Skip to main content

Automated Offensive Comment Detection for the Romanian Language

  • Conference paper
  • First Online:
AI Approaches for Designing and Evaluating Interactive Intelligent Systems (ROCHI 2022)

Abstract

Offensive language can lead to uncomfortable situations, psychological harm, and, in particular cases, even violence. Social networks and websites struggle to reduce the prevalence of these messages by using an automated detector. One goal of Human-computer interaction (HCI) sciences is to provide respectful, safe, and user-friendly systems. This extends to any form of computer-mediated social interaction. This chapter contributes to this objective by proposing a Romanian language dataset for offensive message detection. We manually annotated 4,052 comments on a Romanian local news website into one of the following classes: non-offensive, targeted insults, racist, homophobic, and sexist. In addition, we establish a baseline of five automated classifiers, out of which the model based on RoBERT and two layers of CNN achieves the highest performance with a weighted F1-score of 74.74%.

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

Access this chapter

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

Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Similar content being viewed by others

Notes

  1. 1.

    https://github.com/readerbench/news-ro-offense (Accessed on 27th November 2023).

  2. 2.

    https://www.statista.com/topics/7134/social-media-usage-in-romania (Accessed on 27th November 2023).

  3. 3.

    https://www.trafic.ro/vizitatori/top-siteuri-stiri-massmedia/luna-martie-2022-pg1 (Accessed on 17th October 2023).

  4. 4.

    https://www.ranks.nl/stopwords/romanian (Accessed on 15th November 2023).

  5. 5.

    https://spacy.io/models/ro Accessed on 27th November 2023.

  6. 6.

    https://github.com/readerbench/ReaderBench (Accessed on 27th November 2023).

  7. 7.

    Slur for Roma people.

References

  1. T. Akiba, S. Sano, T. Yanase, T. Ohta, M. Koyama, Optuna: a next-generation hyperparameter optimization framework, in Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining

    Google Scholar 

  2. R. Akula, I. Garibay, Interpretable multi-head self-attention architecture for sarcasm detection in social media. Entropy 23(4), 394 (2021)

    Article  Google Scholar 

  3. I. Alfina, R. Mulia, M.I. Fanany, Y. Ekanata, Hate speech detection in the indonesian language: A dataset and preliminary study, in 2017 International Conference on Advanced Computer Science and Information Systems (ICACSIS) (IEEE, 2017), pp. 233–238

    Google Scholar 

  4. F. Alkomah, X. Ma, A literature review of textual hate speech detection methods and datasets. Information 13(6), 273 (2022)

    Article  Google Scholar 

  5. R. Alshalan, H. Al-Khalifa, D. Alsaeed, H. Al-Baity, S. Alshalan et al., Detection of hate speech in covid-19-related tweets in the arab region: deep learning and topic modeling approach. J. Med. Internet Res. 22(12), e22609 (2020)

    Article  Google Scholar 

  6. P. Bojanowski, É. Grave, A. Joulin, T. Mikolov, Enriching word vectors with subword information. Trans. Assoc. Comput. Linguist. 5, 135–146 (2017)

    Article  Google Scholar 

  7. T. Caselli, A. Schelhaas, M. Weultjes, F. Leistra, H. van der Veen, G. Timmerman, M. Nissim, Dalc: the dutch abusive language corpus, in Proceedings of the 5th Workshop on Online Abuse and Harms (WOAH 2021) (2021), pp. 54–66

    Google Scholar 

  8. F. Celli, M. Lai, A. Duzha, C. Bosco, V. Patti, Policycorpus xl: An italian corpus for the detection of hate speech against politics, in Proceedings of the Eighth Italian Conference on Computational Linguistics, CLiC-it 2021, Milan, Italy, January 26–28, 2022. Volume 3033 (2021), pp. 56–62

    Google Scholar 

  9. B.R. Chakravarthi, R. Priyadharshini, V. Muralidaran, N. Jose, S. Suryawanshi, E. Sherly, J.P. McCrae, Dravidiancodemix: sentiment analysis and offensive language identification dataset for dravidian languages in code-mixed text. Lang. Resour. Eval. 765–806 (2022)

    Google Scholar 

  10. S.A. Chowdhury, H. Mubarak, A. Abdelali, S.g. Jung, B.J. Jansen, J. Salminen, A multi-platform arabic news comment dataset for offensive language detection, in Proceedings of the 12th Language Resources and Evaluation (2020), pp. 6203–6212

    Google Scholar 

  11. M. Cinelli, A. Pelicon, I. Mozetic, W. Quattrociocchi, P.K. Novak, F. Zollo, Online hate: behavioural dynamics and relationship with misinformation. CoRR arXiv:abs/2105.14005 (2021)

  12. A. Cojocaru, A. Paraschiv, M. Dascalu, News-ro-offense—a romanian offensive language dataset and baseline models centered on news article comments, in 19th International Conference on Human-Computer Interaction, RoCHI 2022, Craiova, Romania/Hybrid, October 6–7, 2022, Matrix Rom, ed. by P. Popescu, C. Kolski (2022), pp. 65–72

    Google Scholar 

  13. Ç. Çøltekin, A corpus of turkish offensive language on social media, in Proceedings of the 12th Language Resources and Evaluation Conference, European Language Resources Association (2020), pp. 6174–6184

    Google Scholar 

  14. Z. Dai, Z. Yang, Y. Yang, J. Carbonell, Q.V. Le, R. Salakhutdinov, Transformer-xl: attentive language models beyond a fixed-length context, in Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, Florence, Italy, Association for Computational Linguistics (2019), pp. 2978–2988

    Google Scholar 

  15. T. Davidson, D. Warmsley, M. Macy, I. Weber, Automated hate speech detection and the problem of offensive language, in Proceedings of the International AAAI Conference on Web and Social Media, vol. 11 (2017), pp. 512–515

    Google Scholar 

  16. O. De Gibert, N. Perez, A. García-Pablos, M. Cuadros, Hate speech dataset from a white supremacy forum. arXiv:1809.04444 (2018)

  17. R.P. de Pelle, V.P. Moreira, Offensive comments in the brazilian web: a dataset and baseline results, in Anais do VI Brazilian Workshop on Social Network Analysis and Mining, SBC (2017), pp. 510–519

    Google Scholar 

  18. F. Del Vigna12, A. Cimino23, F. Dell’Orletta, M. Petrocchi, M. Tesconi, Hate me, hate me not: hate speech detection on facebook, in Proceedings of the First Italian Conference on Cybersecurity (ITASEC17) (2017), pp. 86–95

    Google Scholar 

  19. J. Devlin, M.W. Chang, K. Lee, K. Toutanova, Bert: pre-training of deep bidirectional transformers for language understanding, in Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NACL, Volume 1 (Long and Short Papers). ACL 2018, 4171–4186 (2018)

    Google Scholar 

  20. J.L. Fleiss, Measuring nominal scale agreement among many raters. Psychol. Bull. 76(5), 378 (1971)

    Article  Google Scholar 

  21. P. Fortuna, J. Soler-Company, L. Wanner, How well do hate speech, toxicity, abusive and offensive language classification models generalize across datasets? Inf. Process. Manag. 58(3), 102524 (2021)

    Article  Google Scholar 

  22. B. Gambäck, U.K. Sikdar, Using convolutional neural networks to classify hate-speech, in Proceedings of the First Workshop on Abusive Language Online (2017), pp. 85–90

    Google Scholar 

  23. S. Gupta, Z. Waseem, A comparative study of embeddings methods for hate speech detection from tweets, in EMNLP 2018 Workshop on Noisy User Generated Text (Poster presentation, Association for Computational Linguistics, 2017)

    Google Scholar 

  24. V. Gvozdovaitė, A. Naujalytė, J. Mandravickaitė, T. Krilavičius, An overview of the lithuanian hate speech corpus. Int. J. Des. Anal. Tools Integr. Circuits Syst. 54–57 (2020)

    Google Scholar 

  25. A. Hande, R. Priyadharshini, B.R. Chakravarthi, Kancmd: Kannada codemixed dataset for sentiment analysis and offensive language detection, in Proceedings of the Third Workshop on Computational Modeling of People’s Opinions, Personality, and Emotion’s in Social Media (2020), pp. 54–63

    Google Scholar 

  26. B. Kennedy, M. Atari, A.M. Davani, L. Yeh, A. Omrani, Y. Kim, K. Coombs, S. Havaldar, G. Portillo-Wightman, E. Gonzalez, et al., The gab hate corpus: a collection of 27k posts annotated for hate speech (2018)

    Google Scholar 

  27. T.N. Kipf, M. Welling, Semi-supervised classification with graph convolutional networks, in 5th International Conference on Learning Representations, ICLR 2017, Toulon, France, April 24–26, 2017, Conference Track Proceedings, OpenReview.net (2017)

    Google Scholar 

  28. Z. Lan, M. Chen, S. Goodman, K. Gimpel, P. Sharma, R. Soricut, ALBERT: a lite BERT for self-supervised learning of language representations, in 8th International Conference on Learning Representations, ICLR 2020, Addis Ababa, Ethiopia, April 26–30, 2020, OpenReview.net (2020)

    Google Scholar 

  29. S. Li, W. Li, C. Cook, C. Zhu, Y. Gao, Independently recurrent neural network (indrnn): building a longer and deeper RNN, in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2018), pp. 5457–5466

    Google Scholar 

  30. Y. Lin, Y. Meng, X. Sun, Q. Han, K. Kuang, J. Li, F. Wu, Bertgcn: transductive text classification by combining GCN and BERT. CoRR arXiv:abs/2105.05727 (2021)

  31. Y. Liu, M. Ott, N. Goyal, J. Du, M. Joshi, D. Chen, O. Levy, M. Lewis, L. Zettlemoyer, V. Stoyanov, Roberta: a robustly optimized BERT pretraining approach. CoRR arXiv:abs/1907.11692 (2019)

  32. N. Ljubešić, D. Fišer, T. Erjavec, The FRENK datasets of socially unacceptable discourse in slovene and english, in Text, Speech, and Dialogue. ed. by K. Ekštein (Springer International Publishing, Cham, 2019), pp.103–114

    Chapter  Google Scholar 

  33. Z. Lu, P. Du, J.Y. Nie: Vgcn-bert: augmenting bert with graph embedding for text classification, in European Conference on Information Retrieval, Springer (2020), pp. 369–382

    Google Scholar 

  34. M. Manolescu, Ç. Çöltekin, Roff-a romanian twitter dataset for offensive language, in Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2021) (2021), pp. 895–900

    Google Scholar 

  35. M. Masala, S. Ruseti, M. Dascalu, Robert–a romanian bert model, in Proceedings of the 28th International Conference on Computational Linguistics (2020), pp. 6626–6637

    Google Scholar 

  36. T. Mikolov, K. Chen, G. Corrado, J. Dean, Efficient estimation of word representations in vector space, in 1st International Conference on Learning Representations, ICLR 2013, Scottsdale, Arizona, USA, May 2–4, 2013, Workshop Track Proceedings (2013)

    Google Scholar 

  37. M. Mohiyaddeen, S. Siddiqui, Automatic hate speech detection: a literature review. Int. J. Eng. Manag. Res. 11, 116–121 (2021)

    Article  Google Scholar 

  38. I. Mollas, Z. Chrysopoulou, S. Karlos, G. Tsoumakas, Ethos: a multi-label hate speech detection dataset. Complex Intell. Syst. 1–16 (2022)

    Google Scholar 

  39. J.P. Montani, P. Schüller, Tuwienkbs19 at germeval task 2, 2019: ensemble learning for german offensive language detection, in Proceedings of the 15th Conference on Natural Language Processing, KONVENS 2019, Erlangen, Germany, October 9–11, 2019 (2019)

    Google Scholar 

  40. J. Moon, W.I. Cho, J. Lee, Beep! Korean corpus of online news comments for toxic speech detection, in Proceedings of the Eighth International Workshop on Natural Language Processing for Social Media (2020), pp. 25–31

    Google Scholar 

  41. N. Ousidhoum, Z. Lin, H. Zhang, Y. Song, D.Y. Yeung, Multilingual and multi-aspect hate speech analysis, in Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) (2019), pp. 4675–4684

    Google Scholar 

  42. A. Paraschiv, I. Sandu, D.C. Cercel, M. Dascalu, Fighting romanian offensive language with ro-offense: a dataset and classification models for online comments. (under review)

    Google Scholar 

  43. A. Paraschiv, D.C. Cercel, Upb at germeval-2019 task 2: Bert-based offensive language classification of german tweets, in Proceedings of the 15th Conference on Natural Language Processing, KONVENS 2019, Erlangen, Germany, October 9–11, 2019 (2019)

    Google Scholar 

  44. J.H. Park, P. Fung, One-step and two-step classification for abusive language detection on Twitter, in Proceedings of the First Workshop on Abusive Language Online, Vancouver, BC, Canada, Association for Computational Linguistics (August 2017), pp. 41–45

    Google Scholar 

  45. R. Pascanu, T. Mikolov, Y. Bengio, On the difficulty of training recurrent neural networks, in Proceedings of the 30th International Conference on Machine Learning, ICML 2013, Atlanta, GA, USA, 16-21 June 2013. Volume 28 of JMLR Workshop and Conference Proceedings., JMLR.org (2013), pp. 1310–1318

    Google Scholar 

  46. J. Pennington, R. Socher, C.D. Manning: Glove: global vectors for word representation, in Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP) (2014), pp. 1532–1543

    Google Scholar 

  47. H.T. Phan, N.T. Nguyen, D. Hwang, Aspect-level sentiment analysis using CNN over BERT-GCN. IEEE Access 10, 110402–110409 (2022)

    Article  Google Scholar 

  48. T. Pires, E. Schlinger, D. Garrette, How multilingual is multilingual bert, in Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics (2019), pp. 4996–5001

    Google Scholar 

  49. Z. Pitenis, M. Zampieri, T. Ranasinghe, Offensive language identification in greek, in Proceedings of the 12th Language Resources and Evaluation Conference (2020), pp. 5113–5119

    Google Scholar 

  50. G.K. Pitsilis, H. Ramampiaro, H. Langseth, Effective hate-speech detection in twitter data using recurrent neural networks. Appl. Intell. 48(12), 4730–4742 (2018)

    Article  Google Scholar 

  51. F.M. Plaza-del Arco, A. Montejo-Ráez, L.A.U. Lopez, M.T. Martín-Valdivia, Offendes: a new corpus in spanish for offensive language research, in Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2021) (2021), pp. 1096–1108

    Google Scholar 

  52. M. Ptaszynski, A. Pieciukiewicz, P. Dybała, Results of the poleval 2019 shared task 6: first dataset and open shared task for automatic cyberbullying detection in polish twitter, in Proceedings of the PolEval 2019 Workshop, vol. 89 (2019)

    Google Scholar 

  53. J.D. Rennie, L. Shih, J. Teevan, D.R. Karger, Tackling the poor assumptions of naive bayes text classifiers, in Proceedings of the 20th International Conference on Machine Learning (ICML-03) (2003), pp. 616–623

    Google Scholar 

  54. D. Robinson, Z. Zhang, J. Tepper, Hate speech detection on twitter: feature engineering vs feature selection, in European Semantic Web Conference (Springer, 2018), pp. 46–49

    Google Scholar 

  55. S. Rosenthal, P. Atanasova, G. Karadzhov, M. Zampieri, P. Nakov, SOLID: a large-scale semi-supervised dataset for offensive language identification, in Findings of the Association for Computational Linguistics: ACL-IJCNLP, Online, Association for. Computational Linguistics 2021, 915–928 (2021)

    Google Scholar 

  56. A. Safaya, M. Abdullatif, D. Yuret, Kuisail at semeval-2020 task 12: BERT-CNN for offensive speech identification in social media, in Proceedings of the Fourteenth Workshop on Semantic Evaluation (2020), pp. 2054–2059

    Google Scholar 

  57. M. Sanguinetti, F. Poletto, C. Bosco, V. Patti, M. Stranisci, An italian twitter corpus of hate speech against immigrants, in Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018) (2018)

    Google Scholar 

  58. V. Sanh, L. Debut, J. Chaumond, T. Wolf, Distilbert, a distilled version of bert: smaller, faster, cheaper and lighter. CoRR arXiv:abs/1910.01108 (2019)

  59. A. Sharma, A. Kabra, M. Jain, Ceasing hate with moh: hate speech detection in hindi-english code-switched language. Inf. Process. Manag. 59(1), 102760 (2022)

    Article  Google Scholar 

  60. G.I. Sigurbergsson, L. Derczynski, Offensive language and hate speech detection for danish, in Proceedings of the 12th Language Resources and Evaluation Conference (2020), pp. 3498–3508

    Google Scholar 

  61. K. Singh, How to improve class imbalance using class weights in machine learning (2020). https://www.analyticsvidhya.com/blog/2020/10/improve-class-imbalance-class-weights/. Accessed 14 June 2022

  62. E. Spertus, Smokey: automatic recognition of hostile messages, in Proceedings of the Fourteenth National Conference on Artificial Intelligence and Ninth Innovative Applications of Artificial Intelligence Conference, AAAI 97, IAAI 97, July 27–31, 1997, Providence, Rhode Island, USA, AAAI Press/The MIT Press, ed. by B. Kuipers, B.L. Webber (1997), pp. 1058–1065

    Google Scholar 

  63. J.M. Struß, M. Siegel, J. Ruppenhofer, M. Wiegand, M. Klenner, Overview of germeval task 2, 2019 shared task on the identification of offensive language, in Proceedings of the 15th Conference on Natural Language Processing, KONVENS 2019, Erlangen, Germany, October 9–11, 2019 (2019)

    Google Scholar 

  64. A. Sureka, S. Agarwal, Learning to classify hate and extremism promoting tweets. IEEE joint intelligence and security informatics conference. IEEE 2014, 320–320 (2014)

    Google Scholar 

  65. X. Tang, X. Shen, Y. Wang, Y. Yang, Categorizing offensive language in social networks: a chinese corpus, systems and an explanation tool, in China National Conference on Chinese Computational Linguistics (Springer, 2020), pp. 300–315

    Google Scholar 

  66. Twitter-API. https://developer.twitter.com/en/docs (n.d.). Accessed 1 Sept 2022

  67. P. Törnberg, How digital media drive affective polarization through partisan sorting. Proc. Natl. Acad. Sci. 119(42), e2207159119 (2022)

    Article  Google Scholar 

  68. F. Vargas, I. Carvalho, F. Rodrigues de Góes, T. Pardo, F. Benevenuto, HateBR: a large expert annotated corpus of Brazilian Instagram comments for offensive language and hate speech detection, in Proceedings of the Thirteenth Language Resources and Evaluation Conference, Marseille, France, European Language Resources Association (2022), pp. 7174–7183

    Google Scholar 

  69. A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A.N. Gomez, Ł Kaiser, I. Polosukhin, Attention is all you need. Adv. Neural Inf. Process. Syst. 30, 5998–6008 (2017)

    Google Scholar 

  70. Z. Waseem, T. Davidson, D. Warmsley, I. Weber, Understanding abuse: a typology of abusive language detection subtasks. arXiv:1705.09899 (2017)

  71. J. Welbl, A. Glaese, J. Uesato, S. Dathathri, J. Mellor, L.A. Hendricks, K. Anderson, P. Kohli, B. Coppin, P. Huang, Challenges in detoxifying language model, in Findings of the Association for Computational Linguistics: EMNLP, Virtual Event/Punta Cana, Dominican Republic, 16–20 November, 2021, Association for Computational Linguistics, ed. by M. Moens, X. Huang, L. Specia, S.W. Yih 2021, 2447–2469 (2021)

    Google Scholar 

  72. G. Xiang, B. Fan, L. Wang, J. Hong, C. Rose, Detecting offensive tweets via topical feature discovery over a large scale twitter corpus, in Proceedings of the 21st ACM International Conference on Information and Knowledge Management (2012), pp. 1980–1984

    Google Scholar 

  73. Z. Yang, Z. Dai, Y. Yang, J. Carbonell, R.R. Salakhutdinov, Q.V. Le: Xlnet: generalized autoregressive pretraining for language understanding. Adv. Neural Inf. Process. Syst. 32 (2019)

    Google Scholar 

  74. L. Yao, C. Mao, Y. Luo, Graph convolutional networks for text classification, in Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33 (2019), pp. 7370–7377

    Google Scholar 

  75. M. Zampieri, S. Malmasi, P. Nakov, S. Rosenthal, N. Farra, R. Kumar, Predicting the type and target of offensive posts in social media, in Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), Minneapolis, Minnesota, Association for Computational Linguistics (2019), pp. 1415–1420

    Google Scholar 

  76. Y. Zhang, B. Wallace, A sensitivity analysis of (and practitioners’ guide to) convolutional neural networks for sentence classification. arXiv:1510.03820 (2015)

  77. Z. Zhang, D. Robinson, J. Tepper, Hate speech detection using a convolution-lstm based deep neural network. Indones. J. Comput. Cybern. Syst. (IJCCS) 11816, 2546–2553 (2019)

    Google Scholar 

  78. J. Zhao, F. Huang, J. Lv, Y. Duan, Z. Qin, G. Li, G. Tian, Do RNN and LSTM have long memory? in International Conference on Machine Learning, PMLR (2020), pp. 11365–11375

    Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Mihai Dascalu .

Editor information

Editors and Affiliations

Additional information

Disclaimer Please be advised that this paper includes real comments that may be regarded as profane, offensive, or abusive. This inclusion is unavoidable due to the nature of the research topic.

Rights and permissions

Reprints and permissions

Copyright information

© 2024 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Paraschiv, A., Cojocaru, A., Dascalu, M. (2024). Automated Offensive Comment Detection for the Romanian Language. In: Kolski, C., Mihăescu, M.C., Rebedea, T. (eds) AI Approaches for Designing and Evaluating Interactive Intelligent Systems. ROCHI 2022. Learning and Analytics in Intelligent Systems, vol 36. Springer, Cham. https://doi.org/10.1007/978-3-031-53957-2_5

Download citation

Publish with us

Policies and ethics