Document (#42106)

Author
Xing, F.Z.
Pallucchini, F.
Cambria, E.
Title
Cognitive-inspired domain adaptation of sentiment lexicons
Source
Information processing and management. 56(2019) no.3, S.554-564
Year
2019
Abstract
Sentiment lexicons are essential tools for polarity classification and opinion mining. In contrast to machine learning methods that only leverage text features or raw text for sentiment analysis, methods that use sentiment lexicons embrace higher interpretability. Although a number of domain-specific sentiment lexicons are made available, it is impractical to build an ex ante lexicon that fully reflects the characteristics of the language usage in endless domains. In this article, we propose a novel approach to simultaneously train a vanilla sentiment classifier and adapt word polarities to the target domain. Specifically, we sequentially track the wrongly predicted sentences and use them as the supervision instead of addressing the gold standard as a whole to emulate the life-long cognitive process of lexicon learning. An exploration-exploitation mechanism is designed to trade off between searching for new sentiment words and updating the polarity score of one word. Experimental results on several popular datasets show that our approach significantly improves the sentiment classification performance for a variety of domains by means of improving the quality of sentiment lexicons. Case-studies also illustrate how polarity scores of the same words are discovered for different domains.
Content
Vgl.: https://doi.org/10.1016/j.ipm.2018.11.002.

Similar documents (content)

  1. Malo, P.; Sinha, A.; Korhonen, P.; Wallenius, J.; Takala, P.: Good debt or bad debt : detecting semantic orientations in economic texts (2014) 0.47
    0.4671248 = sum of:
      0.4671248 = product of:
        1.2975688 = sum of:
          0.010946719 = weight(abstract_txt:that in 3227) [ClassicSimilarity], result of:
            0.010946719 = score(doc=3227,freq=6.0), product of:
              0.02985965 = queryWeight, product of:
                1.2420996 = boost
                2.3946586 = idf(docFreq=10595, maxDocs=42740)
                0.010038867 = queryNorm
              0.36660573 = fieldWeight in 3227, product of:
                2.4494898 = tf(freq=6.0), with freq of:
                  6.0 = termFreq=6.0
                2.3946586 = idf(docFreq=10595, maxDocs=42740)
                0.0625 = fieldNorm(doc=3227)
          0.018080086 = weight(abstract_txt:learning in 3227) [ClassicSimilarity], result of:
            0.018080086 = score(doc=3227,freq=1.0), product of:
              0.06017316 = queryWeight, product of:
                1.2468107 = boost
                4.807482 = idf(docFreq=948, maxDocs=42740)
                0.010038867 = queryNorm
              0.3004676 = fieldWeight in 3227, product of:
                1.0 = tf(freq=1.0), with freq of:
                  1.0 = termFreq=1.0
                4.807482 = idf(docFreq=948, maxDocs=42740)
                0.0625 = fieldNorm(doc=3227)
          0.025035894 = weight(abstract_txt:words in 3227) [ClassicSimilarity], result of:
            0.025035894 = score(doc=3227,freq=1.0), product of:
              0.07475574 = queryWeight, product of:
                1.389701 = boost
                5.358442 = idf(docFreq=546, maxDocs=42740)
                0.010038867 = queryNorm
              0.3349026 = fieldWeight in 3227, product of:
                1.0 = tf(freq=1.0), with freq of:
                  1.0 = termFreq=1.0
                5.358442 = idf(docFreq=546, maxDocs=42740)
                0.0625 = fieldNorm(doc=3227)
          0.026403695 = weight(abstract_txt:word in 3227) [ClassicSimilarity], result of:
            0.026403695 = score(doc=3227,freq=1.0), product of:
              0.07745432 = queryWeight, product of:
                1.4145617 = boost
                5.4543004 = idf(docFreq=496, maxDocs=42740)
                0.010038867 = queryNorm
              0.34089378 = fieldWeight in 3227, product of:
                1.0 = tf(freq=1.0), with freq of:
                  1.0 = termFreq=1.0
                5.4543004 = idf(docFreq=496, maxDocs=42740)
                0.0625 = fieldNorm(doc=3227)
          0.026630992 = weight(abstract_txt:domain in 3227) [ClassicSimilarity], result of:
            0.026630992 = score(doc=3227,freq=1.0), product of:
              0.08917117 = queryWeight, product of:
                1.8589039 = boost
                4.7784038 = idf(docFreq=976, maxDocs=42740)
                0.010038867 = queryNorm
              0.29865023 = fieldWeight in 3227, product of:
                1.0 = tf(freq=1.0), with freq of:
                  1.0 = termFreq=1.0
                4.7784038 = idf(docFreq=976, maxDocs=42740)
                0.0625 = fieldNorm(doc=3227)
          0.07519093 = weight(abstract_txt:lexicon in 3227) [ClassicSimilarity], result of:
            0.07519093 = score(doc=3227,freq=1.0), product of:
              0.1556131 = queryWeight, product of:
                2.0050359 = boost
                7.731065 = idf(docFreq=50, maxDocs=42740)
                0.010038867 = queryNorm
              0.48319155 = fieldWeight in 3227, product of:
                1.0 = tf(freq=1.0), with freq of:
                  1.0 = termFreq=1.0
                7.731065 = idf(docFreq=50, maxDocs=42740)
                0.0625 = fieldNorm(doc=3227)
          0.15373126 = weight(abstract_txt:polarity in 3227) [ClassicSimilarity], result of:
            0.15373126 = score(doc=3227,freq=1.0), product of:
              0.28695098 = queryWeight, product of:
                3.334637 = boost
                8.571848 = idf(docFreq=21, maxDocs=42740)
                0.010038867 = queryNorm
              0.5357405 = fieldWeight in 3227, product of:
                1.0 = tf(freq=1.0), with freq of:
                  1.0 = termFreq=1.0
                8.571848 = idf(docFreq=21, maxDocs=42740)
                0.0625 = fieldNorm(doc=3227)
          0.38839668 = weight(abstract_txt:lexicons in 3227) [ClassicSimilarity], result of:
            0.38839668 = score(doc=3227,freq=2.0), product of:
              0.50090593 = queryWeight, product of:
                5.6878376 = boost
                8.772519 = idf(docFreq=17, maxDocs=42740)
                0.010038867 = queryNorm
              0.7753885 = fieldWeight in 3227, product of:
                1.4142135 = tf(freq=2.0), with freq of:
                  2.0 = termFreq=2.0
                8.772519 = idf(docFreq=17, maxDocs=42740)
                0.0625 = fieldNorm(doc=3227)
          0.5731525 = weight(abstract_txt:sentiment in 3227) [ClassicSimilarity], result of:
            0.5731525 = score(doc=3227,freq=3.0), product of:
              0.6899427 = queryWeight, product of:
                8.955954 = boost
                7.6739063 = idf(docFreq=53, maxDocs=42740)
                0.010038867 = queryNorm
              0.8307247 = fieldWeight in 3227, product of:
                1.7320508 = tf(freq=3.0), with freq of:
                  3.0 = termFreq=3.0
                7.6739063 = idf(docFreq=53, maxDocs=42740)
                0.0625 = fieldNorm(doc=3227)
        0.36 = coord(9/25)
    
  2. Saif, H.; He, Y.; Fernandez, M.; Alani, H.: Contextual semantics for sentiment analysis of Twitter (2016) 0.46
    0.46309906 = sum of:
      0.46309906 = product of:
        1.6539252 = sum of:
          0.0044689793 = weight(abstract_txt:that in 4668) [ClassicSimilarity], result of:
            0.0044689793 = score(doc=4668,freq=1.0), product of:
              0.02985965 = queryWeight, product of:
                1.2420996 = boost
                2.3946586 = idf(docFreq=10595, maxDocs=42740)
                0.010038867 = queryNorm
              0.14966616 = fieldWeight in 4668, product of:
                1.0 = tf(freq=1.0), with freq of:
                  1.0 = termFreq=1.0
                2.3946586 = idf(docFreq=10595, maxDocs=42740)
                0.0625 = fieldNorm(doc=4668)
          0.0354061 = weight(abstract_txt:words in 4668) [ClassicSimilarity], result of:
            0.0354061 = score(doc=4668,freq=2.0), product of:
              0.07475574 = queryWeight, product of:
                1.389701 = boost
                5.358442 = idf(docFreq=546, maxDocs=42740)
                0.010038867 = queryNorm
              0.4736238 = fieldWeight in 4668, product of:
                1.4142135 = tf(freq=2.0), with freq of:
                  2.0 = termFreq=2.0
                5.358442 = idf(docFreq=546, maxDocs=42740)
                0.0625 = fieldNorm(doc=4668)
          0.026403695 = weight(abstract_txt:word in 4668) [ClassicSimilarity], result of:
            0.026403695 = score(doc=4668,freq=1.0), product of:
              0.07745432 = queryWeight, product of:
                1.4145617 = boost
                5.4543004 = idf(docFreq=496, maxDocs=42740)
                0.010038867 = queryNorm
              0.34089378 = fieldWeight in 4668, product of:
                1.0 = tf(freq=1.0), with freq of:
                  1.0 = termFreq=1.0
                5.4543004 = idf(docFreq=496, maxDocs=42740)
                0.0625 = fieldNorm(doc=4668)
          0.106336035 = weight(abstract_txt:lexicon in 4668) [ClassicSimilarity], result of:
            0.106336035 = score(doc=4668,freq=2.0), product of:
              0.1556131 = queryWeight, product of:
                2.0050359 = boost
                7.731065 = idf(docFreq=50, maxDocs=42740)
                0.010038867 = queryNorm
              0.683336 = fieldWeight in 4668, product of:
                1.4142135 = tf(freq=2.0), with freq of:
                  2.0 = termFreq=2.0
                7.731065 = idf(docFreq=50, maxDocs=42740)
                0.0625 = fieldNorm(doc=4668)
          0.21740882 = weight(abstract_txt:polarity in 4668) [ClassicSimilarity], result of:
            0.21740882 = score(doc=4668,freq=2.0), product of:
              0.28695098 = queryWeight, product of:
                3.334637 = boost
                8.571848 = idf(docFreq=21, maxDocs=42740)
                0.010038867 = queryNorm
              0.75765145 = fieldWeight in 4668, product of:
                1.4142135 = tf(freq=2.0), with freq of:
                  2.0 = termFreq=2.0
                8.571848 = idf(docFreq=21, maxDocs=42740)
                0.0625 = fieldNorm(doc=4668)
          0.38839668 = weight(abstract_txt:lexicons in 4668) [ClassicSimilarity], result of:
            0.38839668 = score(doc=4668,freq=2.0), product of:
              0.50090593 = queryWeight, product of:
                5.6878376 = boost
                8.772519 = idf(docFreq=17, maxDocs=42740)
                0.010038867 = queryNorm
              0.7753885 = fieldWeight in 4668, product of:
                1.4142135 = tf(freq=2.0), with freq of:
                  2.0 = termFreq=2.0
                8.772519 = idf(docFreq=17, maxDocs=42740)
                0.0625 = fieldNorm(doc=4668)
          0.87550485 = weight(abstract_txt:sentiment in 4668) [ClassicSimilarity], result of:
            0.87550485 = score(doc=4668,freq=7.0), product of:
              0.6899427 = queryWeight, product of:
                8.955954 = boost
                7.6739063 = idf(docFreq=53, maxDocs=42740)
                0.010038867 = queryNorm
              1.268953 = fieldWeight in 4668, product of:
                2.6457512 = tf(freq=7.0), with freq of:
                  7.0 = termFreq=7.0
                7.6739063 = idf(docFreq=53, maxDocs=42740)
                0.0625 = fieldNorm(doc=4668)
        0.28 = coord(7/25)
    
  3. Abdi, A.; Shamsuddin, S.M.; Aliguliyev, R.M.: QMOS: Query-based multi-documents opinion-oriented summarization (2018) 0.41
    0.41372335 = sum of:
      0.41372335 = product of:
        1.2928855 = sum of:
          0.00945888 = weight(abstract_txt:text in 1090) [ClassicSimilarity], result of:
            0.00945888 = score(doc=1090,freq=1.0), product of:
              0.042706136 = queryWeight, product of:
                1.0503746 = boost
                4.0500593 = idf(docFreq=2023, maxDocs=42740)
                0.010038867 = queryNorm
              0.22148761 = fieldWeight in 1090, product of:
                1.0 = tf(freq=1.0), with freq of:
                  1.0 = termFreq=1.0
                4.0500593 = idf(docFreq=2023, maxDocs=42740)
                0.0546875 = fieldNorm(doc=1090)
          0.014625686 = weight(abstract_txt:methods in 1090) [ClassicSimilarity], result of:
            0.014625686 = score(doc=1090,freq=2.0), product of:
              0.045324318 = queryWeight, product of:
                1.0820934 = boost
                4.172361 = idf(docFreq=1790, maxDocs=42740)
                0.010038867 = queryNorm
              0.3226896 = fieldWeight in 1090, product of:
                1.4142135 = tf(freq=2.0), with freq of:
                  2.0 = termFreq=2.0
                4.172361 = idf(docFreq=1790, maxDocs=42740)
                0.0546875 = fieldNorm(doc=1090)
          0.006772937 = weight(abstract_txt:that in 1090) [ClassicSimilarity], result of:
            0.006772937 = score(doc=1090,freq=3.0), product of:
              0.02985965 = queryWeight, product of:
                1.2420996 = boost
                2.3946586 = idf(docFreq=10595, maxDocs=42740)
                0.010038867 = queryNorm
              0.22682571 = fieldWeight in 1090, product of:
                1.7320508 = tf(freq=3.0), with freq of:
                  3.0 = termFreq=3.0
                2.3946586 = idf(docFreq=10595, maxDocs=42740)
                0.0546875 = fieldNorm(doc=1090)
          0.021906408 = weight(abstract_txt:words in 1090) [ClassicSimilarity], result of:
            0.021906408 = score(doc=1090,freq=1.0), product of:
              0.07475574 = queryWeight, product of:
                1.389701 = boost
                5.358442 = idf(docFreq=546, maxDocs=42740)
                0.010038867 = queryNorm
              0.2930398 = fieldWeight in 1090, product of:
                1.0 = tf(freq=1.0), with freq of:
                  1.0 = termFreq=1.0
                5.358442 = idf(docFreq=546, maxDocs=42740)
                0.0546875 = fieldNorm(doc=1090)
          0.05659114 = weight(abstract_txt:word in 1090) [ClassicSimilarity], result of:
            0.05659114 = score(doc=1090,freq=6.0), product of:
              0.07745432 = queryWeight, product of:
                1.4145617 = boost
                5.4543004 = idf(docFreq=496, maxDocs=42740)
                0.010038867 = queryNorm
              0.73063886 = fieldWeight in 1090, product of:
                2.4494898 = tf(freq=6.0), with freq of:
                  6.0 = termFreq=6.0
                5.4543004 = idf(docFreq=496, maxDocs=42740)
                0.0546875 = fieldNorm(doc=1090)
          0.13158414 = weight(abstract_txt:lexicon in 1090) [ClassicSimilarity], result of:
            0.13158414 = score(doc=1090,freq=4.0), product of:
              0.1556131 = queryWeight, product of:
                2.0050359 = boost
                7.731065 = idf(docFreq=50, maxDocs=42740)
                0.010038867 = queryNorm
              0.8455852 = fieldWeight in 1090, product of:
                2.0 = tf(freq=4.0), with freq of:
                  4.0 = termFreq=4.0
                7.731065 = idf(docFreq=50, maxDocs=42740)
                0.0546875 = fieldNorm(doc=1090)
          0.23298655 = weight(abstract_txt:polarity in 1090) [ClassicSimilarity], result of:
            0.23298655 = score(doc=1090,freq=3.0), product of:
              0.28695098 = queryWeight, product of:
                3.334637 = boost
                8.571848 = idf(docFreq=21, maxDocs=42740)
                0.010038867 = queryNorm
              0.8119385 = fieldWeight in 1090, product of:
                1.7320508 = tf(freq=3.0), with freq of:
                  3.0 = termFreq=3.0
                8.571848 = idf(docFreq=21, maxDocs=42740)
                0.0546875 = fieldNorm(doc=1090)
          0.81895983 = weight(abstract_txt:sentiment in 1090) [ClassicSimilarity], result of:
            0.81895983 = score(doc=1090,freq=8.0), product of:
              0.6899427 = queryWeight, product of:
                8.955954 = boost
                7.6739063 = idf(docFreq=53, maxDocs=42740)
                0.010038867 = queryNorm
              1.1869968 = fieldWeight in 1090, product of:
                2.828427 = tf(freq=8.0), with freq of:
                  8.0 = termFreq=8.0
                7.6739063 = idf(docFreq=53, maxDocs=42740)
                0.0546875 = fieldNorm(doc=1090)
        0.32 = coord(8/25)
    
  4. Thelwall, M.; Buckley, K.: Topic-based sentiment analysis for the social web : the role of mood and issue-related words (2013) 0.38
    0.3783264 = sum of:
      0.3783264 = product of:
        1.3511657 = sum of:
          0.013512687 = weight(abstract_txt:text in 3005) [ClassicSimilarity], result of:
            0.013512687 = score(doc=3005,freq=1.0), product of:
              0.042706136 = queryWeight, product of:
                1.0503746 = boost
                4.0500593 = idf(docFreq=2023, maxDocs=42740)
                0.010038867 = queryNorm
              0.3164109 = fieldWeight in 3005, product of:
                1.0 = tf(freq=1.0), with freq of:
                  1.0 = termFreq=1.0
                4.0500593 = idf(docFreq=2023, maxDocs=42740)
                0.078125 = fieldNorm(doc=3005)
          0.020893836 = weight(abstract_txt:methods in 3005) [ClassicSimilarity], result of:
            0.020893836 = score(doc=3005,freq=2.0), product of:
              0.045324318 = queryWeight, product of:
                1.0820934 = boost
                4.172361 = idf(docFreq=1790, maxDocs=42740)
                0.010038867 = queryNorm
              0.46098512 = fieldWeight in 3005, product of:
                1.4142135 = tf(freq=2.0), with freq of:
                  2.0 = termFreq=2.0
                4.172361 = idf(docFreq=1790, maxDocs=42740)
                0.078125 = fieldNorm(doc=3005)
          0.005586224 = weight(abstract_txt:that in 3005) [ClassicSimilarity], result of:
            0.005586224 = score(doc=3005,freq=1.0), product of:
              0.02985965 = queryWeight, product of:
                1.2420996 = boost
                2.3946586 = idf(docFreq=10595, maxDocs=42740)
                0.010038867 = queryNorm
              0.18708271 = fieldWeight in 3005, product of:
                1.0 = tf(freq=1.0), with freq of:
                  1.0 = termFreq=1.0
                2.3946586 = idf(docFreq=10595, maxDocs=42740)
                0.078125 = fieldNorm(doc=3005)
          0.031294867 = weight(abstract_txt:words in 3005) [ClassicSimilarity], result of:
            0.031294867 = score(doc=3005,freq=1.0), product of:
              0.07475574 = queryWeight, product of:
                1.389701 = boost
                5.358442 = idf(docFreq=546, maxDocs=42740)
                0.010038867 = queryNorm
              0.41862828 = fieldWeight in 3005, product of:
                1.0 = tf(freq=1.0), with freq of:
                  1.0 = termFreq=1.0
                5.358442 = idf(docFreq=546, maxDocs=42740)
                0.078125 = fieldNorm(doc=3005)
          0.16279313 = weight(abstract_txt:lexicon in 3005) [ClassicSimilarity], result of:
            0.16279313 = score(doc=3005,freq=3.0), product of:
              0.1556131 = queryWeight, product of:
                2.0050359 = boost
                7.731065 = idf(docFreq=50, maxDocs=42740)
                0.010038867 = queryNorm
              1.0461403 = fieldWeight in 3005, product of:
                1.7320508 = tf(freq=3.0), with freq of:
                  3.0 = termFreq=3.0
                7.731065 = idf(docFreq=50, maxDocs=42740)
                0.078125 = fieldNorm(doc=3005)
          0.19216406 = weight(abstract_txt:polarity in 3005) [ClassicSimilarity], result of:
            0.19216406 = score(doc=3005,freq=1.0), product of:
              0.28695098 = queryWeight, product of:
                3.334637 = boost
                8.571848 = idf(docFreq=21, maxDocs=42740)
                0.010038867 = queryNorm
              0.6696756 = fieldWeight in 3005, product of:
                1.0 = tf(freq=1.0), with freq of:
                  1.0 = termFreq=1.0
                8.571848 = idf(docFreq=21, maxDocs=42740)
                0.078125 = fieldNorm(doc=3005)
          0.92492086 = weight(abstract_txt:sentiment in 3005) [ClassicSimilarity], result of:
            0.92492086 = score(doc=3005,freq=5.0), product of:
              0.6899427 = queryWeight, product of:
                8.955954 = boost
                7.6739063 = idf(docFreq=53, maxDocs=42740)
                0.010038867 = queryNorm
              1.3405763 = fieldWeight in 3005, product of:
                2.236068 = tf(freq=5.0), with freq of:
                  5.0 = termFreq=5.0
                7.6739063 = idf(docFreq=53, maxDocs=42740)
                0.078125 = fieldNorm(doc=3005)
        0.28 = coord(7/25)
    
  5. Yu, N.: Exploring co-training strategies for opinion detection (2014) 0.26
    0.26495686 = sum of:
      0.26495686 = product of:
        1.103987 = sum of:
          0.011819338 = weight(abstract_txt:methods in 3504) [ClassicSimilarity], result of:
            0.011819338 = score(doc=3504,freq=1.0), product of:
              0.045324318 = queryWeight, product of:
                1.0820934 = boost
                4.172361 = idf(docFreq=1790, maxDocs=42740)
                0.010038867 = queryNorm
              0.26077256 = fieldWeight in 3504, product of:
                1.0 = tf(freq=1.0), with freq of:
                  1.0 = termFreq=1.0
                4.172361 = idf(docFreq=1790, maxDocs=42740)
                0.0625 = fieldNorm(doc=3504)
          0.006320091 = weight(abstract_txt:that in 3504) [ClassicSimilarity], result of:
            0.006320091 = score(doc=3504,freq=2.0), product of:
              0.02985965 = queryWeight, product of:
                1.2420996 = boost
                2.3946586 = idf(docFreq=10595, maxDocs=42740)
                0.010038867 = queryNorm
              0.21165991 = fieldWeight in 3504, product of:
                1.4142135 = tf(freq=2.0), with freq of:
                  2.0 = termFreq=2.0
                2.3946586 = idf(docFreq=10595, maxDocs=42740)
                0.0625 = fieldNorm(doc=3504)
          0.031315625 = weight(abstract_txt:learning in 3504) [ClassicSimilarity], result of:
            0.031315625 = score(doc=3504,freq=3.0), product of:
              0.06017316 = queryWeight, product of:
                1.2468107 = boost
                4.807482 = idf(docFreq=948, maxDocs=42740)
                0.010038867 = queryNorm
              0.52042514 = fieldWeight in 3504, product of:
                1.7320508 = tf(freq=3.0), with freq of:
                  3.0 = termFreq=3.0
                4.807482 = idf(docFreq=948, maxDocs=42740)
                0.0625 = fieldNorm(doc=3504)
          0.07519093 = weight(abstract_txt:lexicon in 3504) [ClassicSimilarity], result of:
            0.07519093 = score(doc=3504,freq=1.0), product of:
              0.1556131 = queryWeight, product of:
                2.0050359 = boost
                7.731065 = idf(docFreq=50, maxDocs=42740)
                0.010038867 = queryNorm
              0.48319155 = fieldWeight in 3504, product of:
                1.0 = tf(freq=1.0), with freq of:
                  1.0 = termFreq=1.0
                7.731065 = idf(docFreq=50, maxDocs=42740)
                0.0625 = fieldNorm(doc=3504)
          0.04338691 = weight(abstract_txt:domains in 3504) [ClassicSimilarity], result of:
            0.04338691 = score(doc=3504,freq=1.0), product of:
              0.12346354 = queryWeight, product of:
                2.1873288 = boost
                5.622636 = idf(docFreq=419, maxDocs=42740)
                0.010038867 = queryNorm
              0.35141474 = fieldWeight in 3504, product of:
                1.0 = tf(freq=1.0), with freq of:
                  1.0 = termFreq=1.0
                5.622636 = idf(docFreq=419, maxDocs=42740)
                0.0625 = fieldNorm(doc=3504)
          0.93595403 = weight(abstract_txt:sentiment in 3504) [ClassicSimilarity], result of:
            0.93595403 = score(doc=3504,freq=8.0), product of:
              0.6899427 = queryWeight, product of:
                8.955954 = boost
                7.6739063 = idf(docFreq=53, maxDocs=42740)
                0.010038867 = queryNorm
              1.3565677 = fieldWeight in 3504, product of:
                2.828427 = tf(freq=8.0), with freq of:
                  8.0 = termFreq=8.0
                7.6739063 = idf(docFreq=53, maxDocs=42740)
                0.0625 = fieldNorm(doc=3504)
        0.24 = coord(6/25)