49045905 = fieldWeight in 3765, product of:
               1.7320508 = tf(freq=3.0), with freq of:
                 3.0 = termFreq=3.0
               5.177905 = idf(docFreq=680, maxDocs=44421)
               0.0546875 = fieldNorm(doc=3765)
         0.024227384 = weight(abstract_txt:often in 3765) [ClassicSimilarity], result of:
           0.024227384 = score(doc=3765,freq=1.0), product of:
             0.0928373 = queryWeight, product of:
               1.5793779 = boost
               4.7719507 = idf(docFreq=1021, maxDocs=44421)
               0.012318008 = queryNorm
             0.26096606 = fieldWeight in 3765, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               4.7719507 = idf(docFreq=1021, maxDocs=44421)
               0.0546875 = fieldNorm(doc=3765)
         0.010931072 = weight(abstract_txt:information in 3765) [ClassicSimilarity], result of:
           0.010931072 = score(doc=3765,freq=3.0), product of:
             0.047708552 = queryWeight, product of:
               1.6011719 = boost
               2.4188995 = idf(docFreq=10748, maxDocs=44421)
               0.012318008 = queryNorm
             0.22912185 = fieldWeight in 3765, product of:
               1.7320508 = tf(freq=3.0), with freq of:
                 3.0 = termFreq=3.0
               2.4188995 = idf(docFreq=10748, maxDocs=44421)
               0.0546875 = fieldNorm(doc=3765)
         0.018913897 = weight(abstract_txt:classification in 3765) [ClassicSimilarity], result of:
           0.018913897 = score(doc=3765,freq=1.0), product of:
             0.08663334 = queryWeight, product of:
               1.7617193 = boost
               3.9921594 = idf(docFreq=2228, maxDocs=44421)
               0.012318008 = queryNorm
             0.21832122 = fieldWeight in 3765, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               3.9921594 = idf(docFreq=2228, maxDocs=44421)
               0.0546875 = fieldNorm(doc=3765)
         0.31427586 = weight(abstract_txt:passages in 3765) [ClassicSimilarity], result of:
           0.31427586 = score(doc=3765,freq=14.0), product of:
             0.18577434 = queryWeight, product of:
               1.8241984 = boost
               8.267481 = idf(docFreq=30, maxDocs=44421)
               0.012318008 = queryNorm
             1.6917076 = fieldWeight in 3765, product of:
               3.7416575 = tf(freq=14.0), with freq of:
                 14.0 = termFreq=14.0
               8.267481 = idf(docFreq=30, maxDocs=44421)
               0.0546875 = fieldNorm(doc=3765)
         0.46600363 = weight(abstract_txt:passage in 3765) [ClassicSimilarity], result of:
           0.46600363 = score(doc=3765,freq=14.0), product of:
             0.27652538 = queryWeight, product of:
               2.7257895 = boost
               8.235732 = idf(docFreq=31, maxDocs=44421)
               0.012318008 = queryNorm
             1.6852111 = fieldWeight in 3765, product of:
               3.7416575 = tf(freq=14.0), with freq of:
                 14.0 = termFreq=14.0
               8.235732 = idf(docFreq=31, maxDocs=44421)
               0.0546875 = fieldNorm(doc=3765)
         0.07845957 = weight(abstract_txt:text in 3765) [ClassicSimilarity], result of:
           0.07845957 = score(doc=3765,freq=4.0), product of:
             0.1775218 = queryWeight, product of:
               3.5664408 = boost
               4.040882 = idf(docFreq=2122, maxDocs=44421)
               0.012318008 = queryNorm
             0.44197148 = fieldWeight in 3765, product of:
               2.0 = tf(freq=4.0), with freq of:
                 4.0 = termFreq=4.0
               4.040882 = idf(docFreq=2122, maxDocs=44421)
               0.0546875 = fieldNorm(doc=3765)
       0.36 = coord(9/25)
   

2. Liu, R.-L.: Dynamic category profiling for text filtering and classification (2007) 0.29

   0.29234317 = sum of:
     0.29234317 = product of:
       0.91357243 = sum of:
         0.04168757 = weight(abstract_txt:categories in 1900) [ClassicSimilarity], result of:
           0.04168757 = score(doc=1900,freq=2.0), product of:
             0.072869785 = queryWeight, product of:
               1.1424913 = boost
               5.177905 = idf(docFreq=680, maxDocs=44421)
               0.012318008 = queryNorm
             0.57208306 = fieldWeight in 1900, product of:
               1.4142135 = tf(freq=2.0), with freq of:
                 2.0 = termFreq=2.0
               5.177905 = idf(docFreq=680, maxDocs=44421)
               0.078125 = fieldNorm(doc=1900)
         0.037179224 = weight(abstract_txt:technique in 1900) [ClassicSimilarity], result of:
           0.037179224 = score(doc=1900,freq=1.0), product of:
             0.08506547 = queryWeight, product of:
               1.2343998 = boost
               5.5944448 = idf(docFreq=448, maxDocs=44421)
               0.012318008 = queryNorm
             0.437066 = fieldWeight in 1900, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               5.5944448 = idf(docFreq=448, maxDocs=44421)
               0.078125 = fieldNorm(doc=1900)
         0.028245263 = weight(abstract_txt:problem in 1900) [ClassicSimilarity], result of:
           0.028245263 = score(doc=1900,freq=1.0), product of:
             0.08107381 = queryWeight, product of:
               1.4759278 = boost
               4.4593854 = idf(docFreq=1396, maxDocs=44421)
               0.012318008 = queryNorm
             0.34838948 = fieldWeight in 1900, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               4.4593854 = idf(docFreq=1396, maxDocs=44421)
               0.078125 = fieldNorm(doc=1900)
         0.048946705 = weight(abstract_txt:often in 1900) [ClassicSimilarity], result of:
           0.048946705 = score(doc=1900,freq=2.0), product of:
             0.0928373 = queryWeight, product of:
               1.5793779 = boost
               4.7719507 = idf(docFreq=1021, maxDocs=44421)
               0.012318008 = queryNorm
             0.52723104 = fieldWeight in 1900, product of:
               1.4142135 = tf(freq=2.0), with freq of:
                 2.0 = termFreq=2.0
               4.7719507 = idf(docFreq=1021, maxDocs=44421)
               0.078125 = fieldNorm(doc=1900)
         0.009015797 = weight(abstract_txt:information in 1900) [ClassicSimilarity], result of:
           0.009015797 = score(doc=1900,freq=1.0), product of:
             0.047708552 = queryWeight, product of:
               1.6011719 = boost
               2.4188995 = idf(docFreq=10748, maxDocs=44421)
               0.012318008 = queryNorm
             0.18897653 = fieldWeight in 1900, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               2.4188995 = idf(docFreq=10748, maxDocs=44421)
               0.078125 = fieldNorm(doc=1900)
         0.02701985 = weight(abstract_txt:classification in 1900) [ClassicSimilarity], result of:
           0.02701985 = score(doc=1900,freq=1.0), product of:
             0.08663334 = queryWeight, product of:
               1.7617193 = boost
               3.9921594 = idf(docFreq=2228, maxDocs=44421)
               0.012318008 = queryNorm
             0.31188744 = fieldWeight in 1900, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               3.9921594 = idf(docFreq=2228, maxDocs=44421)
               0.078125 = fieldNorm(doc=1900)
         0.056042552 = weight(abstract_txt:text in 1900) [ClassicSimilarity], result of:
           0.056042552 = score(doc=1900,freq=1.0), product of:
             0.1775218 = queryWeight, product of:
               3.5664408 = boost
               4.040882 = idf(docFreq=2122, maxDocs=44421)
               0.012318008 = queryNorm
             0.3156939 = fieldWeight in 1900, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               4.040882 = idf(docFreq=2122, maxDocs=44421)
               0.078125 = fieldNorm(doc=1900)
         0.66543543 = weight(abstract_txt:classifiers in 1900) [ClassicSimilarity], result of:
           0.66543543 = score(doc=1900,freq=6.0), product of:
             0.46196988 = queryWeight, product of:
               4.9824924 = boost
               7.5270805 = idf(docFreq=64, maxDocs=44421)
               0.012318008 = queryNorm
             1.4404303 = fieldWeight in 1900, product of:
               2.4494898 = tf(freq=6.0), with freq of:
                 6.0 = termFreq=6.0
               7.5270805 = idf(docFreq=64, maxDocs=44421)
               0.078125 = fieldNorm(doc=1900)
       0.32 = coord(8/25)
   

3. Hofmann-Apitius, M.: Direct use of information extraction from scientific text for modeling and simulation in the life sciences (2009) 0.19

   0.19444905 = sum of:
     0.19444905 = product of:
       0.8102044 = sum of:
         0.082655534 = weight(abstract_txt:etiology in 3814) [ClassicSimilarity], result of:
           0.082655534 = score(doc=3814,freq=1.0), product of:
             0.13345383 = queryWeight, product of:
               1.0932758 = boost
               9.909708 = idf(docFreq=5, maxDocs=44421)
               0.012318008 = queryNorm
             0.61935675 = fieldWeight in 3814, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               9.909708 = idf(docFreq=5, maxDocs=44421)
               0.0625 = fieldNorm(doc=3814)
         0.033698454 = weight(abstract_txt:identification in 3814) [ClassicSimilarity], result of:
           0.033698454 = score(doc=3814,freq=1.0), product of:
             0.09244847 = queryWeight, product of:
               1.2868533 = boost
               5.8321705 = idf(docFreq=353, maxDocs=44421)
               0.012318008 = queryNorm
             0.36451066 = fieldWeight in 3814, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               5.8321705 = idf(docFreq=353, maxDocs=44421)
               0.0625 = fieldNorm(doc=3814)
         0.015298693 = weight(abstract_txt:about in 3814) [ClassicSimilarity], result of:
           0.015298693 = score(doc=3814,freq=1.0), product of:
             0.062511474 = queryWeight, product of:
               1.295999 = boost
               3.9157467 = idf(docFreq=2405, maxDocs=44421)
               0.012318008 = queryNorm
             0.24473417 = fieldWeight in 3814, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               3.9157467 = idf(docFreq=2405, maxDocs=44421)
               0.0625 = fieldNorm(doc=3814)
         0.014425274 = weight(abstract_txt:information in 3814) [ClassicSimilarity], result of:
           0.014425274 = score(doc=3814,freq=4.0), product of:
             0.047708552 = queryWeight, product of:
               1.6011719 = boost
               2.4188995 = idf(docFreq=10748, maxDocs=44421)
               0.012318008 = queryNorm
             0.30236244 = fieldWeight in 3814, product of:
               2.0 = tf(freq=4.0), with freq of:
                 4.0 = termFreq=4.0
               2.4188995 = idf(docFreq=10748, maxDocs=44421)
               0.0625 = fieldNorm(doc=3814)
         0.11861972 = weight(abstract_txt:text in 3814) [ClassicSimilarity], result of:
           0.11861972 = score(doc=3814,freq=7.0), product of:
             0.1775218 = queryWeight, product of:
               3.5664408 = boost
               4.040882 = idf(docFreq=2122, maxDocs=44421)
               0.012318008 = queryNorm
             0.66819805 = fieldWeight in 3814, product of:
               2.6457512 = tf(freq=7.0), with freq of:
                 7.0 = termFreq=7.0
               4.040882 = idf(docFreq=2122, maxDocs=44421)
               0.0625 = fieldNorm(doc=3814)
         0.5455067 = weight(abstract_txt:disease in 3814) [ClassicSimilarity], result of:
           0.5455067 = score(doc=3814,freq=4.0), product of:
             0.56584287 = queryWeight, product of:
               5.9560885 = boost
               7.7124834 = idf(docFreq=53, maxDocs=44421)
               0.012318008 = queryNorm
             0.9640604 = fieldWeight in 3814, product of:
               2.0 = tf(freq=4.0), with freq of:
                 4.0 = termFreq=4.0
               7.7124834 = idf(docFreq=53, maxDocs=44421)
               0.0625 = fieldNorm(doc=3814)
       0.24 = coord(6/25)
   

4. Sebastiani, F.: Classification of text, automatic (2006) 0.19

   0.1892592 = sum of:
     0.1892592 = product of:
       0.67592573 = sum of:
         0.050025087 = weight(abstract_txt:categories in 3) [ClassicSimilarity], result of:
           0.050025087 = score(doc=3,freq=2.0), product of:
             0.072869785 = queryWeight, product of:
               1.1424913 = boost
               5.177905 = idf(docFreq=680, maxDocs=44421)
               0.012318008 = queryNorm
             0.6864997 = fieldWeight in 3, product of:
               1.4142135 = tf(freq=2.0), with freq of:
                 2.0 = termFreq=2.0
               5.177905 = idf(docFreq=680, maxDocs=44421)
               0.09375 = fieldNorm(doc=3)
         0.0645695 = weight(abstract_txt:texts in 3) [ClassicSimilarity], result of:
           0.0645695 = score(doc=3,freq=2.0), product of:
             0.086385444 = queryWeight, product of:
               1.2439401 = boost
               5.6376824 = idf(docFreq=429, maxDocs=44421)
               0.012318008 = queryNorm
             0.74745816 = fieldWeight in 3, product of:
               1.4142135 = tf(freq=2.0), with freq of:
                 2.0 = termFreq=2.0
               5.6376824 = idf(docFreq=429, maxDocs=44421)
               0.09375 = fieldNorm(doc=3)
         0.09698555 = weight(abstract_txt:classifier in 3) [ClassicSimilarity], result of:
           0.09698555 = score(doc=3,freq=1.0), product of:
             0.14274807 = queryWeight, product of:
               1.5990584 = boost
               7.2471204 = idf(docFreq=85, maxDocs=44421)
               0.012318008 = queryNorm
             0.67941755 = fieldWeight in 3, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               7.2471204 = idf(docFreq=85, maxDocs=44421)
               0.09375 = fieldNorm(doc=3)
         0.0108189555 = weight(abstract_txt:information in 3) [ClassicSimilarity], result of:
           0.0108189555 = score(doc=3,freq=1.0), product of:
             0.047708552 = queryWeight, product of:
               1.6011719 = boost
               2.4188995 = idf(docFreq=10748, maxDocs=44421)
               0.012318008 = queryNorm
             0.22677183 = fieldWeight in 3, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               2.4188995 = idf(docFreq=10748, maxDocs=44421)
               0.09375 = fieldNorm(doc=3)
         0.032423824 = weight(abstract_txt:classification in 3) [ClassicSimilarity], result of:
           0.032423824 = score(doc=3,freq=1.0), product of:
             0.08663334 = queryWeight, product of:
               1.7617193 = boost
               3.9921594 = idf(docFreq=2228, maxDocs=44421)
               0.012318008 = queryNorm
             0.37426496 = fieldWeight in 3, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               3.9921594 = idf(docFreq=2228, maxDocs=44421)
               0.09375 = fieldNorm(doc=3)
         0.09510736 = weight(abstract_txt:text in 3) [ClassicSimilarity], result of:
           0.09510736 = score(doc=3,freq=2.0), product of:
             0.1775218 = queryWeight, product of:
               3.5664408 = boost
               4.040882 = idf(docFreq=2122, maxDocs=44421)
               0.012318008 = queryNorm
             0.5357503 = fieldWeight in 3, product of:
               1.4142135 = tf(freq=2.0), with freq of:
                 2.0 = termFreq=2.0
               4.040882 = idf(docFreq=2122, maxDocs=44421)
               0.09375 = fieldNorm(doc=3)
         0.32599542 = weight(abstract_txt:classifiers in 3) [ClassicSimilarity], result of:
           0.32599542 = score(doc=3,freq=1.0), product of:
             0.46196988 = queryWeight, product of:
               4.9824924 = boost
               7.5270805 = idf(docFreq=64, maxDocs=44421)
               0.012318008 = queryNorm
             0.7056638 = fieldWeight in 3, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               7.5270805 = idf(docFreq=64, maxDocs=44421)
               0.09375 = fieldNorm(doc=3)
       0.28 = coord(7/25)
   

5. Liu, R.-L.: Context-based term frequency assessment for text classification (2010) 0.18

   0.17966552 = sum of:
     0.17966552 = product of:
       0.7486063 = sum of:
         0.019980665 = weight(abstract_txt:several in 318) [ClassicSimilarity], result of:
           0.019980665 = score(doc=318,freq=1.0), product of:
             0.056228917 = queryWeight, product of:
               1.0035963 = boost
               4.548416 = idf(docFreq=1277, maxDocs=44421)
               0.012318008 = queryNorm
             0.355345 = fieldWeight in 318, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               4.548416 = idf(docFreq=1277, maxDocs=44421)
               0.078125 = fieldNorm(doc=318)
         0.037179224 = weight(abstract_txt:technique in 318) [ClassicSimilarity], result of:
           0.037179224 = score(doc=318,freq=1.0), product of:
             0.08506547 = queryWeight, product of:
               1.2343998 = boost
               5.5944448 = idf(docFreq=448, maxDocs=44421)
               0.012318008 = queryNorm
             0.437066 = fieldWeight in 318, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               5.5944448 = idf(docFreq=448, maxDocs=44421)
               0.078125 = fieldNorm(doc=318)
         0.009015797 = weight(abstract_txt:information in 318) [ClassicSimilarity], result of:
           0.009015797 = score(doc=318,freq=1.0), product of:
             0.047708552 = queryWeight, product of:
               1.6011719 = boost
               2.4188995 = idf(docFreq=10748, maxDocs=44421)
               0.012318008 = queryNorm
             0.18897653 = fieldWeight in 318, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               2.4188995 = idf(docFreq=10748, maxDocs=44421)
               0.078125 = fieldNorm(doc=318)
         0.02701985 = weight(abstract_txt:classification in 318) [ClassicSimilarity], result of:
           0.02701985 = score(doc=318,freq=1.0), product of:
             0.08663334 = queryWeight, product of:
               1.7617193 = boost
               3.9921594 = idf(docFreq=2228, maxDocs=44421)
               0.012318008 = queryNorm
             0.31188744 = fieldWeight in 318, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               3.9921594 = idf(docFreq=2228, maxDocs=44421)
               0.078125 = fieldNorm(doc=318)
         0.112085104 = weight(abstract_txt:text in 318) [ClassicSimilarity], result of:
           0.112085104 = score(doc=318,freq=4.0), product of:
             0.1775218 = queryWeight, product of:
               3.5664408 = boost
               4.040882 = idf(docFreq=2122, maxDocs=44421)
               0.012318008 = queryNorm
             0.6313878 = fieldWeight in 318, product of:
               2.0 = tf(freq=4.0), with freq of:
                 4.0 = termFreq=4.0
               4.040882 = idf(docFreq=2122, maxDocs=44421)
               0.078125 = fieldNorm(doc=318)
         0.5433257 = weight(abstract_txt:classifiers in 318) [ClassicSimilarity], result of:
           0.5433257 = score(doc=318,freq=4.0), product of:
             0.46196988 = queryWeight, product of:
               4.9824924 = boost
               7.5270805 = idf(docFreq=64, maxDocs=44421)
               0.012318008 = queryNorm
             1.1761063 = fieldWeight in 318, product of:
               2.0 = tf(freq=4.0), with freq of:
                 4.0 = termFreq=4.0
               7.5270805 = idf(docFreq=64, maxDocs=44421)
               0.078125 = fieldNorm(doc=318)
       0.24 = coord(6/25)