Abstract
Social media has revolutionized communication, allowing people worldwide to connect and interact instantly. However, it has also led to increases in cyberbullying, which poses a significant threat to children and adolescents globally, affecting their mental health and well-being. It is critical to accurately detect the roles of individuals involved in cyberbullying incidents to effectively address the issue on a large scale. This study explores the use of machine learning models to detect the roles involved in cyberbullying interactions. After examining the AMiCA dataset and addressing class imbalance issues, we evaluate the performance of various models built with four underlying LLMs (i.e. BERT, RoBERTa, T5, and GPT-2) for role detection. Our analysis shows that oversampling techniques help improve model performance. The best model, a fine-tuned RoBERTa using oversampled data, achieved an overall F1 score of 83.5%, increasing to 89.3% after applying a prediction threshold. The top-2 F1 score without thresholding was 95.7%. Our method outperforms previously proposed models. After investigating the per-class model performance and confidence scores, we show that the models perform well in classes with more samples and less contextual confusion (e.g. Bystander Other), but struggle with classes with fewer samples (e.g. Bystander Assistant) and more contextual ambiguity (e.g. Harasser and Victim). This work highlights current strengths and limitations in the development of accurate models with limited data and complex scenarios.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Bastiaensens, S., Vandebosch, H., Poels, K., Van Cleemput, K., DeSmet, A., De Bourdeaudhuij, I.: ‘Can i afford to help?’ how affordances of communication modalities guide bystanders’ helping intentions towards harassment on social network sites. Behav. Inf. Technol. 34(4), 425–435 (2015)
Cheng, L., Guo, R., Silva, Y., Hall, D., Liu, H.: Hierarchical attention networks for cyberbullying detection on the instagram social network. In: Proceedings of the 2019 SIAM International Conference on Data Mining (SDM), pp. 235–243. Society for Industrial and Applied Mathematics (2019). https://doi.org/10.1137/1.9781611975673.27
Cheng, L., Guo, R., Silva, Y.N., Hall, D., Liu, H.: Modeling temporal patterns of cyberbullying detection with hierarchical attention networks. ACM/IMS Trans. Data Sci. 2(2) (2021)
Cheng, L., Li, J., Silva, Y., Hall, D., Liu, H.: PI-bully: personalized cyberbullying detection with peer influence. In: Electronic Proceedings of IJCAI 2019, pp. 5829–5835 (2019)
Dadvar, M., de Jong, F., Ordelman, R., Trieschnigg, R.: Improved cyberbullying detection using gender information. In: Proceedings of the Twelfth Dutch-Belgian Information Retrieval Workshop (DIR 2012), pp. 23–25. Ghent University, Belgium (2012)
Dadvar, M., Eckert, K.: Cyberbullying detection in social networks using deep learning based models; a reproducibility study. arXiv preprint arXiv:1812.08046 (2018)
Dang, J., Liu, L.: Me and others around: the roles of personal and social norms in Chinese adolescent bystanders’ responses toward cyberbullying. J. Interpersonal Violence 37(9-10), NP6329–NP6354 (2022). https://doi.org/10.1177/0886260520967128. pMID: 33073678
Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: Bert: pre-training of deep bidirectional transformers for language understanding (2019)
Hamlett, M., Powell, G., Silva, Y.N., Hall, D.: A labeled dataset for investigating cyberbullying content patterns in instagram. In: Proceedings of the International AAAI Conference on Web and Social Media, vol. 16, no. 1, pp. 1251–1258 (2022). https://doi.org/10.1609/icwsm.v16i1.19376
He, H., Bai, Y., Garcia, E.A., Li, S.: Adasyn: adaptive synthetic sampling approach for imbalanced learning. In: 2008 IEEE International Joint Conference on Neural Networks (IEEE World Congress on Computational Intelligence), pp. 1322–1328 (2008). https://doi.org/10.1109/IJCNN.2008.4633969
Jacobs, G., Van Hee, C., Hoste, V.: Automatic classification of participant roles in cyberbullying: can we detect victims, bullies, and bystanders in social media text? Nat. Lang. Eng. 28(2), 141–166 (2022)
Loureiro, D., Barbieri, F., Neves, L., Anke, L.E., Camacho-Collados, J.: Timelms: diachronic language models from twitter (2022)
Orue, I., Fernández-González, L., Machimbarrena, J.M., González-Cabrera, J., Calvete, E.: Bidirectional relationships between cyberbystanders’ roles, cyberbullying perpetration, and justification of violence. Youth Soc. 55(4), 611–629 (2023). https://doi.org/10.1177/0044118X211053356
Radford, A., Wu, J., Child, R., Luan, D., Amodei, D., Sutskever, I.: Language models are unsupervised multitask learners (2019)
Raffel, C., et al.: Exploring the limits of transfer learning with a unified text-to-text transformer (2023)
Rathnayake, G., Atapattu, T., Herath, M., Zhang, G., Falkner, K.: Enhancing the identification of cyberbullying through participant roles. In: Proceedings of the Fourth Workshop on Online Abuse and Harms, pp. 89–94. Association for Computational Linguistics (2020)
Salmivalli, C.: Participant roles in bullying: how can peer bystanders be utilized in interventions? Theory Into Pract. 53(4), 286–292 (2014)
Salmivalli, C., Lagerspetz, K., Björkqvist, K., Österman, K., Kaukiainen, A.: Bullying as a group process: participant roles and their relations to social status within the group. Aggressive Behav. 22(1), 1–15 (1996)
Sanh, V., Debut, L., Chaumond, J., Wolf, T.: Distilbert, a distilled version of bert: smaller, faster, cheaper and lighter (2020)
Singh, V.K., Ghosh, S., Jose, C.: Toward multimodal cyberbullying detection. In: Proceedings of the 2017 CHI Conference Extended Abstracts on Human Factors in Computing Systems, pp. 2090–2099. Association for Computing Machinery (2017)
Teng, T.H., Varathan, K.D.: Cyberbullying detection in social networks: a comparison between machine learning and transfer learning approaches. IEEE Access (2023)
Van Hee, C., et al.: Automatic detection of cyberbullying in social media text. PLoS ONE 13(10), e0203794 (2018)
Wang, K., Xiong, Q., Wu, C., Gao, M., Yu, Y.: Multi-modal cyberbullying detection on social networks. In: 2020 International Joint Conference on Neural Networks (IJCNN), pp. 1–8 (2020)
Xu, J.M., Jun, K.S., Zhu, X., Bellmore, A.: Learning from bullying traces in social media. In: Proceedings of the 2012 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp. 656–666. NAACL HLT 2012. Association for Computational Linguistics, USA (2012)
Ziems, C., Vigfusson, Y., Morstatter, F.: Aggressive, repetitive, intentional, visible, and imbalanced: Refining representations for cyberbullying classification. CoRR abs/2004.01820 (2020). https://arxiv.org/abs/2004.01820
Acknowledgments
This work was supported by NSF Awards #2227488 and #1719722 and a Google Award for Inclusion Research.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2025 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Sandoval, M., Abuhamad, M., Furman, P., Nazari, M., Hall, D.L., Silva, Y.N. (2025). Identifying Cyberbullying Roles in Social Media. In: Aiello, L.M., Chakraborty, T., Gaito, S. (eds) Social Networks Analysis and Mining. ASONAM 2024. Lecture Notes in Computer Science, vol 15213. Springer, Cham. https://doi.org/10.1007/978-3-031-78548-1_26
Download citation
DOI: https://doi.org/10.1007/978-3-031-78548-1_26
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-78547-4
Online ISBN: 978-3-031-78548-1
eBook Packages: Computer ScienceComputer Science (R0)