Document (#43394)

Author

Xiang, R.
Chersoni, E.
Lu, Q.
Huang, C.-R.
Li, W.
Long, Y.

Title

Lexical data augmentation for sentiment analysis

Source

Journal of the Association for Information Science and Technology. 72(2021) no.11, S.1432-1447

Year

2021

Abstract

Machine learning methods, especially deep learning models, have achieved impressive performance in various natural language processing tasks including sentiment analysis. However, deep learning models are more demanding for training data. Data augmentation techniques are widely used to generate new instances based on modifications to existing data or relying on external knowledge bases to address annotated data scarcity, which hinders the full potential of machine learning techniques. This paper presents our work using part-of-speech (POS) focused lexical substitution for data augmentation (PLSDA) to enhance the performance of machine learning algorithms in sentiment analysis. We exploit POS information to identify words to be replaced and investigate different augmentation strategies to find semantically related substitutions when generating new instances. The choice of POS tags as well as a variety of strategies such as semantic-based substitution methods and sampling methods are discussed in detail. Performance evaluation focuses on the comparison between PLSDA and two previous lexical substitution-based data augmentation methods, one of which is thesaurus-based, and the other is lexicon manipulation based. Our approach is tested on five English sentiment analysis benchmarks: SST-2, MR, IMDB, Twitter, and AirRecord. Hyperparameters such as the candidate similarity threshold and number of newly generated instances are optimized. Results show that six classifiers (SVM, LSTM, BiLSTM-AT, bidirectional encoder representations from transformers [BERT], XLNet, and RoBERTa) trained with PLSDA achieve accuracy improvement of more than 0.6% comparing to two previous lexical substitution methods averaged on five benchmarks. Introducing POS constraint and well-designed augmentation strategies can improve the reliability of lexical data augmentation methods. Consequently, PLSDA significantly improves the performance of sentiment analysis algorithms.

Content

Vgl.: https://asistdl.onlinelibrary.wiley.com/doi/10.1002/asi.24493.

Theme

Computerlinguistik

Similar documents (author)

1. Long, C.A.: Making information available to partially sighted and blind clients (1993) 2.46

   2.462272 = sum of:
     2.462272 = product of:
       4.924544 = sum of:
         4.924544 = weight(author_txt:long in 7029) [ClassicSimilarity], result of:
           4.924544 = score(doc=7029,freq=1.0), product of:
             0.85490346 = queryWeight, product of:
               1.2837011 = boost
               9.216561 = idf(docFreq=11, maxDocs=44421)
               0.07225772 = queryNorm
             5.7603507 = fieldWeight in 7029, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               9.216561 = idf(docFreq=11, maxDocs=44421)
               0.625 = fieldNorm(doc=7029)
       0.5 = coord(1/2)
   

2. Long, C.E.: ¬The Internet's value to catalogers : results of a survey (1997) 2.46

   2.462272 = sum of:
     2.462272 = product of:
       4.924544 = sum of:
         4.924544 = weight(author_txt:long in 494) [ClassicSimilarity], result of:
           4.924544 = score(doc=494,freq=1.0), product of:
             0.85490346 = queryWeight, product of:
               1.2837011 = boost
               9.216561 = idf(docFreq=11, maxDocs=44421)
               0.07225772 = queryNorm
             5.7603507 = fieldWeight in 494, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               9.216561 = idf(docFreq=11, maxDocs=44421)
               0.625 = fieldNorm(doc=494)
       0.5 = coord(1/2)
   

3. Long, C.E.: Improving subject searching in Web-based OPACs : evaluation of the problem and guidelines for design (2000) 2.46

   2.462272 = sum of:
     2.462272 = product of:
       4.924544 = sum of:
         4.924544 = weight(author_txt:long in 110) [ClassicSimilarity], result of:
           4.924544 = score(doc=110,freq=1.0), product of:
             0.85490346 = queryWeight, product of:
               1.2837011 = boost
               9.216561 = idf(docFreq=11, maxDocs=44421)
               0.07225772 = queryNorm
             5.7603507 = fieldWeight in 110, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               9.216561 = idf(docFreq=11, maxDocs=44421)
               0.625 = fieldNorm(doc=110)
       0.5 = coord(1/2)
   

4. Long, J.: Google hacking (2005) 2.46

   2.462272 = sum of:
     2.462272 = product of:
       4.924544 = sum of:
         4.924544 = weight(author_txt:long in 5551) [ClassicSimilarity], result of:
           4.924544 = score(doc=5551,freq=1.0), product of:
             0.85490346 = queryWeight, product of:
               1.2837011 = boost
               9.216561 = idf(docFreq=11, maxDocs=44421)
               0.07225772 = queryNorm
             5.7603507 = fieldWeight in 5551, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               9.216561 = idf(docFreq=11, maxDocs=44421)
               0.625 = fieldNorm(doc=5551)
       0.5 = coord(1/2)
   

5. Long, J.: Google hacking (2008) 2.46

   2.462272 = sum of:
     2.462272 = product of:
       4.924544 = sum of:
         4.924544 = weight(author_txt:long in 3925) [ClassicSimilarity], result of:
           4.924544 = score(doc=3925,freq=1.0), product of:
             0.85490346 = queryWeight, product of:
               1.2837011 = boost
               9.216561 = idf(docFreq=11, maxDocs=44421)
               0.07225772 = queryNorm
             5.7603507 = fieldWeight in 3925, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               9.216561 = idf(docFreq=11, maxDocs=44421)
               0.625 = fieldNorm(doc=3925)
       0.5 = coord(1/2)
   

Similar documents (content)

1. Yu, N.: Exploring co-training strategies for opinion detection (2014) 0.31

   0.31246644 = sum of:
     0.31246644 = product of:
       0.7811661 = sum of:
         0.020593645 = weight(abstract_txt:previous in 2503) [ClassicSimilarity], result of:
           0.020593645 = score(doc=2503,freq=1.0), product of:
             0.06316061 = queryWeight, product of:
               1.1320561 = boost
               5.216832 = idf(docFreq=654, maxDocs=44421)
               0.010694771 = queryNorm
             0.326052 = fieldWeight in 2503, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               5.216832 = idf(docFreq=654, maxDocs=44421)
               0.0625 = fieldNorm(doc=2503)
         0.026862673 = weight(abstract_txt:algorithms in 2503) [ClassicSimilarity], result of:
           0.026862673 = score(doc=2503,freq=1.0), product of:
             0.075403295 = queryWeight, product of:
               1.2369152 = boost
               5.7000527 = idf(docFreq=403, maxDocs=44421)
               0.010694771 = queryNorm
             0.3562533 = fieldWeight in 2503, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               5.7000527 = idf(docFreq=403, maxDocs=44421)
               0.0625 = fieldNorm(doc=2503)
         0.04115097 = weight(abstract_txt:strategies in 2503) [ClassicSimilarity], result of:
           0.04115097 = score(doc=2503,freq=2.0), product of:
             0.0910398 = queryWeight, product of:
               1.6645854 = boost
               5.113918 = idf(docFreq=725, maxDocs=44421)
               0.010694771 = queryNorm
             0.45201075 = fieldWeight in 2503, product of:
               1.4142135 = tf(freq=2.0), with freq of:
                 2.0 = termFreq=2.0
               5.113918 = idf(docFreq=725, maxDocs=44421)
               0.0625 = fieldNorm(doc=2503)
         0.045162827 = weight(abstract_txt:machine in 2503) [ClassicSimilarity], result of:
           0.045162827 = score(doc=2503,freq=2.0), product of:
             0.096864656 = queryWeight, product of:
               1.7170111 = boost
               5.274979 = idf(docFreq=617, maxDocs=44421)
               0.010694771 = queryNorm
             0.4662467 = fieldWeight in 2503, product of:
               1.4142135 = tf(freq=2.0), with freq of:
                 2.0 = termFreq=2.0
               5.274979 = idf(docFreq=617, maxDocs=44421)
               0.0625 = fieldNorm(doc=2503)
         0.01653896 = weight(abstract_txt:based in 2503) [ClassicSimilarity], result of:
           0.01653896 = score(doc=2503,freq=2.0), product of:
             0.058784977 = queryWeight, product of:
               1.7268236 = boost
               3.1830752 = idf(docFreq=5005, maxDocs=44421)
               0.010694771 = queryNorm
             0.28134674 = fieldWeight in 2503, product of:
               1.4142135 = tf(freq=2.0), with freq of:
                 2.0 = termFreq=2.0
               3.1830752 = idf(docFreq=5005, maxDocs=44421)
               0.0625 = fieldNorm(doc=2503)
         0.043038998 = weight(abstract_txt:analysis in 2503) [ClassicSimilarity], result of:
           0.043038998 = score(doc=2503,freq=6.0), product of:
             0.07711317 = queryWeight, product of:
               1.977785 = boost
               3.6456752 = idf(docFreq=3151, maxDocs=44421)
               0.010694771 = queryNorm
             0.55812776 = fieldWeight in 2503, product of:
               2.4494898 = tf(freq=6.0), with freq of:
                 6.0 = termFreq=6.0
               3.6456752 = idf(docFreq=3151, maxDocs=44421)
               0.0625 = fieldNorm(doc=2503)
         0.066975646 = weight(abstract_txt:learning in 2503) [ClassicSimilarity], result of:
           0.066975646 = score(doc=2503,freq=3.0), product of:
             0.1304693 = queryWeight, product of:
               2.5725806 = boost
               4.7420692 = idf(docFreq=1052, maxDocs=44421)
               0.010694771 = queryNorm
             0.51334405 = fieldWeight in 2503, product of:
               1.7320508 = tf(freq=3.0), with freq of:
                 3.0 = termFreq=3.0
               4.7420692 = idf(docFreq=1052, maxDocs=44421)
               0.0625 = fieldNorm(doc=2503)
         0.03095475 = weight(abstract_txt:methods in 2503) [ClassicSimilarity], result of:
           0.03095475 = score(doc=2503,freq=1.0), product of:
             0.119531624 = queryWeight, product of:
               2.6974092 = boost
               4.1434727 = idf(docFreq=1915, maxDocs=44421)
               0.010694771 = queryNorm
             0.25896704 = fieldWeight in 2503, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               4.1434727 = idf(docFreq=1915, maxDocs=44421)
               0.0625 = fieldNorm(doc=2503)
         0.0524891 = weight(abstract_txt:data in 2503) [ClassicSimilarity], result of:
           0.0524891 = score(doc=2503,freq=6.0), product of:
             0.102953196 = queryWeight, product of:
               2.8906446 = boost
               3.3302255 = idf(docFreq=4320, maxDocs=44421)
               0.010694771 = queryNorm
             0.5098346 = fieldWeight in 2503, product of:
               2.4494898 = tf(freq=6.0), with freq of:
                 6.0 = termFreq=6.0
               3.3302255 = idf(docFreq=4320, maxDocs=44421)
               0.0625 = fieldNorm(doc=2503)
         0.4373985 = weight(abstract_txt:sentiment in 2503) [ClassicSimilarity], result of:
           0.4373985 = score(doc=2503,freq=8.0), product of:
             0.32871968 = queryWeight, product of:
               4.0834537 = boost
               7.5270805 = idf(docFreq=64, maxDocs=44421)
               0.010694771 = queryNorm
             1.3306124 = fieldWeight in 2503, product of:
               2.828427 = tf(freq=8.0), with freq of:
                 8.0 = termFreq=8.0
               7.5270805 = idf(docFreq=64, maxDocs=44421)
               0.0625 = fieldNorm(doc=2503)
       0.4 = coord(10/25)
   

2. Thelwall, M.; Buckley, K.: Topic-based sentiment analysis for the social web : the role of mood and issue-related words (2013) 0.21

   0.21237607 = sum of:
     0.21237607 = product of:
       0.758486 = sum of:
         0.03357834 = weight(abstract_txt:algorithms in 2004) [ClassicSimilarity], result of:
           0.03357834 = score(doc=2004,freq=1.0), product of:
             0.075403295 = queryWeight, product of:
               1.2369152 = boost
               5.7000527 = idf(docFreq=403, maxDocs=44421)
               0.010694771 = queryNorm
             0.4453166 = fieldWeight in 2004, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               5.7000527 = idf(docFreq=403, maxDocs=44421)
               0.078125 = fieldNorm(doc=2004)
         0.03804146 = weight(abstract_txt:analysis in 2004) [ClassicSimilarity], result of:
           0.03804146 = score(doc=2004,freq=3.0), product of:
             0.07711317 = queryWeight, product of:
               1.977785 = boost
               3.6456752 = idf(docFreq=3151, maxDocs=44421)
               0.010694771 = queryNorm
             0.4933199 = fieldWeight in 2004, product of:
               1.7320508 = tf(freq=3.0), with freq of:
                 3.0 = termFreq=3.0
               3.6456752 = idf(docFreq=3151, maxDocs=44421)
               0.078125 = fieldNorm(doc=2004)
         0.035752844 = weight(abstract_txt:performance in 2004) [ClassicSimilarity], result of:
           0.035752844 = score(doc=2004,freq=1.0), product of:
             0.09906066 = queryWeight, product of:
               2.0049818 = boost
               4.619759 = idf(docFreq=1189, maxDocs=44421)
               0.010694771 = queryNorm
             0.36091867 = fieldWeight in 2004, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               4.619759 = idf(docFreq=1189, maxDocs=44421)
               0.078125 = fieldNorm(doc=2004)
         0.05472078 = weight(abstract_txt:methods in 2004) [ClassicSimilarity], result of:
           0.05472078 = score(doc=2004,freq=2.0), product of:
             0.119531624 = queryWeight, product of:
               2.6974092 = boost
               4.1434727 = idf(docFreq=1915, maxDocs=44421)
               0.010694771 = queryNorm
             0.45779335 = fieldWeight in 2004, product of:
               1.4142135 = tf(freq=2.0), with freq of:
                 2.0 = termFreq=2.0
               4.1434727 = idf(docFreq=1915, maxDocs=44421)
               0.078125 = fieldNorm(doc=2004)
         0.037880745 = weight(abstract_txt:data in 2004) [ClassicSimilarity], result of:
           0.037880745 = score(doc=2004,freq=2.0), product of:
             0.102953196 = queryWeight, product of:
               2.8906446 = boost
               3.3302255 = idf(docFreq=4320, maxDocs=44421)
               0.010694771 = queryNorm
             0.3679414 = fieldWeight in 2004, product of:
               1.4142135 = tf(freq=2.0), with freq of:
                 2.0 = termFreq=2.0
               3.3302255 = idf(docFreq=4320, maxDocs=44421)
               0.078125 = fieldNorm(doc=2004)
         0.12626947 = weight(abstract_txt:lexical in 2004) [ClassicSimilarity], result of:
           0.12626947 = score(doc=2004,freq=1.0), product of:
             0.2474741 = queryWeight, product of:
               3.5430696 = boost
               6.5309834 = idf(docFreq=175, maxDocs=44421)
               0.010694771 = queryNorm
             0.5102331 = fieldWeight in 2004, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               6.5309834 = idf(docFreq=175, maxDocs=44421)
               0.078125 = fieldNorm(doc=2004)
         0.43224233 = weight(abstract_txt:sentiment in 2004) [ClassicSimilarity], result of:
           0.43224233 = score(doc=2004,freq=5.0), product of:
             0.32871968 = queryWeight, product of:
               4.0834537 = boost
               7.5270805 = idf(docFreq=64, maxDocs=44421)
               0.010694771 = queryNorm
             1.3149269 = fieldWeight in 2004, product of:
               2.236068 = tf(freq=5.0), with freq of:
                 5.0 = termFreq=5.0
               7.5270805 = idf(docFreq=64, maxDocs=44421)
               0.078125 = fieldNorm(doc=2004)
       0.28 = coord(7/25)
   

3. Zhang, L.; Wang, S.; Liu, B.: Deep learning for sentiment analysis : a survey (2018) 0.20

   0.19578435 = sum of:
     0.19578435 = product of:
       0.8157681 = sum of:
         0.14485916 = weight(abstract_txt:deep in 92) [ClassicSimilarity], result of:
           0.14485916 = score(doc=92,freq=4.0), product of:
             0.10058722 = queryWeight, product of:
               1.4286182 = boost
               6.5834737 = idf(docFreq=166, maxDocs=44421)
               0.010694771 = queryNorm
             1.4401349 = fieldWeight in 92, product of:
               2.0 = tf(freq=4.0), with freq of:
                 4.0 = termFreq=4.0
               6.5834737 = idf(docFreq=166, maxDocs=44421)
               0.109375 = fieldNorm(doc=92)
         0.055886146 = weight(abstract_txt:machine in 92) [ClassicSimilarity], result of:
           0.055886146 = score(doc=92,freq=1.0), product of:
             0.096864656 = queryWeight, product of:
               1.7170111 = boost
               5.274979 = idf(docFreq=617, maxDocs=44421)
               0.010694771 = queryNorm
             0.57695085 = fieldWeight in 92, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               5.274979 = idf(docFreq=617, maxDocs=44421)
               0.109375 = fieldNorm(doc=92)
         0.043485012 = weight(abstract_txt:analysis in 92) [ClassicSimilarity], result of:
           0.043485012 = score(doc=92,freq=2.0), product of:
             0.07711317 = queryWeight, product of:
               1.977785 = boost
               3.6456752 = idf(docFreq=3151, maxDocs=44421)
               0.010694771 = queryNorm
             0.5639116 = fieldWeight in 92, product of:
               1.4142135 = tf(freq=2.0), with freq of:
                 2.0 = termFreq=2.0
               3.6456752 = idf(docFreq=3151, maxDocs=44421)
               0.109375 = fieldNorm(doc=92)
         0.15131406 = weight(abstract_txt:learning in 92) [ClassicSimilarity], result of:
           0.15131406 = score(doc=92,freq=5.0), product of:
             0.1304693 = queryWeight, product of:
               2.5725806 = boost
               4.7420692 = idf(docFreq=1052, maxDocs=44421)
               0.010694771 = queryNorm
             1.1597675 = fieldWeight in 92, product of:
               2.236068 = tf(freq=5.0), with freq of:
                 5.0 = termFreq=5.0
               4.7420692 = idf(docFreq=1052, maxDocs=44421)
               0.109375 = fieldNorm(doc=92)
         0.037500024 = weight(abstract_txt:data in 92) [ClassicSimilarity], result of:
           0.037500024 = score(doc=92,freq=1.0), product of:
             0.102953196 = queryWeight, product of:
               2.8906446 = boost
               3.3302255 = idf(docFreq=4320, maxDocs=44421)
               0.010694771 = queryNorm
             0.36424342 = fieldWeight in 92, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               3.3302255 = idf(docFreq=4320, maxDocs=44421)
               0.109375 = fieldNorm(doc=92)
         0.3827237 = weight(abstract_txt:sentiment in 92) [ClassicSimilarity], result of:
           0.3827237 = score(doc=92,freq=2.0), product of:
             0.32871968 = queryWeight, product of:
               4.0834537 = boost
               7.5270805 = idf(docFreq=64, maxDocs=44421)
               0.010694771 = queryNorm
             1.1642859 = fieldWeight in 92, product of:
               1.4142135 = tf(freq=2.0), with freq of:
                 2.0 = termFreq=2.0
               7.5270805 = idf(docFreq=64, maxDocs=44421)
               0.109375 = fieldNorm(doc=92)
       0.24 = coord(6/25)
   

4. Wang, Z.; He, H.; Xu, G.; Ren, M.: Will sentiment analysis need subculture? : a new data augmentation approach (2024) 0.18

   0.18217461 = sum of:
     0.18217461 = product of:
       0.91087306 = sum of:
         0.014618515 = weight(abstract_txt:based in 2297) [ClassicSimilarity], result of:
           0.014618515 = score(doc=2297,freq=1.0), product of:
             0.058784977 = queryWeight, product of:
               1.7268236 = boost
               3.1830752 = idf(docFreq=5005, maxDocs=44421)
               0.010694771 = queryNorm
             0.24867775 = fieldWeight in 2297, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               3.1830752 = idf(docFreq=5005, maxDocs=44421)
               0.078125 = fieldNorm(doc=2297)
         0.031060722 = weight(abstract_txt:analysis in 2297) [ClassicSimilarity], result of:
           0.031060722 = score(doc=2297,freq=2.0), product of:
             0.07711317 = queryWeight, product of:
               1.977785 = boost
               3.6456752 = idf(docFreq=3151, maxDocs=44421)
               0.010694771 = queryNorm
             0.402794 = fieldWeight in 2297, product of:
               1.4142135 = tf(freq=2.0), with freq of:
                 2.0 = termFreq=2.0
               3.6456752 = idf(docFreq=3151, maxDocs=44421)
               0.078125 = fieldNorm(doc=2297)
         0.046394248 = weight(abstract_txt:data in 2297) [ClassicSimilarity], result of:
           0.046394248 = score(doc=2297,freq=3.0), product of:
             0.102953196 = queryWeight, product of:
               2.8906446 = boost
               3.3302255 = idf(docFreq=4320, maxDocs=44421)
               0.010694771 = queryNorm
             0.45063436 = fieldWeight in 2297, product of:
               1.7320508 = tf(freq=3.0), with freq of:
                 3.0 = termFreq=3.0
               3.3302255 = idf(docFreq=4320, maxDocs=44421)
               0.078125 = fieldNorm(doc=2297)
         0.33481348 = weight(abstract_txt:sentiment in 2297) [ClassicSimilarity], result of:
           0.33481348 = score(doc=2297,freq=3.0), product of:
             0.32871968 = queryWeight, product of:
               4.0834537 = boost
               7.5270805 = idf(docFreq=64, maxDocs=44421)
               0.010694771 = queryNorm
             1.018538 = fieldWeight in 2297, product of:
               1.7320508 = tf(freq=3.0), with freq of:
                 3.0 = termFreq=3.0
               7.5270805 = idf(docFreq=64, maxDocs=44421)
               0.078125 = fieldNorm(doc=2297)
         0.48398605 = weight(abstract_txt:augmentation in 2297) [ClassicSimilarity], result of:
           0.48398605 = score(doc=2297,freq=1.0), product of:
             0.6780505 = queryWeight, product of:
               6.939207 = boost
               9.1365185 = idf(docFreq=12, maxDocs=44421)
               0.010694771 = queryNorm
             0.71379054 = fieldWeight in 2297, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               9.1365185 = idf(docFreq=12, maxDocs=44421)
               0.078125 = fieldNorm(doc=2297)
       0.2 = coord(5/25)
   

5. Abdi, A.; Shamsuddin, S.M.; Aliguliyev, R.M.: QMOS: Query-based multi-documents opinion-oriented summarization (2018) 0.17

   0.17209479 = sum of:
     0.17209479 = product of:
       0.61462426 = sum of:
         0.025460862 = weight(abstract_txt:strategies in 89) [ClassicSimilarity], result of:
           0.025460862 = score(doc=89,freq=1.0), product of:
             0.0910398 = queryWeight, product of:
               1.6645854 = boost
               5.113918 = idf(docFreq=725, maxDocs=44421)
               0.010694771 = queryNorm
             0.27966738 = fieldWeight in 89, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               5.113918 = idf(docFreq=725, maxDocs=44421)
               0.0546875 = fieldNorm(doc=89)
         0.017724007 = weight(abstract_txt:based in 89) [ClassicSimilarity], result of:
           0.017724007 = score(doc=89,freq=3.0), product of:
             0.058784977 = queryWeight, product of:
               1.7268236 = boost
               3.1830752 = idf(docFreq=5005, maxDocs=44421)
               0.010694771 = queryNorm
             0.30150574 = fieldWeight in 89, product of:
               1.7320508 = tf(freq=3.0), with freq of:
                 3.0 = termFreq=3.0
               3.1830752 = idf(docFreq=5005, maxDocs=44421)
               0.0546875 = fieldNorm(doc=89)
         0.026629021 = weight(abstract_txt:analysis in 89) [ClassicSimilarity], result of:
           0.026629021 = score(doc=89,freq=3.0), product of:
             0.07711317 = queryWeight, product of:
               1.977785 = boost
               3.6456752 = idf(docFreq=3151, maxDocs=44421)
               0.010694771 = queryNorm
             0.34532392 = fieldWeight in 89, product of:
               1.7320508 = tf(freq=3.0), with freq of:
                 3.0 = termFreq=3.0
               3.6456752 = idf(docFreq=3151, maxDocs=44421)
               0.0546875 = fieldNorm(doc=89)
         0.035393506 = weight(abstract_txt:performance in 89) [ClassicSimilarity], result of:
           0.035393506 = score(doc=89,freq=2.0), product of:
             0.09906066 = queryWeight, product of:
               2.0049818 = boost
               4.619759 = idf(docFreq=1189, maxDocs=44421)
               0.010694771 = queryNorm
             0.35729125 = fieldWeight in 89, product of:
               1.4142135 = tf(freq=2.0), with freq of:
                 2.0 = termFreq=2.0
               4.619759 = idf(docFreq=1189, maxDocs=44421)
               0.0546875 = fieldNorm(doc=89)
         0.03830455 = weight(abstract_txt:methods in 89) [ClassicSimilarity], result of:
           0.03830455 = score(doc=89,freq=2.0), product of:
             0.119531624 = queryWeight, product of:
               2.6974092 = boost
               4.1434727 = idf(docFreq=1915, maxDocs=44421)
               0.010694771 = queryNorm
             0.32045534 = fieldWeight in 89, product of:
               1.4142135 = tf(freq=2.0), with freq of:
                 2.0 = termFreq=2.0
               4.1434727 = idf(docFreq=1915, maxDocs=44421)
               0.0546875 = fieldNorm(doc=89)
         0.08838864 = weight(abstract_txt:lexical in 89) [ClassicSimilarity], result of:
           0.08838864 = score(doc=89,freq=1.0), product of:
             0.2474741 = queryWeight, product of:
               3.5430696 = boost
               6.5309834 = idf(docFreq=175, maxDocs=44421)
               0.010694771 = queryNorm
             0.35716316 = fieldWeight in 89, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               6.5309834 = idf(docFreq=175, maxDocs=44421)
               0.0546875 = fieldNorm(doc=89)
         0.3827237 = weight(abstract_txt:sentiment in 89) [ClassicSimilarity], result of:
           0.3827237 = score(doc=89,freq=8.0), product of:
             0.32871968 = queryWeight, product of:
               4.0834537 = boost
               7.5270805 = idf(docFreq=64, maxDocs=44421)
               0.010694771 = queryNorm
             1.1642859 = fieldWeight in 89, product of:
               2.828427 = tf(freq=8.0), with freq of:
                 8.0 = termFreq=8.0
               7.5270805 = idf(docFreq=64, maxDocs=44421)
               0.0546875 = fieldNorm(doc=89)
       0.28 = coord(7/25)