Proceedings

PI-Bully: Personalized Cyberbullying Detection with Peer Influence

Download BibTeX Cite

Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence. AI for Improving Human Well-being. Pages 5829-5835.

https://doi.org/10.24963/ijcai.2019/808

© 2019 International Joint Conferences on Artificial Intelligence

Abstract

Cyberbullying has become one of the most pressing online risks for adolescents and has raised serious concerns in society. Recent years have witnessed a surge in research aimed at developing principled learning models to detect cyberbullying behaviors. These efforts have primarily focused on building a single generic classification model to differentiate bullying content from normal (non-bullying) content among all users. These models treat users equally and overlook idiosyncratic information about users that might facilitate the accurate detection of cyberbullying. In this paper, we propose a personalized cyberbullying detection framework, PI-Bully, that draws on empirical findings from psychology highlighting unique characteristics of victims and bullies and peer influence from like-minded users as predictors of cyberbullying behaviors. Our framework is novel in its ability to model peer influence in a collaborative environment and tailor cyberbullying prediction for each individual user. Extensive experimental evaluations on real-world datasets corroborate the effectiveness of the proposed framework.

  1. [Al-garadi et al., 2016] Mohammed Ali Al-garadi, Kas- turi Dewi Varathan, and Sri Devi Ravana. Cybercrime de- tection in online communications: The experimental case of cyberbullying detection in the twitter network. Comput- ers in Human Behavior, 63:433-443, 2016.
  2. [Anava and Levy, 2016] Oren Anava and Kfir Levy. k*- nearest neighbors: From global to local. In NIPS, pages 4916-4924, 2016.
  3. [Baughman et al., 2012] Holly M Baughman, Sylvia Dear- ing, Erica Giammarco, and Philip A Vernon. Relation- ships between bullying behaviours and the dark triad: A study with adults. Personality and Individual Differences, 52(5):571-575, 2012.
  4. [Beck and Teboulle, 2009] Amir Beck and Marc Teboulle. A fast iterative shrinkage-thresholding algorithm for linear inverse problems. SIIMS, 2(1):183-202, 2009.
  5. [Bellmore et al., 2015] Amy Bellmore, Angela J Calvin, Jun-Ming Xu, and Xiaojin Zhu. The five w's of "bullying" on twitter: who, what, why, where, and when. Computers in human behavior, 44:305-314, 2015.
  6. [Boyd et al., 2011] Stephen Boyd, Neal Parikh, Eric Chu, Borja Peleato, and Jonathan Eckstein. Distributed opti- mization and statistical learning via the alternating direc- tion method of multipliers. Foundations and Trends R in Machine Learning, 3(1):1-122, 2011.
  7. [Cheng et al., 2019] Lu Cheng, Jundong Li, Yasin Silva, Deborah Hall, and Huan Liu. Xbully: Cyberbullying de- tection within a multi-modal context. In WSDM, pages 339-347, 2019.
  8. [Dadvar et al., 2013] Maral Dadvar, Dolf Trieschnigg, Roe- land Ordelman, and Franciska de Jong. Improving cyber- bullying detection with user context. In ECIR, pages 693- 696, 2013.
  9. [Dani et al., 2017] Harsh Dani, Jundong Li, and Huan Liu. Sentiment informed cyberbullying detection in social me- dia. In ECML PKDD, pages 52-67, 2017.
  10. [Dinakar et al., 2011] Karthik Dinakar, Roi Reichart, and Henry Lieberman. Modeling the detection of textual cy- berbullying. The Social Mobile Web, 11(02), 2011.
  11. [Espelage et al., 2003] Dorothy L Espelage, Melissa K Holt, and Rachael R Henkel. Examination of peer-group con- textual effects on aggression during early adolescence. Child development, 74(1):205-220, 2003.
  12. [Goodboy and Martin, 2015] Alan K Goodboy and Matthew M Martin. The personality profile of a cy- berbully: Examining the dark triad. Computers in human behavior, 49:1-4, 2015.
  13. [Gradinger et al., 2011] Petra Gradinger, Dagmar Strohmeier, and Christiane Spiel. Motives for bully- ing others in cyberspace. Cyberbullying in the global playground: Research from international perspectives, 263, 2011.
  14. [Hallac et al., 2015] David Hallac, Jure Leskovec, and Stephen Boyd. Network lasso: Clustering and optimiza- tion in large graphs. In KDD, pages 387-396, 2015.
  15. [Hinduja and Patchin, 2013] Sameer Hinduja and Justin W Patchin. Social influences on cyberbullying behaviors among middle and high school students. Journal of youth and adolescence, 42(5):711-722, 2013.
  16. [Hosseinmardi et al., 2015] Homa Hosseinmardi, Sab- rina Arredondo Mattson, Rahat Ibn Rafiq, Richard Han, Qin Lv, and Shivakant Mishra. Analyzing labeled cyber- bullying incidents on the instagram social network. In SocInfo, pages 49-66, 2015.
  17. [Kowalski et al., 2014] Robin M Kowalski, Gary W Giumetti, Amber N Schroeder, and Micah R Lattan- ner. Bullying in the digital age: A critical review and meta-analysis of cyberbullying research among youth., 2014.
  18. [Li et al., 2014] Homa Hosseinmardi Shaosong Li, Zhili Yang, Qin Lv, Rahat Ibn Rafiq Richard Han, and Shiv- akant Mishra. A comparison of common users across in- stagram and ask. fm to better understand cyberbullying. In BdCloud, pages 355-362, 2014.
  19. [Li et al., 2017] Jundong Li, Kewei Cheng, Suhang Wang, Fred Morstatter, Robert P Trevino, Jiliang Tang, and Huan Liu. Feature selection: A data perspective. CSUR, 50(6):94, 2017.
  20. [Nand et al., 2016] Parma Nand, Rivindu Perera, and Abhi- jeet Kasture. " how bullying is this message?": A psy- chometric thermometer for bullying. In COLING, pages 695-706, 2016.
  21. [Pennebaker et al., 2001] James W Pennebaker, Martha E Francis, and Roger J Booth. Linguistic inquiry and word count: Liwc 2001. Mahway: Lawrence Erlbaum Asso- ciates, 71(2001):2001, 2001.
  22. [Rafiq et al., 2016] Rahat Ibn Rafiq, Homa Hosseinmardi, Sabrina Arredondo Mattson, Richard Han, Qin Lv, and Shivakant Mishra. Analysis and detection of labeled cy- berbullying instances in vine, a video-based social net- work. Social Network Analysis and Mining, 6(1):88, 2016.
  23. [Silva et al., 2016a] Yasin N. Silva, Christopher Rich, Jaime Chon, and Lisa M. Tsosie. Bullyblocker: An app to iden- tify cyberbullying in facebook. In ASONAM 2016,, pages 1401-1405, 2016.
  24. [Silva et al., 2016b] Yasin N. Silva, Christopher Rich, and Deborah Hall. Bullyblocker: Towards the identification of cyberbullying in social networking sites. In ASONAM 2016, pages 1377-1379, 2016.
  25. [Smith, 2012] Peter K Smith. Cyberbullying and cyber ag- gression. In Handbook of school violence and school safety, pages 111-121. Routledge, 2012.
  26. [Squicciarini et al., 2015] A Squicciarini, S Rajtmajer, Y Liu, and Christopher Griffin. Identification and charac- terization of cyberbullying dynamics in an online social network. In ASONAM, pages 280-285, 2015.
  27. [Wu and Huang, 2016] Fangzhao Wu and Yongfeng Huang. Personalized microblog sentiment classification via multi- task learning. In AAAI, pages 3059-3065, 2016.
  28. [Xu et al., 2012] Jun-Ming Xu, Kwang-Sung Jun, Xiaojin Zhu, and Amy Bellmore. Learning from bullying traces in social media. In NAACL HLT, pages 656-666, 2012.

References were extracted automatically from the PDF and may contain errors.

Welcome Future Conferences AI Journal Division IJCAI Proceedings About IJCAI IJCAI Awards