Classification and Detection of Amharic Language Fake News on Social Media Using Machine Learning Approach


  • Kedir Lemma Arega School of Technology and Informatics, Department of Information Technology, Ambo University, Ethiopia



The pervasive idea of web-based media stages brought about a lot of sight and sound information in interpersonal organizations. The transparency and unlimited way of sharing the data via online media stage encourages data spread across the organization paying little mind to its noteworthiness.The multiplication of misdirecting data in regular access news sources, for example, web-based media channels, news websites, and online papers has made it trying to recognize dependable news sources, in this way expanding the requirement for computational devices to give bits of knowledge into the unwavering quality of online substance. The broad spread of phony news contrarily affects people and society. Along these lines, counterfeit news identification via web-based media has as of late become arising research drawing in enormous consideration. Observing the possible damage caused by the rapid spread of fake news in various fields such as politics and finance, the use of language analysis to automatically identify fake news has attracted the attention of the research community. A social networking service is a platform for people with similar interests, activities,or backgrounds to form social networks or social relations. Participants who register on this site with its own expression (often a profile) and social links are generally offered a social network service.


Amharic fake news detection; Amharic posts and comments datasets; Classification; Machine learning; Social media


[1] Fikremariam, Genet Mezemir, 2009. Automatic Stemming for Amharic Text: An Experiment Using Successor Variety Approach. pp. 1-79.

[2] Kelemework, Worku, 2013. Automatic Amharic text news classification: Aneural networks approach.Ethiop. J. Sci. & Technol. Vol. 6, pp. 127-137.

[3] Bajaj, Samir, 2017. Fake News Detection Using Deep Learning. Stanford University: cs 224n.

[4] Srinivas Rao Pulluri, Jayadev Gyani, Narsimha Gugulothu, 2017. A Comprehensive Model for Detecting Fake Profiles in Online Social Networks. International Journal of Advanced Research in Science and Engineering. Vol. 6, pp. 1-10.

[5] Ver´onica P´erez-Rosas, Bennett Kleinberg, Alexandra Lefevre, August 20-26, 2018. Automatic Detection of Fake News. Santa Fe, New Mexico, USA. s.n.

[6] 2018. Proceedings of the 27th International Conference on Computational Linguistics. pp.3391-3401.

[7] Lorent, Simon. 2018-2019. Fake News Detection Using Machine. pp. 1-91.

[8] O’Brien, Nicole, 2018. Machine Learning for Detection of Fake News. pp. 1-56.

[9] Ajeet Ram Pathaka, Aditee Mahajana, Keshav Singha, Aishwarya Patila, Anusha Naira, 2019.Analysis of Techniques for Rumor Detection in Social Media.International Conference on Computational Intelligence and Data Science (ICCIDS 2019). pp. 1-11.

[10] Sachin Ingle, Satish Borade, Sagar Awasare,2019. Detecting Fake User Accounts on. IJARIIE-ISSN(O)-2395-4396. pp. 927-931.

[11] Defar, Yonas Kenenisa. 2019. Hate Speech Detection for Amharic Language on Social Media Using Machine Learning Techniques. pp. 1-103.

[12] Lu, Y.J., Li, Ch.T., 2020. GCAN: Graph-aware Co-Attention Networks. arXiv, Vol. 1, pp. 1-10.

[13] Md Zobaer Hossainy, Md Ashraful Rahmany, Md Saiful Islam, Sudipta Kar. Bangla,BanFakeNews: A Dataset for Detecting Fake News in. 2020, University of Houston, Texas,USA. pp. 1-10.

[14] Arega, Kedir Lemma, 6, 2020. Social Media Fake Account Detection for Amharic Language.Global Scientific Journals. Vol. 8, pp. 604-614.

[15] Josef Kapusta, Petr Hajek, Michal Munk, Lubomir Benko, 2020. Comparison of fake and real news based on morphological analysis. ELSEVIER. pp. 1-9.

[16] Kai Shuy, Amy Slivaz, Suhang Wangy, Jiliang Tang,Huan Liuy. Fake News Detection on Social Media:A Data Mining Perspective.


How to Cite

Arega, K. L. (2022). Classification and Detection of Amharic Language Fake News on Social Media Using Machine Learning Approach. Electrical Science & Engineering, 4(1), 1–6.


Article Type