ABSTRACT
A few troublemakers often spoil online environments for everyone else. An extremely disruptive type of abuser is the troll, whose malicious activities are relatively non-obvious, and thus difficult to detect and contain -- particularly by automated systems. A growing corpus of qualitative research focuses on trolling, and differentiates it from other forms of abuse; however, its findings are not directly actionable into automated systems. On the other hand, quantitative research uses definitions of "troll" that mostly fail to capture what moderators and users consider trolling. We address this gap by giving a quantitative analysis of posts, conversations, and users, specifically sanctioned for trolling in an online forum. Although trolls (unlike most other abusers) hardly stand out in a conversation e.g. in terms of vocabulary, textit{how} they interact, rather than textit{what} they contribute, provides cues of their malicious intent.
- Jonathan Bishop. 2014. Representations of 'trolls' in mass media communication: a review of media-texts and moral panics relating to 'internet trolling'. International Journal of Web Based Communities 10, 1 (2014), 7. Google ScholarDigital Library
- Jonathan Bishop. 2016. Trolling Is Not Just a Art. It Is an Science. In Handbook of Research on Digital Crime, Cyberspace Security, and Information Assurance. Number July. IGI Global, Chapter 28, 436--450.Google Scholar
- Leo Breiman. 2001. Random forests. Machine learning (2001), 5--32. Google ScholarDigital Library
- Erin E. Buckels, Paul D. Trapnell, and Delroy L. Paulhus. 2014. Trolls just want to have fun. Personality and Individual Differences 67 (9 2014), 97--102.Google Scholar
- Catherine Buni and Soraya Chemaly. 2016. The Secret Rules of the Internet: The Murky History of Moderation, and How It's Shaping the Future of Free Speech. (2016). https://goo.gl/mG2jDAGoogle Scholar
- Erik Cambria, Praphul Chandra, Avinash Sharma, and Amir Hussain. 2010. Do Not Feel the Trolls. In Proceedings of the 3rd International Workshop on Social Data on the Web (SDoW 2010). http://ceur-ws.org/Vol-664/paper1.pdfGoogle Scholar
- Justin Cheng, Cristian Danescu-Niculescu-Mizil, and Jure Leskovec. 2014. How community feedback shapes user behavior. In Proceedings of the Eighth International AAAI Conference on Weblogs and Social Media ICWSM '14. 41--50. http://arxiv.org/abs/1405.1429Google ScholarCross Ref
- Justin Cheng, Cristian Danescu-Niculescu-Mizil, and Jure Leskovec. 2015. Antisocial Behavior in Online Discussion Communities. In Proceedings of the Ninth International AAAI Conference on Web and Social Media ICWSM '15. http://arxiv.org/abs/1504.00680Google Scholar
- Cristian Danescu-Niculescu-Mizil, Moritz Sudhof, Dan Jurafsky, Jure Leskovec, and Christopher Potts. 2013. A computational approach to politeness with application to social factors. Proceedings of ACL (2013). http://politeness.mpi-sws.org/Google Scholar
- Imen Ouled Dlala, Dorra Attiaoui, Arnaud Martin, and Boutheina Ben Yaghlane. 2014. Trolls Identification within an Uncertain Framework. In 2014 IEEE 26th International Conference on Tools with Artificial Intelligence. IEEE, 1011--1015. Google ScholarDigital Library
- Judith Donath. 1999. Idenity and Deception in the Virtual Community. Communities in Cyberspace (1999), 27--58.Google Scholar
- Patxi Galán-García, José Gaviria De La Puerta, Carlos Laorden Gómez, Igor Santos, and Pablo García Bringas. 2014. Supervised machine learning for the detection of troll profiles in twitter social network: Application to a real case of cyberbullying. Logic Journal of the IGPL 24, 1 (2014), 42--53.Google Scholar
- Claire Hardaker. 2010. Trolling in asynchronous computer-mediated communication: From user discussions to academic definitions. Journal of Politeness Research 6, 2 (2010), 215--242.Google ScholarCross Ref
- Claire Hardaker. 2013. "Uh. . . . not to be nitpicky,but...the past tense of drag is dragged, not drug.: An overview of trolling strategies. Journal of Language Aggression and Conflict 1, 1 (2013), 58--86.Google ScholarCross Ref
- Claire Hardaker. 2015. "I refuse to respond to this obvious troll": an overview of responses to (perceived) trolling. Corpora 10, 2 (8 2015), 201--229.Google Scholar
- Susan Herring, Kirk Job-Sluder, Rebecca Scheckler, and Sasha Barab. 2002. Searching for Safety Online: Managing "Trolling" in a Feminist Forum. The Information Society 18, 5 (2002), 371--384.Google ScholarCross Ref
- Todor Mihaylov and Preslav Nakov. 2016. Hunting for Troll Comments in News Community Forums. Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers) (2016), 399--405. http://anthology.aclweb.org/P16--2065Google ScholarCross Ref
- Paul R. Rosenbaum and Donald B. Rubin. 1983. The central role of the propensity score in observational studies for causal effects. Biometrika 70, 1 (1983), 41--55.Google ScholarCross Ref
- Mattia Samory and Enoch Peserico. 2016. Content attribution ignoring content. In Proceedings of the 8th ACM Conference on Web Science - WebSci '16. ACM Press, New York, New York, USA, 233--243. Google ScholarDigital Library
- Pnina Shachaf and Noriko Hara. 2010. Beyond vandalism: Wikipedia trolls. Journal of Information Science 36, 3 (2010), 357--370. Google ScholarDigital Library
- Edgar A. Smith and R J. Senter. 1967. Automated readability index. AMRL-TR. Aerospace Medical Research Laboratories (U.S.) (5 1967), 1--14. http://www.dtic.mil/dtic/tr/fulltext/u2/667273. pdfGoogle Scholar
- Yla R. Tausczik and James W. Pennebaker. 2010. The Psychological Meaning of Words: LIWC and Computerized Text Analysis Methods. Journal of Language and Social Psychology 29, 1 (2010), 24--54.Google ScholarCross Ref
- Hyeongseok Wi and Wonjae Lee. 2014. The norm of normlessness: Structural Correlates of A Trolling Community. In Proceedings of the 2014 ACM conference on Web science - WebSci '14. ACM Press, New York, New York, USA, 275--276. Google ScholarDigital Library
Index Terms
- Sizing Up the Troll: A Quantitative Characterization of Moderator-Identified Trolling in an Online Forum
Recommendations
Anyone Can Become a Troll: Causes of Trolling Behavior in Online Discussions
CSCW '17: Proceedings of the 2017 ACM Conference on Computer Supported Cooperative Work and Social ComputingIn online communities, antisocial behavior such as trolling disrupts constructive discussion. While prior work suggests that trolling behavior is confined to a vocal and antisocial minority, we demonstrate that ordinary people can engage in such ...
Who would respond to A troll? A social network analysis of reactions to trolls in online communities
AbstractTrolls are individual internet users with anti-social remarks and behaviors who can disrupt on-topic discussions and wreak havoc on the various functions of online communities. This study investigated the aftermath of trolling on ...
Highlights- Trolls provoke emotional and behavioral responses from internet users and damage the normal functioning of online communities.
Dealing with Internet Trolling in Political Online Communities: Towards the This Is Why We Can't Have Nice Things Scale
Internet trolling has become a popularly used term to describe the posting of any content on the Internet which is provocative or offensive. This is different from the original meaning online in the 1990s, which referred to the posting of provocative ...
Comments