A Review of Key Technologies for the Analysis and Classification of Social Media Hate Speech Content.

Yingjie Liu; Chen Gong; Xingyue Ma

doi:10.54097/n8w8j896

Authors

Yingjie Liu
Chen Gong
Xingyue Ma

DOI:

https://doi.org/10.54097/n8w8j896

Keywords:

Hate Speech Detection; Machine Learning; Deep Learning; Multimodal Analysis.

Abstract

With the explosive growth of social media content and the enhanced information-sharing capabilities of platforms, the proliferation of online hate speech has become a global governance challenge. Its dissemination patterns are rapidly evolving towards multimodality (the deep integration of text and images), further complicating content security management. On one hand, the subtlety and strong contextual dependence of hate speech significantly increase the difficulty of detection. On the other hand, emerging forms of dissemination, such as meme images, present dual challenges for classification tasks due to their inherent characteristics: a seemingly humorous facade, reliance on cultural context, and semantic conflicts between text and image. To address these issues, this paper focuses on two major technical approaches: unimodal text analysis and multimodal content classification. It provides a systematic review of the research progress in hate speech detection methods based on text and multimodal detection methods, while also analyzing their limitations. Furthermore, this paper consolidates the characteristics and applicable scenarios of current mainstream unimodal and multimodal hate speech datasets, offering reference directions for optimizing technical approaches and constructing datasets in subsequent research.

Downloads

Download data is not yet available.

References

[1] Blaya C. Cyberhate: A review and content analysis of intervention strategies[J]. Aggression and violent behavior, 2019, 45: 163-172.

[2] Talat Z, Hovy D. Hateful symbols or hateful people? predictive features for hate speech detection on twitter[C]//Proceedings of the NAACL student research workshop. 2016: 88-93.

[3] Rozental A, Biton D. Amobee at SemEval-2019 tasks 5 and 6: Multiple choice CNN over contextual embedding[J]. arxiv preprint arxiv:1904.08292, 2019.

[4] Mandl T, Modha S, Majumder P, et al. Overview of the hasoc track at fire 2019: Hate speech and offensive content identification in indo-european languages[C]//Proceedings of the 11th annual meeting of the Forum for Information Retrieval Evaluation. 2019: 14-17.

[5] Wang B, Ding H. YNU NLP at SemEval-2019 task 5: Attention and capsule ensemble for identifying hate speech[C]//Proceedings of the 13th International Workshop on Semantic Evaluation. 2019: 529-534.

[6] Yang X, Obadinma S, Zhao H, et al. SemEval-2020 task 5: Counterfactual recognition[J]. arxiv preprint arxiv:2008.00563, 2020.

[7] Zampieri M, Malmasi S, Nakov P, et al. Semeval-2019 task 6: Identifying and categorizing offensive language in social media (offenseval)[J]. arxiv preprint arxiv:1903.08983, 2019.

[8] Guest E, Vidgen B, Mittos A, et al. An expert annotated dataset for the detection of online misogyny[C]//Proceedings of the 16th conference of the European chapter of the association for computational linguistics: main volume. 2021: 1336-1350. 2021

[9] Mulki H, Haddad H, Ali C B, et al. L-hsab: A levantine twitter dataset for hate speech and abusive language[C]//Proceedings of the third workshop on abusive language online. 2019: 111-118.

[10] Kiela D, Firooz H, Mohan A, et al. The hateful memes challenge: Detecting hate speech in multimodal memes[J]. Advances in neural information processing systems, 2020, 33: 2611-2624.

[11] Pàmies M, Öhman E, Kajava K, et al. LT@ Helsinki at SemEval-2020 Task 12: Multilingual or language-specific BERT?[J]. arxiv preprint arxiv:2008.00805, 2020.

[12] Hossain E, Sharif O, Hoque M M, et al. Deciphering hate: identifying hateful memes and their targets[J]. arxiv preprint arxiv:2403.10829, 2024.

[13] Suryawanshi S, Chakravarthi B R, Arcan M, et al. Multimodal meme dataset (MultiOFF) for identifying offensive content in image and text[C]//Proceedings of the second workshop on trolling, aggression and cyberbullying. 2020: 32-41.

[14] Wu J, Hong Q, Cao M, et al. A group consensus-based travel destination evaluation method with online reviews[J]. Applied Intelligence, 2022, 52(2): 1306-1324.

[15] Rodriguez A, Argueta C, Chen Y L. Automatic detection of hate speech on facebook using sentiment and emotion analysis[C]//2019 international conference on artificial intelligence in information and communication (ICAIIC). IEEE, 2019: 169-174.

[16] [19] Al-Garadi M A, Hussain M R, Khan N, et al. Predicting cyberbullying on social media in the big data era using machine learning algorithms: review of literature and open challenges[J]. IEEE Access, 2019, 7: 70701-70718.

[17] Weir G, Owoeye K, Oberacker A, et al. Cloud-based textual analysis as a basis for document classification[C]//2018 International Conference on High Performance Computing & Simulation (HPCS). IEEE, 2018: 672-676.

[18] Nurce E, Keci J, Derczynski L. Detecting abusive albanian[J]. arxiv preprint arxiv:2107.13592, 2021.

[19] Albadi,N.,M.Kurdi,andS.Mishra.Aretheyourbrothers?analysisanddetection ofreligioushatespeechinthearabictwittersphere.in2018IEEE/ACM InternationalConferenceonAdvancesinSocialNetworksAnalysisandMining (ASONAM).2018.IEEE.

[20] Davidson T, Warmsley D, Macy M, et al. Automated hate speech detection and the problem of offensive language[C]//Proceedings of the international AAAI conference on web and social media. 2017, 11(1): 512-515.

[21] Mollas I, Chrysopoulou Z, Karlos S, et al. ETHOS: a multi-label hate speech detection dataset[J]. Complex & Intelligent Systems, 2022, 8(6): 4663-4678.

[22] Wiegand M, Siegel M, Ruppenhofer J. Overview of the germeval 2018 shared task on the identification of offensive language[J]. 2018. 2018

[23] Gitari N D, Zu** Z, Damien H, et al. A lexicon-based approach for hate speech detection[J]. International Journal of Multimedia and Ubiquitous Engineering, 2015, 10(4): 215-230.

[24] Liao W, Zeng B, Yin X, et al. An improved aspect-category sentiment analysis model for text sentiment analysis based on RoBERTa[J]. Applied Intelligence, 2021, 51: 3522-3533. Appl Intell, 2021

[25] Fersini E, Rosso P, Anzovino M. Overview of the task on automatic misogyny identification at IberEval 2018[J]. Ibereval@ sepln, 2018, 2150: 214-228.

[26] Salminen J, Almerekhi H, Milenković M, et al. Anatomy of online hate: develo** a taxonomy and machine learning models for identifying and classifying hate in online news media[C]//Proceedings of the International AAAI Conference on Web and Social Media. 2018, 12(1). 2018

[27] Salminen J, Almerekhi H, Milenković M, et al. Anatomy of online hate: develo** a taxonomy and machine learning models for identifying and classifying hate in online news media[C]//Proceedings of the International AAAI Conference on Web and Social Media. 2018, 12(1)

[28] Pitsilis G K, Ramampiaro H, Langseth H. Detecting offensive language in tweets using deep learning[J]. arxiv preprint arxiv:1801.04433, 2018.

[29] Fu E, **ang J, **ong C. Deep Learning Techniques for Sentiment Analysis[J]. Highlights in Science, Engineering and Technology, 2022, 16: 1-7.

[30] Vaswani A, Shazeer N, Parmar N, et al. Attention is all you need[J]. Advances in neural information processing systems, 2017, 30.

[31] Kennedy C J, Bacon G, Sahn A, et al. Constructing interval variables via faceted rasch measurement and multitask deep learning: a hate speech application[J]. arxiv preprint arxiv:2009.10277, 2020.

[32] Pavlopoulos J, Sorensen J, Laugier L, et al. SemEval-2021 task 5: Toxic spans detection[C]//Proceedings of the 15th international workshop on semantic evaluation (SemEval-2021). 2021: 59-69.

[33] Mathew B, Saha P, Yimam S M, et al. Hatexplain: A benchmark dataset for explainable hate speech detection[C]//Proceedings of the AAAI conference on artificial intelligence. 2021, 35(17): 14867-14875. 2021

[34] De la Peña Sarracén G L, Rosso P. Unsupervised embeddings with graph auto-encoders for multi-domain and multilingual hate speech detection[C]//Proceedings of the Thirteenth Language Resources and Evaluation Conference. 2022: 2196-2204. 2196～2204

[35] Gandhi A, Adhvaryu K, Khanduja V. Multimodal sentiment analysis: review, application domains and future directions[C]//2021 IEEE Pune section international conference (PuneCon). IEEE, 2021: 1-5.

[36] Krizhevsky A, Sutskever I, Hinton G E. Imagenet classification with deep convolutional neural networks[J]. Advances in neural information processing systems, 2012, 25.

[37] Lan Z, Chen M, Goodman S, et al. Albert: A lite bert for self-supervised learning of language representations[J]. arxiv preprint arxiv:1909.11942, 2019.

[38] Howard J, Ruder S. Universal language model fine-tuning for text classification[J]. arxiv preprint arxiv:1801.06146, 2018.

[39] Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition[J]. arxiv preprint arxiv:1409.1556, 2014.

[40] He K, Zhang X, Ren S, et al. Deep residual learning for image recognition[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2016: 770-778.

[41] Huang G, Liu Z, Van Der Maaten L, et al. Densely connected convolutional networks[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2017: 4700-4708. 4700～4708

[42] Gomez R, Gibert J, Gomez L, et al. Exploring hate speech detection in multimodal publications[C]//Proceedings of the IEEE/CVF winter conference on applications of computer vision. 2020: 1470-1478.

[43] Chen Y C, Li L, Yu L, et al. Uniter: Universal image-text representation learning[C]//European conference on computer vision. Cham: Springer International Publishing, 2020: 104-120.