Abstract
With the increase of social media platforms such as Facebook, Twitter, and YouTube, individuals from diverse cultures and societal backgrounds can communicate and express their viewpoints on several aspects of daily life. However, due to the differences in these cultures, along with the freedom of expression, hateful and offensive speech has increased and spread on these platforms. The detection of hate speech has significantly increased the interest of researchers in natural language processing (NLP). The OSACT5 shared task provides a new dataset that aims to detect the offensive language in addition to identifying the type of hate speech on Arabic social media. However, the available dataset is unbalanced, which leads to low performance, especially in the F1 score. Therefore, in this paper, we focused on overcoming such a problem by augmenting the text data. We fine-tuned and evaluated various pre-trained deep learning models in addition to augmenting the data to achieve the best performance. We observed that data augmentation increases the F1 score. After fine-tuning the QARiB model and augmenting the data we achieved the best F1 score of 0.49.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Aljarah, I., et al.: Intelligent detection of hate speech in Arabic social network: a machine learning approach. J. Inf. Sci. 0165551520917651 (2020)
Salem, F.: Social media and the internet of things towards data-driven policymaking in the arab world: potential, limits and concerns. In: The Arab Social Media Report, p. 7. MBR School of Government, Dubai (2017)
Alrehili, A.: Automatic hate speech detection on social media: a brief survey. In: 2019 IEEE/ACS 16th International Conference on Computer Systems and Applications (AICCSA), pp. 1–6. IEEE (2019)
Fortuna, P., Nunes, S.: A survey on automatic detection of hate speech in text. ACM Comput. Surv. (CSUR) 51(4), 1–30 (2018)
Watanabe, H., Bouazizi, M., Ohtsuki, T.: Hate speech on twitter: a pragmatic approach to collect hateful and offensive expressions and perform hate speech detection. IEEE Access 6, 13825–13835 (2018)
Müller, K., Schwarz, C.: Fanning the flames of hate: social media and hate crime. In: Report, Competitive Advantage in the Global Economy (CAGE) (2018)
Waseem, Z., Hovy, D.: Hateful symbols or hateful people? predictive features for hate speech detection on twitter. In: Proceedings of the NAACL Student Research Workshop, pp. 88–93 (2016)
Alsafari, S., Sadaoui, S., Mouhoub, M.: Hate and offensive speech detection on Arabic social media. Online Soc. Netw. Media 19, 100096 (2020)
Basile, V., et al.: Semeval-2019 task 5: multilingual detection of hate speech against immigrants and women in twitter. In: Proceedings of the 13th International Workshop on Semantic Evaluation, pp. 54–63 (2019)
Zampieri, M., et al.: Semeval-2020 task 12: multilingual offensive language identification in social media (offenseval 2020). arXiv preprint arXiv:2006.07235 (2020)
Mubarak, H., Al-Khalifa, H., Al-Thubaity, A.: Overview of osact5 shared task on Arabic offensive language and hate speech detection. In: Proceedings of the 5th Workshop on Open-Source Arabic Corpora and Processing Tools with Shared Tasks on Qur’an QA and Fine-Grained Hate Speech Detection, pp. 162–166 (2022)
Al-Hassan, A., Al-Dossari, H.: Detection of hate speech in social networks: a survey on multilingual corpus. In: 6th International Conference on Computer Science and Information Technology, vol. 10, pp. 10–5121 (2019)
Mansur, Z., Omar, N., Tiun, S.: Twitter hate speech detection: a systematic review of methods, taxonomy analysis, challenges, and opportunities. IEEE Access (2023)
Sanguinetti, M., Poletto, F., Bosco, C., Patti, V., Stranisci, M.: An Italian twitter corpus of hate speech against immigrants. In: Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018) (2018)
Mubarak, H., Hassan, S., Absar Chowdhury, S.: Emojis as anchors to detect Arabic offensive language and hate speech. arXiv preprint arXiv:2201.06723 (2022)
Ousidhoum, N., Lin, Z., Zhang, H., Song, Y., Yeung, D.-Y.: Multilingual and multi-aspect hate speech analysis. arXiv preprint arXiv:1908.11049 (2019)
Al-Hassan, A., Al-Dossari, H.: Detection of hate speech in Arabic tweets using deep learning. Multim. Syst. 1–12 (2021)
Alsafari, S., Sadaoui, S., Mouhoub, M.: Deep learning ensembles for hate speech detection. In: 2020 IEEE 32nd International Conference on Tools with Artificial Intelligence (ICTAI), pp. 526–531. IEEE (2020)
AlKhamissi, B., Diab, M.: Meta AI at Arabic hate speech 2022: multitask learning with self-correction for hate speech classification. arXiv preprint arXiv:2205.07960 (2022)
Bennessir, M.A., Rhouma, M., Haddad, H., Fourati, C.: Icompass at Arabic hate speech 2022: detect hate speech using GRNN and transformers. In: Proceedings of the 5th Workshop on Open-Source Arabic Corpora and Processing Tools with Shared Tasks on Qur’an QA and Fine-Grained Hate Speech Detection, pp. 176–180 (2022)
Makram, K., et al.: Chillax-at Arabic hate speech 2022: a hybrid machine learning and transformers based model to detect Arabic offensive and hate speech. In: Proceedings of the 5th Workshop on Open-Source Arabic Corpora and Processing Tools with Shared Tasks on Qur’an QA and Fine-Grained Hate Speech Detection, pp. 194–199 (2022)
Alzubi, S., Ferreira, T.C., Pavanelli, L., Al-Badrashiny, M.: Aixplain at Arabic hate speech 2022: an ensemble based approach to detecting offensive tweets. In: Proceedings of the 5th Workshop on Open-Source Arabic Corpora and Processing Tools with Shared Tasks on Qur’an QA and Fine-Grained Hate Speech Detection, pp. 214–217 (2022)
Antoun, W., Baly, F., Hajj, H.: Arabert: transformer-based model for Arabic language understanding. In: LREC 2020 Workshop Language Resources and Evaluation Conference 11–16 May 2020, p. 9 (2020)
Alammary, A.S.: Bert models for Arabic text classification: a systematic review. Appl. Sci. 12(11), 5720 (2022)
Abdul-Mageed, M., Elmadany, A., Billah Nagoudi, E.M.: Arbert & marbert: deep bidirectional transformers for Arabic. arXiv preprint arXiv:2101.01785 (2020)
Devlin, J., Chang, M.-W., Lee, K., Toutanova, K.: Bert: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)
Abdelali, A., Hassan, S., Mubarak, H., Darwish, K., Samih, Y.: Pre-training bert on Arabic tweets: practical considerations. arXiv preprint arXiv:2102.10684 (2021)
El-Khair, I.A.: 1.5 billion words Arabic corpus. arXiv preprint arXiv:1611.04033 (2016)
Lison, P., Tiedemann, J.: Opensubtitles 2016: extracting large parallel corpora from movie and tv subtitles (2016)
Wolf, T., et al.: Huggingface’s transformers: state-of-the-art natural language processing. arXiv preprint arXiv:1910.03771 (2019)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Batarfi, H.A., Alsaedi, O.A., Wali, A.M., Jamal, A.T. (2023). Impact of Data Augmentation on Hate Speech Detection. In: Krieger, U.R., Eichler, G., Erfurth, C., Fahrnberger, G. (eds) Innovations for Community Services. I4CS 2023. Communications in Computer and Information Science, vol 1876. Springer, Cham. https://doi.org/10.1007/978-3-031-40852-6_10
Download citation
DOI: https://doi.org/10.1007/978-3-031-40852-6_10
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-40851-9
Online ISBN: 978-3-031-40852-6
eBook Packages: Computer ScienceComputer Science (R0)