Troll Detection and Anti-Trolling Solution using Artificial Intelligence/ Machine Learning

Authors

  • Saloni Dangre  Department of Computer Engineering, Dr. D.Y.Patil School of Engineering, Lohegaon, Maharashtra India
  • Shubham Sharma  Department of Computer Engineering, Dr. D.Y.Patil School of Engineering, Lohegaon, Maharashtra India
  • Swati Balyan  Department of Computer Engineering, Dr. D.Y.Patil School of Engineering, Lohegaon, Maharashtra India
  • Tanisha Jaiswal  Department of Computer Engineering, Dr. D.Y.Patil School of Engineering, Lohegaon, Maharashtra India
  • Dr. Pankaj Agarkar  Head of Department , Department of Computer Engineering, Dr. D.Y.Patil School of Engineering, Lohegaon, Maharashtra India
  • Prof. Pooja Shinde  Professor, Department of Computer Engineering, Dr. D.Y.Patil School of Engineering, Lohegaon, Maharashtra India

Keywords:

With the increase in usage of social media platforms, bullying and trolling has burgeoned proportionately. The sole reason for this is that there is no surveilling authority on these platforms. To add to that, anonymity protects the identity of these bullies. Anyone from kids to teenagers to adults can fall prey to trolling. This paper focuses on using AI/ML algorithms to invigilate and report such bullies and further take actions depending on the severity of the threat imposed by them. We will be introducing lexical, aggression, syntactic and sentiment analyzers to examine a tweet and determine if it was meant to be a troll or not. The output of these analyzers will be then fed to classifier algorithms such as Naive Bayes algorithm, K-mean, to segregate these tweets based on their toxicity rating.

Abstract

With the increase in usage of social media platforms, bullying and trolling has burgeoned proportionately. The sole reason for this is that there is no surveilling authority on these platforms. To add to that, anonymity protects the identity of these bullies. Anyone from kids to teenagers to adults can fall prey to trolling. This paper focuses on using AI/ML algorithms to invigilate and report such bullies and further take actions depending on the severity of the threat imposed by them. We will be introducing lexical, aggression, syntactic and sentiment analyzers to examine a tweet and determine if it was meant to be a troll or not. The output of these analyzers will be then fed to classifier algorithms such as Naive Bayes algorithm, K-mean, to segregate these tweets based on their toxicity rating.

References

  1. Zannettou, S.; Sirivianos, M.; Caulfield, T.; Stringhini, G.; De Cristofaro, E.; Blackburn, J. Disinformation warfare: Understanding state-sponsored trolls on twitter and their influence on the web. In Proceedings of the Web Conference 2019—Companion of the World Wide Web Conference, WWW 2019, San Francisco, CA, USA, 13–17 May 2019; pp. 218–226.
  2. Badawy, A.; Lerman, K.; Ferrara, E. Who falls for online political manipulation? In Proceedings of the Web Conference 2019—Companion of the World Wide Web Conference, San Francisco, CA, USA, 13–17 May 2019; pp. 162–168.
  3. Fornacciari, P.; Mordonini, M.; Poggi, A.; Sani, L.; Tomaiuolo, M. A holistic system for troll detection on Twitter. Comput. Hum. Behav. 2018, 89, 258–268.
  4. Donath, J.S. Identity and deception in the virtual community. In Communities in Cyberspace; Routledge: Abingdon-on-Thames, UK, 2002; pp. 37–68.
  5. Chun, S.A.; Holowczak, R.; Dharan, K.N.; Wang, R.; Basu, S.; Geller, J. Detecting political bias trolls in Twitter data. In Proceedings of the 15th International Conference on Web Information Systems and Technologies, WEBIST 2019, Vienna, Austria, 18–20 September 2019; pp. 334–342.
  6. “https://perspectiveapi.com/”, last retrieved on 10th January 2017.
  7. “https://jigsaw.google.com/projects/#conversation-ai”, last retrieved on 14th March 2017.
  8. “http://www.telegraph.co.uk/technology/internetsecurity/10283665/Worlds-first-anti-trolling-software-launchedin-UK.html”, last retrieved on 10th October 2017.
  9. “https://www.networkworld.com/article/2225302/opensourcesubnet/introducing-the-world-s-first--anti-trolling-software- .html” ,last retrieved on 10th October 2017.
  10. “http://www.wired.co.uk/article/twitter-tools-harassment”, last retrieved on 10th October 2017.
  11. “http://www.dailymail.co.uk/sciencetech/article-3506068/Istrolling-Facebook-working-troll-hunter-tool-lets-catchimpersonators-social-network.html”,last retrieved on 10th October 2017.
  12. “https://thinkprogress.org/microsofts-lovable-teen-chatbotturned-racist-troll-proves-how-badly-silicon-valley-needsdiversity-1648e7020ea6#.dwoymxuwj”,last retrieved on 21st March 2017.
  13. “http://www.tabletmag.com/scroll/219117/we-built-a-bot-thattrolls-twitters-worst-anti-semitic-trolls”, last retrieved on 21st March 2017.
  14. “World’s first anti-trolling software' launched in UK”, “http://www.telegraph.co.uk/technology/internetsecurity/10283665/Worlds-first-anti-trolling-software-launchedin-UK.html”, last retrieved on 20th March 2017.
  15. Phillips, Whitney; Publication Information: Cambridge, Massachusetts: The MIT Press. 2015 This Is Why We Can't Have Nice Things: Mapping the Relationship Between Online Trolling and Mainstream Culture.

International Journal of Scientific Research in Science and Technology

Downloads

Published

2020-12-18

Issue

Volume 5, Issue 8, November-December-2020

Section

Research Articles

License

Copyright (c) IJSRST

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

How to Cite

[1]
Saloni Dangre, Shubham Sharma, Swati Balyan, Tanisha Jaiswal, Dr. Pankaj Agarkar, Prof. Pooja Shinde, " Troll Detection and Anti-Trolling Solution using Artificial Intelligence/ Machine Learning, International Journal of Scientific Research in Science and Technology(IJSRST), Online ISSN : 2395-602X, Print ISSN : 2395-6011, Volume 5, Issue 8, pp.53-58, November-December-2020.