Ex Machina: Personal Attacks Seen at Scale

The damage personal attacks cause to online discourse motivates many platforms to try to curb the phenomenon. However, understanding the prevalence and impact of personal attacks in online platforms at scale remains surprisingly difficult. The contribution of this paper is to develop and illustrate a method that combines crowdsourcing and machine learning to analyze personal attacks at scale. We show an evaluation method for a classifier in terms of the aggregated number of crowd-workers it can approximate. We apply our methodology to English Wikipedia, generating a corpus of over 100k high quality human-labeled comments and 63M machine-labeled ones from a classifier that is as good as the aggregate of 3 crowd-workers, as measured by the area under the ROC curve and Spearman correlation. Using this corpus of machine-labeled scores, our methodology allows us to explore some of the open questions about the nature of online personal attacks. This reveals that the majority of personal attacks on Wikipedia are not the result of a few malicious users, nor primarily the consequence of allowing anonymous contributions from unregistered users.

[1]  References , 1971 .

[2]  Klaus Krippendorff,et al.  Content Analysis: An Introduction to Its Methodology , 1980 .

[3]  David Wiener Negligent Publication of Statements Posted on Electronic Bulletin Boards: Is There Any Liability Left After Zeran? , 1999 .

[4]  Michele L. Ybarra,et al.  Youth engaging in online harassment: associations with caregiver-child relationships, Internet use, and personal characteristics. , 2004, Journal of adolescence.

[5]  K. Krippendorff Reliability in Content Analysis: Some Common Misconceptions and Recommendations , 2004 .

[6]  N. Willard Cyberbullying and Cyberthreats: Responding to the Challenge of Online Social Aggression, Threats, and Distress , 2007 .

[7]  Klaus Krippendorff,et al.  Answering the Call for a Standard Reliability Measure for Coding Data , 2007 .

[8]  Brian D. Davison,et al.  Detection of Harassment on Web 2.0 , 2009 .

[9]  Kimberly A. Neuendorf,et al.  Reliability for Content Analysis , 2010 .

[10]  Martin Chodorow,et al.  Rethinking Grammatical Error Annotation and Evaluation with the Amazon Mechanical Turk , 2010 .

[11]  Robert S. Tokunaga,et al.  Following you home from school: A critical review and synthesis of research on cyberbullying victimization , 2010, Comput. Hum. Behav..

[12]  L. Webb,et al.  Computer-Mediated Communication in Personal Relationships , 2010 .

[13]  Henry Lieberman,et al.  Modeling the Detection of Textual Cyberbullying , 2011, The Social Mobile Web.

[14]  Michael D. Buhrmester,et al.  Amazon's Mechanical Turk , 2011, Perspectives on psychological science : a journal of the Association for Psychological Science.

[15]  Yoshua Bengio,et al.  Random Search for Hyper-Parameter Optimization , 2012, J. Mach. Learn. Res..

[16]  Julia Hirschberg,et al.  Detecting Hate Speech on the World Wide Web , 2012 .

[17]  Jiawei Han,et al.  Survey on web spam detection: principles and algorithms , 2012, SKDD.

[18]  Elizabeth F. Churchill,et al.  Automatic identification of personal insults on social news sites , 2012, J. Assoc. Inf. Sci. Technol..

[19]  Tatsuya Suda,et al.  Anonymity and roles associated with aggressive posts in an online forum , 2012, Comput. Hum. Behav..

[20]  Marilyn A. Walker,et al.  A Corpus for Research on Deliberation and Debate , 2012, LREC.

[21]  Carolyn Penstein Rosé,et al.  Detecting offensive tweets via topical feature discovery over a large scale twitter corpus , 2012, CIKM.

[22]  Jun-Ming Xu,et al.  An Examination of Regret in Bullying Tweets , 2013, HLT-NAACL.

[23]  Yuzhou Wang,et al.  Locate the Hate: Detecting Tweets against Blacks , 2013, AAAI.

[24]  Dirk Hovy,et al.  Learning part-of-speech taggers with inter-annotator agreement loss , 2014, EACL.

[25]  Jure Leskovec,et al.  Antisocial Behavior in Online Discussion Communities , 2015, ICWSM.

[26]  S. Pieschl,et al.  Beware of Publicity! Perceived Distress of Negative Cyber Incidents and Implications for Defining Cyberbullying , 2015 .

[27]  Navneet Kaur,et al.  Opinion mining and sentiment analysis , 2016, 2016 3rd International Conference on Computing for Sustainable Global Development (INDIACom).

[28]  Dirk Hovy,et al.  Hateful Symbols or Hateful People? Predictive Features for Hate Speech Detection on Twitter , 2016, NAACL.

[29]  Joel R. Tetreault,et al.  Abusive Language Detection in Online User Content , 2016, WWW.

[30]  Derek Ruths,et al.  A Web of Hate: Tackling Hateful Speech in Online Social Spaces , 2017, ArXiv.

[31]  J. Golbeck Online Harassment , 2020, Human Resource Management International Digest.