Skip to main content
Springer Nature Link
Log in

A two-stage cyberbullying detection based on multi-view features and decision fusion strategy

  • Published:
Applied Intelligence Aims and scope Submit manuscript

Abstract

Cyberbullying has emerged as a pressing concern across various social platforms due to the escalating usage of online networks. Cyberbullying may lead victims to depression, self-harm, and even suicide. In this research, a two-stage cyberbullying detection framework based on multi-view features and decision fusion strategies is proposed. The first stage is to discover cyberbullying texts in social media, and the second stage delves into categorizing the specific forms of bullying present in the identified texts. In the two-stage detection process, features are constructed from multiple views, including Content view, Profanity view, and User view, to portray the bullying behavior. Furthermore, a decision fusion strategy is designed, incorporating both single-view features and multi-view features to enhance detection effectiveness. Finally, the research explains the complex mechanism of multi-view features in two-stage cyberbullying detection by calculating their SHAP values. The experimental results demonstrate the effectiveness of the multi-view feature and decision fusion strategy in cyberbullying detection. Notably, this framework yields impressive results, boasting an F1-score of 89.66% and an AUC of 95.98% in Stage I, while achieving an F1-score of 74.25% and an Accuracy of 79.01% in Stage II. The interpretability analysis of features affirms the pivotal role played by multi-view features, with the Content view features emerging as especially significant in the pursuit of effective cyberbullying detection.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12

Similar content being viewed by others

Explore related subjects

Discover the latest articles, news and stories from top researchers in related subjects.

Data availability

The data that support the findings of this study can be published publicly with the accompanying paper. The data is available at: https://pan.baidu.com/s/1vx3dy9q5Da353WMDSeTpfQ?pwd=ggwh Extraction code: ggwh.

Notes

  1. https://weibo.com/

  2. https://service.account.weibo.com/roles/xizeNote: Log in to your Weibo account to view.

  3. https://service.account.weibo.com/?type=6&status=4Note: Log in to your Weibo account to view.

  4. https://www.noswearing.com/

  5. https://baike.baidu.com/item/%E6%96%B0%E6%B5%AA%E5%BE%AE%E5%8D%9A%E8%AE%A4%E8%AF%81/8998254?fr=aladdin

  6. https://pan.baidu.com/s/1vx3dy9q5Da353WMDSeTpfQ?pwd=ggwh Extraction code: ggwh.

References

  1. Wang N, Lv X (2022) Research on the Evolution and Prediction of Cyber Violence Incidents. Inf Res 1:73–81

    MATH  Google Scholar 

  2. Zhou J, Zhao H, Zou Y (2024) Cyberbullying and Traditional Bullying Victimization, Depressive Symptoms, and Suicidal Ideation Among Chinese Early Adolescents: Cognitive Reappraisal and Emotion Invalidation as Moderators. Soc Sci Comput Rev 42:512–534

    Article  Google Scholar 

  3. Wang X (2020) An Analysis of the Linguistic Form and Pan Entertainment Phenomenon of Cyberbullying Language. World Scie Res J 6:16–23

    MATH  Google Scholar 

  4. Yi P, Zubiaga A (2022) Cyberbullying detection across social media platforms via platform-aware adversarial encoding. In: Proceedings of the International AAAI Conference on Web and Social Media. pp 1430–1434

  5. Al-Harigy LM, Al-Nuaim HA, Moradpoor N, Tan Z (2022) Building towards automated cyberbullying detection: A comparative analysis. Comput Intell Neurosci 1:4794227

    Google Scholar 

  6. Jacob RP, Manoj K, Mohan D, et al (2022) Cyberbullying Detection and Prevention Using Artificial Intelligence. In: Ranganathan G, Fernando X, Shi F, El Allioui Y (eds) Soft Computing for Security Applications. pp 905–914

  7. Chia ZL, Ptaszynski M, Masui F et al (2021) Machine Learning and feature engineering-based study into sarcasm and irony classification with application to cyberbullying detection. Inf Process Manage 58:102600

    Article  Google Scholar 

  8. Eronen J, Ptaszynski M, Masui F et al (2021) Improving classifier training efficiency for automatic cyberbullying detection with feature density. Inf Process Manage 58:102616

    Article  MATH  Google Scholar 

  9. Mahbub S, Pardede E, Kayes ASM (2021) Detection of Harassment Type of Cyberbullying: A Dictionary of Approach Words and Its Impact. Secur Commun Netw 1:5594175

    Google Scholar 

  10. Al-Hashedi M, Soon L-K, Goh H-N et al (2023) Cyberbullying Detection Based on Emotion. IEEE Access 11:53907–53918

    Article  Google Scholar 

  11. Li T, Zeng Z, Li Q, Sun S (2024) Integrating GIN-based multimodal feature transformation and multi-feature combination voting for irony-aware cyberbullying detection. Inf Process Manage 61:103651

    Article  MATH  Google Scholar 

  12. Zhu C, Huang S, Evans R, Zhang W (2021) Cyberbullying Among Adolescents and Children: A Comprehensive Review of the Global Situation, Risk Factors, and Preventive Measures. Front Public Health 9:634909

    Article  Google Scholar 

  13. Agustiningsih N, YusufAhsan A (2023) Types of Cyberbullying Experienced by Adolescents. Malays J Med Health Sci 19:99–103

    Google Scholar 

  14. Bozyiğit A, Utku S, Nasibov E (2021) Cyberbullying detection: Utilizing social media features. Expert Syst Appl 179:115001

    Article  MATH  Google Scholar 

  15. Maity K, Saha S, Bhattacharyya P (2022) Emoji, sentiment and emotion aided cyberbullying detection in hinglish. IEEE Transact Comput Soc Syst 10(5):2411–2420

    Article  MATH  Google Scholar 

  16. Yadav J, Kumar D, Chauhan D (2020) Cyberbullying detection using pre-trained bert model. In: 2020 International Conference on Electronics and Sustainable Communication Systems (ICESC). pp 1096–1100

  17. Paul S, Saha S (2022) CyberBERT: BERT for cyberbullying identification: BERT for cyberbullying identification. Multimedia Syst 28:1897–1904

    Article  MATH  Google Scholar 

  18. Khanna P, Mathur A, Chandra A, Kumar A (2021) Multimodal cyberbullying detection using ensemble learning. In: Artificial Intelligence and Sustainable Computing for Smart City: First International Conference. pp 221–229

  19. Saeidi M, daSousaMilios SBE et al (2020) Categorizing online harassment on Twitter. Mach Learn Knowl Discov Databases: Int Workshops ECML PKDD 2019:283–297

    MATH  Google Scholar 

  20. Balakrishnan V, Khan S, Arabnia HR (2020) Improving cyberbullying detection using Twitter users’ psychological features and machine learning. Comput Secur 90:101710

    Article  MATH  Google Scholar 

  21. Bharti S, Yadav AK, Kumar M, Yadav D (2021) Cyberbullying detection from tweets using deep learning. Kybernetes 51:2695–2711

    Article  MATH  Google Scholar 

  22. Murshed BAH, Abawajy J, Mallappa S et al (2022) DEA-RNN: A Hybrid Deep Learning Approach for Cyberbullying Detection in Twitter Social Media Platform. IEEE Access 10:25857–25871

    Article  Google Scholar 

  23. Li T, Zeng Z, Sun J, Sun S (2022) Using data mining technology to analyse the spatiotemporal public opinion of COVID-19 vaccine on social media. Electron Libr 40(4):435–452

    Article  MATH  Google Scholar 

  24. Blair SJ, Bi Y, Mulvenna MD (2020) Aggregated topic models for increasing social media topic coherence. Appl Intell 50:138–156

    Article  Google Scholar 

  25. Schodt KB, Quiroz SI, Wheeler B et al (2021) Cyberbullying and Mental Health in Adults: The Moderating Role of Social Media Use and Gender. Front Psych 12:674298

    Article  Google Scholar 

  26. Marr KL, Duell MN (2021) Cyberbullying and cybervictimization: Does gender matter? Psychol Rep 124:577–595

    Article  MATH  Google Scholar 

  27. Sahoo SR, Gupta BB (2021) Multiple features based approach for automatic fake news detection on social networks using deep learning. Appl Soft Comput 100:106983

    Article  MATH  Google Scholar 

  28. Sansonetti G, Gasparetti F, D’aniello G, Micarelli A (2020) Unreliable users detection in social media: Deep learning techniques for automatic detection. IEEE Access 8:213154–213167

    Article  MATH  Google Scholar 

  29. Yin M, Wang J, Zhu D, Gao C (2023) A two-stage approach for identifying and interpreting self-admitted technical debt. Appl Intell 53:26592–26602

    Article  MATH  Google Scholar 

  30. Mangalathu S, Hwang S-H, Jeon J-S (2020) Failure mode and effects analysis of RC members based on machine-learning-based SHapley Additive exPlanations (SHAP) approach. Eng Struct 219:110927

    Article  Google Scholar 

  31. Li T, Zeng Z, Sun S, Sun J (2024) A novel integrated framework based on multi-view features for multidimensional social bot detection. J Inf Sci 50(5):1148–1169

  32. Muneer A, Fati SM (2020) A comparative analysis of machine learning techniques for cyberbullying detection on twitter. Future Internet 12:187

    Article  MATH  Google Scholar 

  33. Plaza-del-Arco FM, Molina-González MD, Urena-López LA, Martín-Valdivia MT (2021) Comparing pre-trained language models for Spanish hate speech detection. Expert Syst Appl 166:114120

    Article  MATH  Google Scholar 

  34. Tolba M, Ouadfel S, Meshoul S (2021) Hybrid ensemble approaches to online harassment detection in highly imbalanced data. Expert Syst Appl 175:114751

    Article  Google Scholar 

  35. Shah C, Du Q, Xu Y (2022) Enhanced TabNet: Attentive interpretable tabular learning for hyperspectral image classification. Remote Sens 14:716

    Article  MATH  Google Scholar 

  36. Zeng Z, Li T, Sun S et al (2022) A novel semi-supervised self-training method based on resampling for Twitter fake account identification. Data Technol Appl 56:409–428

    MATH  Google Scholar 

Download references

Acknowledgements

This work was supported by the National Social Science Fund of China (Grant numbers: 22&ZD324).

Author information

Authors and Affiliations

  1. School of Information Management, Wuhan University, Wuhan, 430072, China

    Tingting Li, Ziming Zeng & Shouqiang Sun

  2. School of Economics and Finance, Chongqing University of Technology, Chongqing, 400054, China

    Tingting Li

  3. Center for Studies of Information Resources, Wuhan University, Wuhan, 430072, China

    Ziming Zeng

Authors
  1. Tingting Li
    View author publications

    You can also search for this author inPubMed Google Scholar

  2. Ziming Zeng
    View author publications

    You can also search for this author inPubMed Google Scholar

  3. Shouqiang Sun
    View author publications

    You can also search for this author inPubMed Google Scholar

Contributions

Tingting Li: Writing—original draft, Data curation, Methodology, Investigation. Ziming Zeng: Writing—review & editing. Shouqiang Sun: Writing—review & editing.

Corresponding author

Correspondence to Ziming Zeng.

Ethics declarations

Ethical and informed consent for data used

This article does not contain any study on human participants or animals performed by any of the authors.

Competing interests

This manuscript has not been published or presented elsewhere and is not under consideration by another journal. We have read and understood your journal’s policies, and we believe that neither the manuscript nor the study violates any of these. All authors have checked the manuscript and agreed to the submission. There are no conflicts of interest to declare.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Appendix 1

Appendix 1

See Appendix Table 10.

Table 10 The description of the algorithm parameters
Full size table

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Li, T., Zeng, Z. & Sun, S. A two-stage cyberbullying detection based on multi-view features and decision fusion strategy. Appl Intell 55, 294 (2025). https://doi.org/10.1007/s10489-024-06049-x

Download citation

  • Accepted:

  • Published:

  • DOI: https://doi.org/10.1007/s10489-024-06049-x

Keywords