Social media platforms enable rapid communication, information sharing, and opinion expression. However, their misuse for hate speech targeting race, religion and political differences has become a growing concern. This issue is particularly sensitive for underrepresented languages like Amharic, a Semitic language with the second-largest number of speakers after Arabic and the working language of Ethiopia. This study addresses the challenge of detecting hate speech in Amharic text by analyzing posts and comments from Facebook, YouTube, and Twitter. A dataset of 7,590 labeled entries was collected using the Face pager tool, focusing on hate speech related to race, religion, politics, and neutral content. The dataset was annotated with the guidance of researchers, legal experts, and language specialists. Preprocessing techniques, including data cleaning, tokenization, and normalization, were applied, and feature extraction was performed using embedding layers. The dataset was split into training (80%), validation (10%), and testing (10%) sets. Several deep learning models LSTM, BiLSTM, GRU, BiGRU, and RoBERTa were developed and evaluated using precision, recall, F1-score, and accuracy metrics. The RoBERTa model outperformed others, achieving an accuracy of 91%. This research highlights the effectiveness of advanced deep learning techniques in detecting Amharic hate speech, offering a valuable tool for mitigating this critical issue in Ethiopian social media contexts.
| Published in | American Journal of Artificial Intelligence (Volume 9, Issue 1) |
| DOI | 10.11648/j.ajai.20250901.12 |
| Page(s) | 16-21 |
| Creative Commons |
This is an Open Access article, distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution and reproduction in any medium or format, provided the original work is properly cited. |
| Copyright |
Copyright © The Author(s), 2025. Published by Science Publishing Group |
Ge’ez, Fidel, LSTM, BiLSTM, GRU, BiGRU
| [1] | Y. Kenenisa and T. Melak, “Adama, Ethiopia, September 2019,” Hate Speech Detect. Amharic Lang. Soc. Media Using Mach. Learn. Tech. By, vol. Unpublishe, pp. 1-103, 2019. |
| [2] | Z. Mossie and J. Wang, “SOCIAL NETWORK HATE SPEECH,” pp. 41-55, 2018. |
| [3] | B. Emuye, “Amharic Text Hate Speech Detection in Social Media Using Deep Learning Approach,” no. july, 2020. |
| [4] | N. Albadi, M. Kurdi, and S. Mishra, “Are They Our Brothers ? Analysis and Detection of Religious Hate Speech in the Arabic Twittersphere,” 2018. |
| [5] | B. Gambäck and U. K. Sikdar, “Using Convolutional Neural Networks to Classify Hate Speech,” no. 7491, pp. 85-90, 2017. |
| [6] | M. Zampieri, “Detecting Hate Speech in Social Media,” pp. 467-472, 2017. |
| [7] | Z. Mossie and J. Wang, “SOCIAL NETWORK HATE SPEECH,” no. April, 2018, |
| [8] | S. Teferra and W. Menzel, “Automatic Speech Recognition for an Under-Resourced Language-Amharic.” |
| [9] | F. A. Melat, “Hate Speech Detection for Amharic Language on Facebook Using Deep Learning,” pp. 1-23, 2022. |
| [10] | A. G. Debele and M. M. Woldeyohannis, “Multimodal Amharic Hate Speech Detection Using Deep Learning,” 2022 Int. Conf. Inf. Commun. Technol. Dev. Africa, ICT4DA 2022, no. December, pp. 102-107, 2022, |
| [11] | S. G. Tesfaye and K. Kakeba, “Automated Amharic Hate Speech Posts and Comments Detection Model Using Recurrent Neural Network,” 2020, |
| [12] | M. Bhardwaj, M. S. Akhtar, A. Ekbal, A. Das, and T. Chakraborty, “Hostility Detection Dataset in Hindi,” Nov. 2020, [Online]. Available: |
| [13] | C. Ozgur, T. Colliau, G. Rogers, Z. Hughes, E. " Bennie, and " Myer-Tyson, “The Selection of Independent Variables for A Multiple Regression Problem Using LASSO methods,” 2017. [Online]. Available: |
APA Style
Wondie, B. K., Tadesse, E. M., Yirdaw, T. W. (2025). Amharic Language Hate Speech Detection on Social Media. American Journal of Artificial Intelligence, 9(1), 16-21. https://doi.org/10.11648/j.ajai.20250901.12
ACS Style
Wondie, B. K.; Tadesse, E. M.; Yirdaw, T. W. Amharic Language Hate Speech Detection on Social Media. Am. J. Artif. Intell. 2025, 9(1), 16-21. doi: 10.11648/j.ajai.20250901.12
Share This Article
Twitter
Linked In
Facebook
Copy
Download@article{10.11648/j.ajai.20250901.12,
author = {Beyene Kassa Wondie and Ermias Melku Tadesse and Tarekegn Walle Yirdaw},
title = {Amharic Language Hate Speech Detection on Social Media
},
journal = {American Journal of Artificial Intelligence},
volume = {9},
number = {1},
pages = {16-21},
doi = {10.11648/j.ajai.20250901.12},
url = {https://doi.org/10.11648/j.ajai.20250901.12},
eprint = {https://article.sciencepublishinggroup.com/pdf/10.11648.j.ajai.20250901.12},
abstract = {Social media platforms enable rapid communication, information sharing, and opinion expression. However, their misuse for hate speech targeting race, religion and political differences has become a growing concern. This issue is particularly sensitive for underrepresented languages like Amharic, a Semitic language with the second-largest number of speakers after Arabic and the working language of Ethiopia. This study addresses the challenge of detecting hate speech in Amharic text by analyzing posts and comments from Facebook, YouTube, and Twitter. A dataset of 7,590 labeled entries was collected using the Face pager tool, focusing on hate speech related to race, religion, politics, and neutral content. The dataset was annotated with the guidance of researchers, legal experts, and language specialists. Preprocessing techniques, including data cleaning, tokenization, and normalization, were applied, and feature extraction was performed using embedding layers. The dataset was split into training (80%), validation (10%), and testing (10%) sets. Several deep learning models LSTM, BiLSTM, GRU, BiGRU, and RoBERTa were developed and evaluated using precision, recall, F1-score, and accuracy metrics. The RoBERTa model outperformed others, achieving an accuracy of 91%. This research highlights the effectiveness of advanced deep learning techniques in detecting Amharic hate speech, offering a valuable tool for mitigating this critical issue in Ethiopian social media contexts.
},
year = {2025}
}
TY - JOUR T1 - Amharic Language Hate Speech Detection on Social Media AU - Beyene Kassa Wondie AU - Ermias Melku Tadesse AU - Tarekegn Walle Yirdaw Y1 - 2025/05/09 PY - 2025 N1 - https://doi.org/10.11648/j.ajai.20250901.12 DO - 10.11648/j.ajai.20250901.12 T2 - American Journal of Artificial Intelligence JF - American Journal of Artificial Intelligence JO - American Journal of Artificial Intelligence SP - 16 EP - 21 PB - Science Publishing Group SN - 2639-9733 UR - https://doi.org/10.11648/j.ajai.20250901.12 AB - Social media platforms enable rapid communication, information sharing, and opinion expression. However, their misuse for hate speech targeting race, religion and political differences has become a growing concern. This issue is particularly sensitive for underrepresented languages like Amharic, a Semitic language with the second-largest number of speakers after Arabic and the working language of Ethiopia. This study addresses the challenge of detecting hate speech in Amharic text by analyzing posts and comments from Facebook, YouTube, and Twitter. A dataset of 7,590 labeled entries was collected using the Face pager tool, focusing on hate speech related to race, religion, politics, and neutral content. The dataset was annotated with the guidance of researchers, legal experts, and language specialists. Preprocessing techniques, including data cleaning, tokenization, and normalization, were applied, and feature extraction was performed using embedding layers. The dataset was split into training (80%), validation (10%), and testing (10%) sets. Several deep learning models LSTM, BiLSTM, GRU, BiGRU, and RoBERTa were developed and evaluated using precision, recall, F1-score, and accuracy metrics. The RoBERTa model outperformed others, achieving an accuracy of 91%. This research highlights the effectiveness of advanced deep learning techniques in detecting Amharic hate speech, offering a valuable tool for mitigating this critical issue in Ethiopian social media contexts. VL - 9 IS - 1 ER -
Department of Information System, Kombolcha Institute of Technology, Wollo University, Kombolcha, Ethiopia
Department of Information Technology, Kombolcha Institute of Technology, Wollo University, Kombolcha, Ethiopia
Department of Information System, Kombolcha Institute of Technology, Wollo University, Kombolcha, Ethiopia
Information