Document (#44021)

Author
Liu, J.
Zhou, Z.
Gao, M.
Tang, J.
Fan, W.
Title
Aspect sentiment mining of short bullet screen comments from online TV series
Source
Journal of the Association for Information Science and Technology. 74(2023) no.8, S.1026-1045
Year
2023
Abstract
Bullet screen comments (BSCs) are user-generated short comments that appear as real-time overlays on many video platforms, expressing the audience opinions and emotions about different aspects of the ongoing video. Unlike traditional long comments after a show, BSCs are often incomplete, ambiguous in context, and correlated over time. Current studies in sentiment analysis of BSCs rarely address these challenges, motivating us to develop an aspect-level sentiment analysis framework. Our framework, BSCNET, is a pre-trained language encoder-based deep neural classifier designed to enhance semantic understanding. A novel neighbor context construction method is proposed to uncover latent contextual correlation among BSCs over time, and we also incorporate semi-supervised learning to reduce labeling costs. The framework increases F1 (Macro) and accuracy by up to 10% and 10.2%, respectively. Additionally, we have developed two novel downstream tasks. The first is noisy BSCs identification, which reached F1 (Macro) and accuracy of 90.1% and 98.3%, respectively, through fine-tuning the BSCNET. The second is the prediction of future episode popularity, where the MAPE is reduced by 11%-19.0% when incorporating sentiment features. Overall, this study provides a methodology reference for aspect-level sentiment analysis of BSCs and highlights its potential for viewing experience or forthcoming content optimization.
Content
Vgl.: https://asistdl.onlinelibrary.wiley.com/doi/10.1002/asi.24800.

Similar documents (author)

  1. Zhou, Z.; Jin, X.-L.; Hsu, C.; Tang, Z.: User empowerment and well-being with mHealth apps during pandemics : a mix-methods investigation in China (2023) 3.48
    3.4819572 = sum of:
      3.4819572 = sum of:
        1.668674 = weight(author_txt:zhou in 2092) [ClassicSimilarity], result of:
          1.668674 = score(doc=2092,freq=1.0), product of:
            0.6872591 = queryWeight, product of:
              7.769642 = idf(docFreq=50, maxDocs=44421)
              0.08845441 = queryNorm
            2.428013 = fieldWeight in 2092, product of:
              1.0 = tf(freq=1.0), with freq of:
                1.0 = termFreq=1.0
              7.769642 = idf(docFreq=50, maxDocs=44421)
              0.3125 = fieldNorm(doc=2092)
        1.8132832 = weight(author_txt:tang in 2092) [ClassicSimilarity], result of:
          1.8132832 = score(doc=2092,freq=1.0), product of:
            0.7264124 = queryWeight, product of:
              1.0280906 = boost
              7.9878955 = idf(docFreq=40, maxDocs=44421)
              0.08845441 = queryNorm
            2.4962173 = fieldWeight in 2092, product of:
              1.0 = tf(freq=1.0), with freq of:
                1.0 = termFreq=1.0
              7.9878955 = idf(docFreq=40, maxDocs=44421)
              0.3125 = fieldNorm(doc=2092)
    
  2. Zhou, L.: Characteristics of material organization and classification in the Kinsey Institute Library (2003) 1.67
    1.668674 = sum of:
      1.668674 = product of:
        3.337348 = sum of:
          3.337348 = weight(author_txt:zhou in 639) [ClassicSimilarity], result of:
            3.337348 = score(doc=639,freq=1.0), product of:
              0.6872591 = queryWeight, product of:
                7.769642 = idf(docFreq=50, maxDocs=44421)
                0.08845441 = queryNorm
              4.856026 = fieldWeight in 639, product of:
                1.0 = tf(freq=1.0), with freq of:
                  1.0 = termFreq=1.0
                7.769642 = idf(docFreq=50, maxDocs=44421)
                0.625 = fieldNorm(doc=639)
        0.5 = coord(1/2)
    
  3. Tang, R.; Solomon, P.: Toward an understanding of the dynamics of relevance judgement : an analysis of one person's search behavior (1998) 1.45
    1.4506266 = sum of:
      1.4506266 = product of:
        2.9012532 = sum of:
          2.9012532 = weight(author_txt:tang in 4268) [ClassicSimilarity], result of:
            2.9012532 = score(doc=4268,freq=1.0), product of:
              0.7264124 = queryWeight, product of:
                1.0280906 = boost
                7.9878955 = idf(docFreq=40, maxDocs=44421)
                0.08845441 = queryNorm
              3.9939477 = fieldWeight in 4268, product of:
                1.0 = tf(freq=1.0), with freq of:
                  1.0 = termFreq=1.0
                7.9878955 = idf(docFreq=40, maxDocs=44421)
                0.5 = fieldNorm(doc=4268)
        0.5 = coord(1/2)
    
  4. Tang, R.; Solomon, P.: Use of relevance criteria across stages of document evaluation : on the complementarity of experimental and naturalistic studies (2001) 1.45
    1.4506266 = sum of:
      1.4506266 = product of:
        2.9012532 = sum of:
          2.9012532 = weight(author_txt:tang in 213) [ClassicSimilarity], result of:
            2.9012532 = score(doc=213,freq=1.0), product of:
              0.7264124 = queryWeight, product of:
                1.0280906 = boost
                7.9878955 = idf(docFreq=40, maxDocs=44421)
                0.08845441 = queryNorm
              3.9939477 = fieldWeight in 213, product of:
                1.0 = tf(freq=1.0), with freq of:
                  1.0 = termFreq=1.0
                7.9878955 = idf(docFreq=40, maxDocs=44421)
                0.5 = fieldNorm(doc=213)
        0.5 = coord(1/2)
    
  5. Tang, M.-C.: Browsing and searching in a faceted information space : a naturalistic study of PubMed users' interaction with a display tool (2007) 1.45
    1.4506266 = sum of:
      1.4506266 = product of:
        2.9012532 = sum of:
          2.9012532 = weight(author_txt:tang in 1617) [ClassicSimilarity], result of:
            2.9012532 = score(doc=1617,freq=1.0), product of:
              0.7264124 = queryWeight, product of:
                1.0280906 = boost
                7.9878955 = idf(docFreq=40, maxDocs=44421)
                0.08845441 = queryNorm
              3.9939477 = fieldWeight in 1617, product of:
                1.0 = tf(freq=1.0), with freq of:
                  1.0 = termFreq=1.0
                7.9878955 = idf(docFreq=40, maxDocs=44421)
                0.5 = fieldNorm(doc=1617)
        0.5 = coord(1/2)
    

Similar documents (content)

  1. Chen, Z.; Huang, Y.; Tian, J.; Liu, X.; Fu, K.; Huang, T.: Joint model for subsentence-level sentiment analysis with Markov logic (2015) 0.23
    0.2256646 = sum of:
      0.2256646 = product of:
        0.9402692 = sum of:
          0.030740641 = weight(abstract_txt:level in 3210) [ClassicSimilarity], result of:
            0.030740641 = score(doc=3210,freq=2.0), product of:
              0.077371225 = queryWeight, product of:
                1.0741904 = boost
                4.4950905 = idf(docFreq=1347, maxDocs=44421)
                0.01602359 = queryNorm
              0.39731362 = fieldWeight in 3210, product of:
                1.4142135 = tf(freq=2.0), with freq of:
                  2.0 = termFreq=2.0
                4.4950905 = idf(docFreq=1347, maxDocs=44421)
                0.0625 = fieldNorm(doc=3210)
          0.042607244 = weight(abstract_txt:analysis in 3210) [ClassicSimilarity], result of:
            0.042607244 = score(doc=3210,freq=6.0), product of:
              0.07633959 = queryWeight, product of:
                1.3068087 = boost
                3.6456752 = idf(docFreq=3151, maxDocs=44421)
                0.01602359 = queryNorm
              0.55812776 = fieldWeight in 3210, 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=3210)
          0.040284898 = weight(abstract_txt:novel in 3210) [ClassicSimilarity], result of:
            0.040284898 = score(doc=3210,freq=1.0), product of:
              0.116737135 = queryWeight, product of:
                1.3194593 = boost
                5.521451 = idf(docFreq=482, maxDocs=44421)
                0.01602359 = queryNorm
              0.3450907 = fieldWeight in 3210, product of:
                1.0 = tf(freq=1.0), with freq of:
                  1.0 = termFreq=1.0
                5.521451 = idf(docFreq=482, maxDocs=44421)
                0.0625 = fieldNorm(doc=3210)
          0.07125925 = weight(abstract_txt:respectively in 3210) [ClassicSimilarity], result of:
            0.07125925 = score(doc=3210,freq=1.0), product of:
              0.17074253 = queryWeight, product of:
                1.5957408 = boost
                6.677587 = idf(docFreq=151, maxDocs=44421)
                0.01602359 = queryNorm
              0.4173492 = fieldWeight in 3210, product of:
                1.0 = tf(freq=1.0), with freq of:
                  1.0 = termFreq=1.0
                6.677587 = idf(docFreq=151, maxDocs=44421)
                0.0625 = fieldNorm(doc=3210)
          0.03369267 = weight(abstract_txt:framework in 3210) [ClassicSimilarity], result of:
            0.03369267 = score(doc=3210,freq=1.0), product of:
              0.11862281 = queryWeight, product of:
                1.6290005 = boost
                4.5445113 = idf(docFreq=1282, maxDocs=44421)
                0.01602359 = queryNorm
              0.28403196 = fieldWeight in 3210, product of:
                1.0 = tf(freq=1.0), with freq of:
                  1.0 = termFreq=1.0
                4.5445113 = idf(docFreq=1282, maxDocs=44421)
                0.0625 = fieldNorm(doc=3210)
          0.72168446 = weight(abstract_txt:sentiment in 3210) [ClassicSimilarity], result of:
            0.72168446 = score(doc=3210,freq=8.0), product of:
              0.54237014 = queryWeight, product of:
                4.49686 = boost
                7.5270805 = idf(docFreq=64, maxDocs=44421)
                0.01602359 = queryNorm
              1.3306124 = fieldWeight in 3210, 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=3210)
        0.24 = coord(6/25)
    
  2. Wei, W.; Liu, Y.-P.; Wei, L-R.: Feature-level sentiment analysis based on rules and fine-grained domain ontology (2020) 0.20
    0.1950256 = sum of:
      0.1950256 = product of:
        0.97512794 = sum of:
          0.024338689 = weight(abstract_txt:context in 876) [ClassicSimilarity], result of:
            0.024338689 = score(doc=876,freq=1.0), product of:
              0.07189615 = queryWeight, product of:
                1.0354862 = boost
                4.333128 = idf(docFreq=1584, maxDocs=44421)
                0.01602359 = queryNorm
              0.33852562 = fieldWeight in 876, product of:
                1.0 = tf(freq=1.0), with freq of:
                  1.0 = termFreq=1.0
                4.333128 = idf(docFreq=1584, maxDocs=44421)
                0.078125 = fieldNorm(doc=876)
          0.027171144 = weight(abstract_txt:level in 876) [ClassicSimilarity], result of:
            0.027171144 = score(doc=876,freq=1.0), product of:
              0.077371225 = queryWeight, product of:
                1.0741904 = boost
                4.4950905 = idf(docFreq=1347, maxDocs=44421)
                0.01602359 = queryNorm
              0.35117894 = fieldWeight in 876, product of:
                1.0 = tf(freq=1.0), with freq of:
                  1.0 = termFreq=1.0
                4.4950905 = idf(docFreq=1347, maxDocs=44421)
                0.078125 = fieldNorm(doc=876)
          0.03765984 = weight(abstract_txt:analysis in 876) [ClassicSimilarity], result of:
            0.03765984 = score(doc=876,freq=3.0), product of:
              0.07633959 = queryWeight, product of:
                1.3068087 = boost
                3.6456752 = idf(docFreq=3151, maxDocs=44421)
                0.01602359 = queryNorm
              0.4933199 = fieldWeight in 876, 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=876)
          0.042115837 = weight(abstract_txt:framework in 876) [ClassicSimilarity], result of:
            0.042115837 = score(doc=876,freq=1.0), product of:
              0.11862281 = queryWeight, product of:
                1.6290005 = boost
                4.5445113 = idf(docFreq=1282, maxDocs=44421)
                0.01602359 = queryNorm
              0.35503995 = fieldWeight in 876, product of:
                1.0 = tf(freq=1.0), with freq of:
                  1.0 = termFreq=1.0
                4.5445113 = idf(docFreq=1282, maxDocs=44421)
                0.078125 = fieldNorm(doc=876)
          0.84384245 = weight(abstract_txt:sentiment in 876) [ClassicSimilarity], result of:
            0.84384245 = score(doc=876,freq=7.0), product of:
              0.54237014 = queryWeight, product of:
                4.49686 = boost
                7.5270805 = idf(docFreq=64, maxDocs=44421)
                0.01602359 = queryNorm
              1.5558424 = fieldWeight in 876, product of:
                2.6457512 = tf(freq=7.0), with freq of:
                  7.0 = termFreq=7.0
                7.5270805 = idf(docFreq=64, maxDocs=44421)
                0.078125 = fieldNorm(doc=876)
        0.2 = coord(5/25)
    
  3. Nguyen, T.T.; Tho Thanh Quan, T.T.; Tuoi Thi Phan, T.T.: Sentiment search : an emerging trend on social media monitoring systems (2014) 0.19
    0.18961653 = sum of:
      0.18961653 = product of:
        0.9480826 = sum of:
          0.01947095 = weight(abstract_txt:context in 2625) [ClassicSimilarity], result of:
            0.01947095 = score(doc=2625,freq=1.0), product of:
              0.07189615 = queryWeight, product of:
                1.0354862 = boost
                4.333128 = idf(docFreq=1584, maxDocs=44421)
                0.01602359 = queryNorm
              0.2708205 = fieldWeight in 2625, product of:
                1.0 = tf(freq=1.0), with freq of:
                  1.0 = termFreq=1.0
                4.333128 = idf(docFreq=1584, maxDocs=44421)
                0.0625 = fieldNorm(doc=2625)
          0.024599303 = weight(abstract_txt:analysis in 2625) [ClassicSimilarity], result of:
            0.024599303 = score(doc=2625,freq=2.0), product of:
              0.07633959 = queryWeight, product of:
                1.3068087 = boost
                3.6456752 = idf(docFreq=3151, maxDocs=44421)
                0.01602359 = queryNorm
              0.3222352 = fieldWeight in 2625, product of:
                1.4142135 = tf(freq=2.0), with freq of:
                  2.0 = termFreq=2.0
                3.6456752 = idf(docFreq=3151, maxDocs=44421)
                0.0625 = fieldNorm(doc=2625)
          0.058357414 = weight(abstract_txt:framework in 2625) [ClassicSimilarity], result of:
            0.058357414 = score(doc=2625,freq=3.0), product of:
              0.11862281 = queryWeight, product of:
                1.6290005 = boost
                4.5445113 = idf(docFreq=1282, maxDocs=44421)
                0.01602359 = queryNorm
              0.49195778 = fieldWeight in 2625, product of:
                1.7320508 = tf(freq=3.0), with freq of:
                  3.0 = termFreq=3.0
                4.5445113 = idf(docFreq=1282, maxDocs=44421)
                0.0625 = fieldNorm(doc=2625)
          0.1239705 = weight(abstract_txt:aspect in 2625) [ClassicSimilarity], result of:
            0.1239705 = score(doc=2625,freq=2.0), product of:
              0.22439519 = queryWeight, product of:
                2.2404945 = boost
                6.250429 = idf(docFreq=232, maxDocs=44421)
                0.01602359 = queryNorm
              0.5524651 = fieldWeight in 2625, product of:
                1.4142135 = tf(freq=2.0), with freq of:
                  2.0 = termFreq=2.0
                6.250429 = idf(docFreq=232, maxDocs=44421)
                0.0625 = fieldNorm(doc=2625)
          0.72168446 = weight(abstract_txt:sentiment in 2625) [ClassicSimilarity], result of:
            0.72168446 = score(doc=2625,freq=8.0), product of:
              0.54237014 = queryWeight, product of:
                4.49686 = boost
                7.5270805 = idf(docFreq=64, maxDocs=44421)
                0.01602359 = queryNorm
              1.3306124 = fieldWeight in 2625, 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=2625)
        0.2 = coord(5/25)
    
  4. Xu, L.; Qiu, J.: Unsupervised multi-class sentiment classification approach (2019) 0.18
    0.18198772 = sum of:
      0.18198772 = product of:
        0.9099386 = sum of:
          0.017394334 = weight(abstract_txt:analysis in 3) [ClassicSimilarity], result of:
            0.017394334 = score(doc=3,freq=1.0), product of:
              0.07633959 = queryWeight, product of:
                1.3068087 = boost
                3.6456752 = idf(docFreq=3151, maxDocs=44421)
                0.01602359 = queryNorm
              0.2278547 = fieldWeight in 3, product of:
                1.0 = tf(freq=1.0), with freq of:
                  1.0 = termFreq=1.0
                3.6456752 = idf(docFreq=3151, maxDocs=44421)
                0.0625 = fieldNorm(doc=3)
          0.040284898 = weight(abstract_txt:novel in 3) [ClassicSimilarity], result of:
            0.040284898 = score(doc=3,freq=1.0), product of:
              0.116737135 = queryWeight, product of:
                1.3194593 = boost
                5.521451 = idf(docFreq=482, maxDocs=44421)
                0.01602359 = queryNorm
              0.3450907 = fieldWeight in 3, product of:
                1.0 = tf(freq=1.0), with freq of:
                  1.0 = termFreq=1.0
                5.521451 = idf(docFreq=482, maxDocs=44421)
                0.0625 = fieldNorm(doc=3)
          0.050545882 = weight(abstract_txt:accuracy in 3) [ClassicSimilarity], result of:
            0.050545882 = score(doc=3,freq=1.0), product of:
              0.13580154 = queryWeight, product of:
                1.4231277 = boost
                5.9552646 = idf(docFreq=312, maxDocs=44421)
                0.01602359 = queryNorm
              0.37220404 = fieldWeight in 3, product of:
                1.0 = tf(freq=1.0), with freq of:
                  1.0 = termFreq=1.0
                5.9552646 = idf(docFreq=312, maxDocs=44421)
                0.0625 = fieldNorm(doc=3)
          0.036251556 = weight(abstract_txt:time in 3) [ClassicSimilarity], result of:
            0.036251556 = score(doc=3,freq=2.0), product of:
              0.098859645 = queryWeight, product of:
                1.4871222 = boost
                4.1487055 = idf(docFreq=1905, maxDocs=44421)
                0.01602359 = queryNorm
              0.36669722 = fieldWeight in 3, product of:
                1.4142135 = tf(freq=2.0), with freq of:
                  2.0 = termFreq=2.0
                4.1487055 = idf(docFreq=1905, maxDocs=44421)
                0.0625 = fieldNorm(doc=3)
          0.7654619 = weight(abstract_txt:sentiment in 3) [ClassicSimilarity], result of:
            0.7654619 = score(doc=3,freq=9.0), product of:
              0.54237014 = queryWeight, product of:
                4.49686 = boost
                7.5270805 = idf(docFreq=64, maxDocs=44421)
                0.01602359 = queryNorm
              1.4113276 = fieldWeight in 3, product of:
                3.0 = tf(freq=9.0), with freq of:
                  9.0 = termFreq=9.0
                7.5270805 = idf(docFreq=64, maxDocs=44421)
                0.0625 = fieldNorm(doc=3)
        0.2 = coord(5/25)
    
  5. Saif, H.; He, Y.; Fernandez, M.; Alani, H.: Contextual semantics for sentiment analysis of Twitter (2016) 0.17
    0.16682015 = sum of:
      0.16682015 = product of:
        0.8341007 = sum of:
          0.01947095 = weight(abstract_txt:context in 3667) [ClassicSimilarity], result of:
            0.01947095 = score(doc=3667,freq=1.0), product of:
              0.07189615 = queryWeight, product of:
                1.0354862 = boost
                4.333128 = idf(docFreq=1584, maxDocs=44421)
                0.01602359 = queryNorm
              0.2708205 = fieldWeight in 3667, product of:
                1.0 = tf(freq=1.0), with freq of:
                  1.0 = termFreq=1.0
                4.333128 = idf(docFreq=1584, maxDocs=44421)
                0.0625 = fieldNorm(doc=3667)
          0.043473832 = weight(abstract_txt:level in 3667) [ClassicSimilarity], result of:
            0.043473832 = score(doc=3667,freq=4.0), product of:
              0.077371225 = queryWeight, product of:
                1.0741904 = boost
                4.4950905 = idf(docFreq=1347, maxDocs=44421)
                0.01602359 = queryNorm
              0.5618863 = fieldWeight in 3667, product of:
                2.0 = tf(freq=4.0), with freq of:
                  4.0 = termFreq=4.0
                4.4950905 = idf(docFreq=1347, maxDocs=44421)
                0.0625 = fieldNorm(doc=3667)
          0.024599303 = weight(abstract_txt:analysis in 3667) [ClassicSimilarity], result of:
            0.024599303 = score(doc=3667,freq=2.0), product of:
              0.07633959 = queryWeight, product of:
                1.3068087 = boost
                3.6456752 = idf(docFreq=3151, maxDocs=44421)
                0.01602359 = queryNorm
              0.3222352 = fieldWeight in 3667, product of:
                1.4142135 = tf(freq=2.0), with freq of:
                  2.0 = termFreq=2.0
                3.6456752 = idf(docFreq=3151, maxDocs=44421)
                0.0625 = fieldNorm(doc=3667)
          0.07148267 = weight(abstract_txt:accuracy in 3667) [ClassicSimilarity], result of:
            0.07148267 = score(doc=3667,freq=2.0), product of:
              0.13580154 = queryWeight, product of:
                1.4231277 = boost
                5.9552646 = idf(docFreq=312, maxDocs=44421)
                0.01602359 = queryNorm
              0.526376 = fieldWeight in 3667, product of:
                1.4142135 = tf(freq=2.0), with freq of:
                  2.0 = termFreq=2.0
                5.9552646 = idf(docFreq=312, maxDocs=44421)
                0.0625 = fieldNorm(doc=3667)
          0.675074 = weight(abstract_txt:sentiment in 3667) [ClassicSimilarity], result of:
            0.675074 = score(doc=3667,freq=7.0), product of:
              0.54237014 = queryWeight, product of:
                4.49686 = boost
                7.5270805 = idf(docFreq=64, maxDocs=44421)
                0.01602359 = queryNorm
              1.244674 = fieldWeight in 3667, product of:
                2.6457512 = tf(freq=7.0), with freq of:
                  7.0 = termFreq=7.0
                7.5270805 = idf(docFreq=64, maxDocs=44421)
                0.0625 = fieldNorm(doc=3667)
        0.2 = coord(5/25)