mlsanityData to 7 Oct 2026

Cyberbullying Detection for Low-resource Languages and Dialects: Review of the State of the Art

arXiv 2308.15745 ↗First posted 30 Aug 2023cs.CLcited by 8

Not on the map. Why?

Abstract (arXiv)

The struggle of social media platforms to moderate content in a timely manner, encourages users to abuse such platforms to spread vulgar or abusive language, which, when performed repeatedly becomes cyberbullying a social problem taking place in virtual environments, yet with real-world consequences, such as depression, withdrawal, or even suicide attempts of its victims. Systems for the automatic detection and mitigation of cyberbullying have been developed but, unfortunately, the vast majority of them are for the English language, with only a handful available for low-resource languages. To estimate the present state of research and recognize the needs for further development, in this paper we present a comprehensive systematic survey of studies done so far for automatic cyberbullying detection in low-resource languages. We analyzed all studies on this topic that were available. We investigated more than seventy published studies on automatic detection of cyberbullying or related language in low-resource languages and dialects that were published between around 2017 and January 2023. There are 23 low-resource languages and dialects covered by this paper, including Bangla, Hindi, Dravidian languages and others. In the survey, we identify some of the research gaps of previous studies, which include the lack of reliable definitions of cyberbullying and its relevant subcategories, biases in the acquisition, and annotation of data. Based on recognizing those research gaps, we provide some suggestions for improving the general research conduct in cyberbullying detection, with a primary focus on low-resource languages. Based on those proposed suggestions, we collect and release a cyberbullying dataset in the Chittagonian dialect of Bangla and propose a number of initial ML solutions trained on that dataset. In addition, pre-trained transformer-based the BanglaBERT model was also attempted.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Builds on 36 of its 171 references that are in the map. First posted on arXiv 30 Aug 2023.

Builds on

36 of 171 references.

References · 36

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2019Unsupervised Cross-lingual Representation Learning at Scalecited by 3,907
  3. 2019ALBERT: A Lite BERT for Self-supervised Learning of Language Representationscited by 2,772
  4. 2020The State and Fate of Linguistic Diversity and Inclusion in the NLP Worldcited by 789
  5. 2017Deep Learning for Hate Speech Detection in Tweetscited by 180
  6. 2020TLDR: Extreme Summarization of Scientific Documentscited by 136
  7. 2021BanglaBERT: Language Model Pretraining and Benchmarks for Low-Resource Language Understanding Evaluation in Banglacited by 123
  8. 2020Toxic Language Detection in Social Media for Brazilian Portuguese: New Dataset and Multilingual Analysiscited by 45
  9. 2016Text Classification Improved by Integrating Bidirectional LSTM with Two-dimensional Max Poolingcited by 39
  10. 2021Overview of the HASOC track at FIRE 2020: Hate Speech and Offensive Content Identification in Indo-European Languagescited by 38
  11. 2020Hate Speech detection in the Bengali language: A dataset and its baseline evaluationcited by 37
  12. 2021DeepHate: Hate Speech Detection via Multi-Faceted Text Representationscited by 29
24 more
  1. 2021Cross-lingual Offensive Language Identification for Low Resource Languages: The Case of Marathicited by 28
  2. 2023Zero-shot cross-lingual transfer language selection using linguistic similaritycited by 28
  3. 2020DeepHateExplainer: Explainable Hate Speech Detection in Under-resourced Bengali Languagecited by 26
  4. 2021A Large-scale Dataset for Hate Speech Detection on Vietnamese Social Media Textscited by 25
  5. 2023Adapting Multilingual Speech Representation Model for a New, Underresourced Language through Multilingual Fine-tuning and Continued Pretrainingcited by 18
  6. 2021Constructive and Toxic Speech Detection for Open-domain Social Media Comments in Vietnamesecited by 17
  7. 2018Cyberbullying Detection in Social Networks Using Deep Learning Based Models; A Reproducibility Studycited by 14
  8. 2020To BAN or not to BAN: Bayesian Attention Networks for Reliable Hate Speech Detectioncited by 9
  9. 2021NLP-CUET@DravidianLangTech-EACL2021: Offensive Language Detection from Multilingual Code-Mixed Text using Transformerscited by 9
  10. 2021Hate-Alert@DravidianLangTech-EACL2021: Ensembling strategies for Transformer-based Offensive language Detectioncited by 8
  11. 2022Transfer Language Selection for Zero-Shot Cross-Lingual Abusive Language Detectioncited by 8
  12. 2019Hate Speech Detection on Vietnamese Social Media Text using the Bi-GRU-LSTM-CNN Modelcited by 7
  13. 2019Hate Speech Detection on Vietnamese Social Media Text using the Bidirectional-LSTM Modelcited by 7
  14. 2021Fine-tuning of Pre-trained Transformers for Hate, Offensive, and Profane Content Detection in English and Marathicited by 6
  15. 2021Offense Detection in Dravidian Languages using Code-Mixing Index based Focal Losscited by 6
  16. 2021Abusive and Threatening Language Detection in Urdu using Boosting based and BERT based models: A Comparative Approachcited by 6
  17. 2021Retweet communities reveal the main sources of hate speechcited by 5
  18. 2021Towards Offensive Language Identification for Tamil Code-Mixed YouTube Comments and Postscited by 4
  19. 2022Offensive Language Detection in Under-resourced Algerian Dialectal Arabic Languagecited by 4
  20. 2021Ceasing hate withMoH: Hate Speech Detection in Hindi-English Code-Switched Languagecited by 3
  21. 2021Improving Classifier Training Efficiency for Automatic Cyberbullying Detection with Feature Densitycited by 3
  22. 2022OneAligner: Zero-shot Cross-lingual Transfer with One Rich-Resource Language Pair for Low-Resource Sentence Retrievalcited by 3
  23. 2021Offensive Language Detection with BERT-based models, By Customizing Attention Probabilitiescited by 2
  24. 2020NAYEL at SemEval-2020 Task 12: TF/IDF-Based Approach for Automatic Offensive Language Detection in Arabic Tweetscited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 1; 2024: 2; 2025: 1; 2026: 4.

8 papers.

  1. 2023Toxic language detection: a systematic review of Arabic datasetscited by 3
  2. 2024A Survey on Automatic Online Hate Speech Detection in Low-Resource Languagescited by 2
  3. 2024A Graph Neural Architecture Search Approach for Identifying Bots in Social Mediacited by 1
  4. 2025Chinese Cyberbullying Detection: Dataset, Method, and Validationcited by 1
  5. 2026Using Machine Learning to Enhance the Detection of Obfuscated Abusive Words in Swahili: A Focus on Child Safetycited by 0
  6. 2026A Fusion of context-aware based BanglaBERT and Two-Layer Stacked LSTM Framework for Multi-Label Cyberbullying Detectioncited by 0
  7. 2026HMS-BERT: Hybrid Multi-Task Self-Training for Multilingual and Multi-Label Cyberbullying Detectioncited by 0
  8. 2026Can Artificial Intelligence Support Healthcare and Mental Health Through Early Cyberbullying Detection ? The Impact of Emotion-Aware AI on Proactive Online Safetycited by 0