Document (#36977)

Author

Sood, S.O.
Churchill, E.F.
Antin, J.

Title

Automatic identification of personal insults on social news sites

Source

Journal of the American Society for Information Science and Technology. 63(2012) no.2, S.270-285

Year

2012

Abstract

As online communities grow and the volume of user-generated content increases, the need for community management also rises. Community management has three main purposes: to create a positive experience for existing participants, to promote appropriate, socionormative behaviors, and to encourage potential participants to make contributions. Research indicates that the quality of content a potential participant sees on a site is highly influential; off-topic, negative comments with malicious intent are a particularly strong boundary to participation or set the tone for encouraging similar contributions. A problem for community managers, therefore, is the detection and elimination of such undesirable content. As a community grows, this undertaking becomes more daunting. Can an automated system aid community managers in this task? In this paper, we address this question through a machine learning approach to automatic detection of inappropriate negative user contributions. Our training corpus is a set of comments from a news commenting site that we tasked Amazon Mechanical Turk workers with labeling. Each comment is labeled for the presence of profanity, insults, and the object of the insults. Support vector machines trained on these data are combined with relevance and valence analysis systems in a multistep approach to the detection of inappropriate negative user contributions. The system shows great potential for semiautomated community management.

Theme

Internet

Similar documents (content)

1. Zheng, H.; Goh, D.H.-L.; Lee, E.W.J.; Lee, C.S.; Theng, Y.-L.: Understanding the effects of message cues on COVID-19 information sharing on Twitter (2022) 0.14

   0.14151606 = sum of:
     0.14151606 = product of:
       0.5054145 = sum of:
         0.16486652 = weight(abstract_txt:valence in 1565) [ClassicSimilarity], result of:
           0.16486652 = score(doc=1565,freq=2.0), product of:
             0.19845462 = queryWeight, product of:
               1.0667099 = boost
               9.398883 = idf(docFreq=9, maxDocs=44421)
               0.019794233 = queryNorm
             0.8307517 = fieldWeight in 1565, product of:
               1.4142135 = tf(freq=2.0), with freq of:
                 2.0 = termFreq=2.0
               9.398883 = idf(docFreq=9, maxDocs=44421)
               0.0625 = fieldNorm(doc=1565)
         0.011065669 = weight(abstract_txt:this in 1565) [ClassicSimilarity], result of:
           0.011065669 = score(doc=1565,freq=2.0), product of:
             0.052028906 = queryWeight, product of:
               1.0923656 = boost
               2.4062347 = idf(docFreq=10885, maxDocs=44421)
               0.019794233 = queryNorm
             0.21268311 = fieldWeight in 1565, product of:
               1.4142135 = tf(freq=2.0), with freq of:
                 2.0 = termFreq=2.0
               2.4062347 = idf(docFreq=10885, maxDocs=44421)
               0.0625 = fieldNorm(doc=1565)
         0.021006847 = weight(abstract_txt:user in 1565) [ClassicSimilarity], result of:
           0.021006847 = score(doc=1565,freq=1.0), product of:
             0.09131257 = queryWeight, product of:
               1.2532612 = boost
               3.6808684 = idf(docFreq=3042, maxDocs=44421)
               0.019794233 = queryNorm
             0.23005427 = fieldWeight in 1565, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               3.6808684 = idf(docFreq=3042, maxDocs=44421)
               0.0625 = fieldNorm(doc=1565)
         0.08401112 = weight(abstract_txt:news in 1565) [ClassicSimilarity], result of:
           0.08401112 = score(doc=1565,freq=2.0), product of:
             0.15951717 = queryWeight, product of:
               1.3524911 = boost
               5.9584646 = idf(docFreq=311, maxDocs=44421)
               0.019794233 = queryNorm
             0.52665883 = fieldWeight in 1565, product of:
               1.4142135 = tf(freq=2.0), with freq of:
                 2.0 = termFreq=2.0
               5.9584646 = idf(docFreq=311, maxDocs=44421)
               0.0625 = fieldNorm(doc=1565)
         0.043494243 = weight(abstract_txt:content in 1565) [ClassicSimilarity], result of:
           0.043494243 = score(doc=1565,freq=2.0), product of:
             0.11773381 = queryWeight, product of:
               1.4230721 = boost
               4.1796083 = idf(docFreq=1847, maxDocs=44421)
               0.019794233 = queryNorm
             0.36942866 = fieldWeight in 1565, product of:
               1.4142135 = tf(freq=2.0), with freq of:
                 2.0 = termFreq=2.0
               4.1796083 = idf(docFreq=1847, maxDocs=44421)
               0.0625 = fieldNorm(doc=1565)
         0.032103654 = weight(abstract_txt:management in 1565) [ClassicSimilarity], result of:
           0.032103654 = score(doc=1565,freq=1.0), product of:
             0.12115081 = queryWeight, product of:
               1.4435754 = boost
               4.239827 = idf(docFreq=1739, maxDocs=44421)
               0.019794233 = queryNorm
             0.2649892 = fieldWeight in 1565, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               4.239827 = idf(docFreq=1739, maxDocs=44421)
               0.0625 = fieldNorm(doc=1565)
         0.14886636 = weight(abstract_txt:negative in 1565) [ClassicSimilarity], result of:
           0.14886636 = score(doc=1565,freq=2.0), product of:
             0.2673895 = queryWeight, product of:
               2.144611 = boost
               6.2987905 = idf(docFreq=221, maxDocs=44421)
               0.019794233 = queryNorm
             0.5567397 = fieldWeight in 1565, product of:
               1.4142135 = tf(freq=2.0), with freq of:
                 2.0 = termFreq=2.0
               6.2987905 = idf(docFreq=221, maxDocs=44421)
               0.0625 = fieldNorm(doc=1565)
       0.28 = coord(7/25)
   

2. Bullard, J.; Howison, J.: Learning from Elitist Jerks : creating high-quality knowledge resources from ongoing conversations (2015) 0.13

   0.12534094 = sum of:
     0.12534094 = product of:
       0.44764623 = sum of:
         0.00782461 = weight(abstract_txt:this in 3268) [ClassicSimilarity], result of:
           0.00782461 = score(doc=3268,freq=1.0), product of:
             0.052028906 = queryWeight, product of:
               1.0923656 = boost
               2.4062347 = idf(docFreq=10885, maxDocs=44421)
               0.019794233 = queryNorm
             0.15038967 = fieldWeight in 3268, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               2.4062347 = idf(docFreq=10885, maxDocs=44421)
               0.0625 = fieldNorm(doc=3268)
         0.05193859 = weight(abstract_txt:site in 3268) [ClassicSimilarity], result of:
           0.05193859 = score(doc=3268,freq=1.0), product of:
             0.14585444 = queryWeight, product of:
               1.2932739 = boost
               5.6975803 = idf(docFreq=404, maxDocs=44421)
               0.019794233 = queryNorm
             0.35609877 = fieldWeight in 3268, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               5.6975803 = idf(docFreq=404, maxDocs=44421)
               0.0625 = fieldNorm(doc=3268)
         0.030755075 = weight(abstract_txt:content in 3268) [ClassicSimilarity], result of:
           0.030755075 = score(doc=3268,freq=1.0), product of:
             0.11773381 = queryWeight, product of:
               1.4230721 = boost
               4.1796083 = idf(docFreq=1847, maxDocs=44421)
               0.019794233 = queryNorm
             0.26122552 = fieldWeight in 3268, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               4.1796083 = idf(docFreq=1847, maxDocs=44421)
               0.0625 = fieldNorm(doc=3268)
         0.032103654 = weight(abstract_txt:management in 3268) [ClassicSimilarity], result of:
           0.032103654 = score(doc=3268,freq=1.0), product of:
             0.12115081 = queryWeight, product of:
               1.4435754 = boost
               4.239827 = idf(docFreq=1739, maxDocs=44421)
               0.019794233 = queryNorm
             0.2649892 = fieldWeight in 3268, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               4.239827 = idf(docFreq=1739, maxDocs=44421)
               0.0625 = fieldNorm(doc=3268)
         0.074422464 = weight(abstract_txt:comments in 3268) [ClassicSimilarity], result of:
           0.074422464 = score(doc=3268,freq=1.0), product of:
             0.18537974 = queryWeight, product of:
               1.4580145 = boost
               6.4233527 = idf(docFreq=195, maxDocs=44421)
               0.019794233 = queryNorm
             0.40145954 = fieldWeight in 3268, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               6.4233527 = idf(docFreq=195, maxDocs=44421)
               0.0625 = fieldNorm(doc=3268)
         0.1223999 = weight(abstract_txt:contributions in 3268) [ClassicSimilarity], result of:
           0.1223999 = score(doc=3268,freq=1.0), product of:
             0.3254295 = queryWeight, product of:
               2.7319589 = boost
               6.017888 = idf(docFreq=293, maxDocs=44421)
               0.019794233 = queryNorm
             0.376118 = fieldWeight in 3268, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               6.017888 = idf(docFreq=293, maxDocs=44421)
               0.0625 = fieldNorm(doc=3268)
         0.12820193 = weight(abstract_txt:community in 3268) [ClassicSimilarity], result of:
           0.12820193 = score(doc=3268,freq=2.0), product of:
             0.30494374 = queryWeight, product of:
               3.2389271 = boost
               4.7564163 = idf(docFreq=1037, maxDocs=44421)
               0.019794233 = queryNorm
             0.42041177 = fieldWeight in 3268, product of:
               1.4142135 = tf(freq=2.0), with freq of:
                 2.0 = termFreq=2.0
               4.7564163 = idf(docFreq=1037, maxDocs=44421)
               0.0625 = fieldNorm(doc=3268)
       0.28 = coord(7/25)
   

3. Song, M.; Jeong, Y.K.; Kim, H.J.: Identifying the topology of the K-pop video community on YouTube : a combined co-comment analysis approach (2015) 0.12

   0.12454301 = sum of:
     0.12454301 = product of:
       0.62271506 = sum of:
         0.14443687 = weight(abstract_txt:commenting in 3273) [ClassicSimilarity], result of:
           0.14443687 = score(doc=3273,freq=2.0), product of:
             0.1817014 = queryWeight, product of:
               1.0206922 = boost
               8.993418 = idf(docFreq=14, maxDocs=44421)
               0.019794233 = queryNorm
             0.7949133 = fieldWeight in 3273, product of:
               1.4142135 = tf(freq=2.0), with freq of:
                 2.0 = termFreq=2.0
               8.993418 = idf(docFreq=14, maxDocs=44421)
               0.0625 = fieldNorm(doc=3273)
         0.01564922 = weight(abstract_txt:this in 3273) [ClassicSimilarity], result of:
           0.01564922 = score(doc=3273,freq=4.0), product of:
             0.052028906 = queryWeight, product of:
               1.0923656 = boost
               2.4062347 = idf(docFreq=10885, maxDocs=44421)
               0.019794233 = queryNorm
             0.30077934 = fieldWeight in 3273, product of:
               2.0 = tf(freq=4.0), with freq of:
                 4.0 = termFreq=4.0
               2.4062347 = idf(docFreq=10885, maxDocs=44421)
               0.0625 = fieldNorm(doc=3273)
         0.06302054 = weight(abstract_txt:user in 3273) [ClassicSimilarity], result of:
           0.06302054 = score(doc=3273,freq=9.0), product of:
             0.09131257 = queryWeight, product of:
               1.2532612 = boost
               3.6808684 = idf(docFreq=3042, maxDocs=44421)
               0.019794233 = queryNorm
             0.69016284 = fieldWeight in 3273, product of:
               3.0 = tf(freq=9.0), with freq of:
                 9.0 = termFreq=9.0
               3.6808684 = idf(docFreq=3042, maxDocs=44421)
               0.0625 = fieldNorm(doc=3273)
         0.19690333 = weight(abstract_txt:comments in 3273) [ClassicSimilarity], result of:
           0.19690333 = score(doc=3273,freq=7.0), product of:
             0.18537974 = queryWeight, product of:
               1.4580145 = boost
               6.4233527 = idf(docFreq=195, maxDocs=44421)
               0.019794233 = queryNorm
             1.062162 = fieldWeight in 3273, product of:
               2.6457512 = tf(freq=7.0), with freq of:
                 7.0 = termFreq=7.0
               6.4233527 = idf(docFreq=195, maxDocs=44421)
               0.0625 = fieldNorm(doc=3273)
         0.20270507 = weight(abstract_txt:community in 3273) [ClassicSimilarity], result of:
           0.20270507 = score(doc=3273,freq=5.0), product of:
             0.30494374 = queryWeight, product of:
               3.2389271 = boost
               4.7564163 = idf(docFreq=1037, maxDocs=44421)
               0.019794233 = queryNorm
             0.6647294 = fieldWeight in 3273, product of:
               2.236068 = tf(freq=5.0), with freq of:
                 5.0 = termFreq=5.0
               4.7564163 = idf(docFreq=1037, maxDocs=44421)
               0.0625 = fieldNorm(doc=3273)
       0.2 = coord(5/25)
   

4. Thelwall, M.; Buckley, K.; Paltoglou, G.; Cai, D.; Kappas, A.: Sentiment strength detection in short informal text (2010) 0.12

   0.11688585 = sum of:
     0.11688585 = product of:
       0.48702437 = sum of:
         0.013552622 = weight(abstract_txt:this in 200) [ClassicSimilarity], result of:
           0.013552622 = score(doc=200,freq=3.0), product of:
             0.052028906 = queryWeight, product of:
               1.0923656 = boost
               2.4062347 = idf(docFreq=10885, maxDocs=44421)
               0.019794233 = queryNorm
             0.26048255 = fieldWeight in 200, product of:
               1.7320508 = tf(freq=3.0), with freq of:
                 3.0 = termFreq=3.0
               2.4062347 = idf(docFreq=10885, maxDocs=44421)
               0.0625 = fieldNorm(doc=200)
         0.021006847 = weight(abstract_txt:user in 200) [ClassicSimilarity], result of:
           0.021006847 = score(doc=200,freq=1.0), product of:
             0.09131257 = queryWeight, product of:
               1.2532612 = boost
               3.6808684 = idf(docFreq=3042, maxDocs=44421)
               0.019794233 = queryNorm
             0.23005427 = fieldWeight in 200, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               3.6808684 = idf(docFreq=3042, maxDocs=44421)
               0.0625 = fieldNorm(doc=200)
         0.074422464 = weight(abstract_txt:comments in 200) [ClassicSimilarity], result of:
           0.074422464 = score(doc=200,freq=1.0), product of:
             0.18537974 = queryWeight, product of:
               1.4580145 = boost
               6.4233527 = idf(docFreq=195, maxDocs=44421)
               0.019794233 = queryNorm
             0.40145954 = fieldWeight in 200, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               6.4233527 = idf(docFreq=195, maxDocs=44421)
               0.0625 = fieldNorm(doc=200)
         0.14183372 = weight(abstract_txt:inappropriate in 200) [ClassicSimilarity], result of:
           0.14183372 = score(doc=200,freq=1.0), product of:
             0.28495693 = queryWeight, product of:
               1.8076748 = boost
               7.963798 = idf(docFreq=41, maxDocs=44421)
               0.019794233 = queryNorm
             0.49773738 = fieldWeight in 200, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               7.963798 = idf(docFreq=41, maxDocs=44421)
               0.0625 = fieldNorm(doc=200)
         0.1052644 = weight(abstract_txt:negative in 200) [ClassicSimilarity], result of:
           0.1052644 = score(doc=200,freq=1.0), product of:
             0.2673895 = queryWeight, product of:
               2.144611 = boost
               6.2987905 = idf(docFreq=221, maxDocs=44421)
               0.019794233 = queryNorm
             0.3936744 = fieldWeight in 200, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               6.2987905 = idf(docFreq=221, maxDocs=44421)
               0.0625 = fieldNorm(doc=200)
         0.13094433 = weight(abstract_txt:detection in 200) [ClassicSimilarity], result of:
           0.13094433 = score(doc=200,freq=1.0), product of:
             0.30927712 = queryWeight, product of:
               2.3064828 = boost
               6.774214 = idf(docFreq=137, maxDocs=44421)
               0.019794233 = queryNorm
             0.42338836 = fieldWeight in 200, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               6.774214 = idf(docFreq=137, maxDocs=44421)
               0.0625 = fieldNorm(doc=200)
       0.24 = coord(6/25)
   

5. Thelwall, M.; Wilkinson, D.; Uppal, S.: Data mining emotion in social network communication : gender differences in MySpace (2009) 0.11

   0.109813824 = sum of:
     0.109813824 = product of:
       0.5490691 = sum of:
         0.009780763 = weight(abstract_txt:this in 309) [ClassicSimilarity], result of:
           0.009780763 = score(doc=309,freq=1.0), product of:
             0.052028906 = queryWeight, product of:
               1.0923656 = boost
               2.4062347 = idf(docFreq=10885, maxDocs=44421)
               0.019794233 = queryNorm
             0.18798709 = fieldWeight in 309, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               2.4062347 = idf(docFreq=10885, maxDocs=44421)
               0.078125 = fieldNorm(doc=309)
         0.064923234 = weight(abstract_txt:site in 309) [ClassicSimilarity], result of:
           0.064923234 = score(doc=309,freq=1.0), product of:
             0.14585444 = queryWeight, product of:
               1.2932739 = boost
               5.6975803 = idf(docFreq=404, maxDocs=44421)
               0.019794233 = queryNorm
             0.44512346 = fieldWeight in 309, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               5.6975803 = idf(docFreq=404, maxDocs=44421)
               0.078125 = fieldNorm(doc=309)
         0.03844384 = weight(abstract_txt:content in 309) [ClassicSimilarity], result of:
           0.03844384 = score(doc=309,freq=1.0), product of:
             0.11773381 = queryWeight, product of:
               1.4230721 = boost
               4.1796083 = idf(docFreq=1847, maxDocs=44421)
               0.019794233 = queryNorm
             0.3265319 = fieldWeight in 309, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               4.1796083 = idf(docFreq=1847, maxDocs=44421)
               0.078125 = fieldNorm(doc=309)
         0.20801713 = weight(abstract_txt:comments in 309) [ClassicSimilarity], result of:
           0.20801713 = score(doc=309,freq=5.0), product of:
             0.18537974 = queryWeight, product of:
               1.4580145 = boost
               6.4233527 = idf(docFreq=195, maxDocs=44421)
               0.019794233 = queryNorm
             1.1221136 = fieldWeight in 309, product of:
               2.236068 = tf(freq=5.0), with freq of:
                 5.0 = termFreq=5.0
               6.4233527 = idf(docFreq=195, maxDocs=44421)
               0.078125 = fieldNorm(doc=309)
         0.22790413 = weight(abstract_txt:negative in 309) [ClassicSimilarity], result of:
           0.22790413 = score(doc=309,freq=3.0), product of:
             0.2673895 = queryWeight, product of:
               2.144611 = boost
               6.2987905 = idf(docFreq=221, maxDocs=44421)
               0.019794233 = queryNorm
             0.8523301 = fieldWeight in 309, product of:
               1.7320508 = tf(freq=3.0), with freq of:
                 3.0 = termFreq=3.0
               6.2987905 = idf(docFreq=221, maxDocs=44421)
               0.078125 = fieldNorm(doc=309)
       0.2 = coord(5/25)