URDU FAKE NEWS DETECTION USING LSTM AND HYBRID CNN-LSTM MODELS

Sabiha Anum; Sqlain Majeed; Muhammad Nabeel Sarwar

doi:10.71146/kjmr921

Authors

Sabiha Anum Administrative Sciences (Business Management), Boston University (Metropolitan College). Author
Sqlain Majeed Faculty of Computer Science & Information Technology, The Superior University Lahore, Pakistan. Author
Muhammad Nabeel Sarwar Lecturer, Department of Software Engineering, Islamia University of Bahawalpur, Pakistan. Author

DOI:

https://doi.org/10.71146/kjmr921

Keywords:

Fake news Detection, Urdu language, deep learning model, long-short-term memory, UFNDL detection

Abstract

Fake news is an increasing point of interest among the research community as it can be transmitted due to numerous media in one of the shortest periods of time. False information, particularly on those languages that lack substantial resources, has turned into a large issue that is increasingly getting worse due to social media and internet crimes. It is difficult to find fake news in Urdu as it is a complex language and there are not many label datasets, which is why it is not a well-researched discipline. The accuracy of the pre-existing machine learning studies in the field of the Urdu fake news detection has been insufficient. In their present work, the authors make use of the deep learning-based methodology of Long Short-Term Memory (LSTM) and a composite method (CNN-LSTM), i.e., both TF-IDF and word embeddings employing LSTMs to address this problem. The LSTM-based word embedding new method was doing significantly better than the best research, having an 95.85% accuracy and a 94.65% F1 score in the D2 dataset. The model was very accurate with 93.87% and F1 score of 94.21% on D1 data. These findings are an important step toward investigating fake news in Urdu and a promising source to reduce the negative impact of information warping in the online society.

Downloads

Download data is not yet available.

References

[1] M. Amjad, G. Sidorov, A. Zhila, H. Gómez-Adorno, I. Voronkov, and A. Gelbukh, ‘“Bend the truth”: Benchmark dataset for fake news detection in Urdu language and its evaluation’, Journal of Intelligent and Fuzzy Systems, vol. 39, no. 2, pp. 2457–2469, 2020, Doi: 10.3233/JIFS-179905.

[2] M. Abdullah Ilyas, M. A. Ilyas, and K. Shahzad, ‘Urdu fake news detection using TF-IDF features and Text CNN’, 2021. [Online]. Available: http://ceur-ws.org

[3] M. S. Farooq, A. Naseem, F. Rustam, and I. Ashraf, ‘Fake news detection in Urdu language using machine learning’, Peer J Comput Sci, vol. 9, 2023, Doi: 10.7717/peerj-cs.1353.

[4] W. H. Bangyal et al., ‘Detection of Fake News Text Classification on COVID-19 Using Deep Learning Approaches’, Comput Math Methods Med, vol. 2021, pp. 1–14, Nov. 2021, Doi: 10.1155/2021/5514220.

[5] R. Tolosana, R. Vera-Rodriguez, J. Fierrez, A. Morales, and J. Ortega-Garcia, ‘Deepfakes and beyond: A Survey of face manipulation and fake detection’, Information Fusion, vol. 64, pp. 131–148, Dec. 2020, Doi: 10.1016/j.inffus.2020.06.014.

[6] S. Butt, N. Ashraf, G. Sidorov, and A. Gelbukh, ‘Sexism Identification using BERT and Data Augmentation-EXIST2021’, 2021.

[7] N. Ashraf, R. Mustafa, G. Sidorov, and A. Gelbukh, ‘Individual vs. Group Violent Threats Classification in Online Discussions’, in Companion Proceedings of the Web Conference 2020, New York, NY, USA: ACM, Apr. 2020, pp. 629–633. Doi: 10.1145/3366424.3385778.

[8] S. Latifi, Ed., 17th International Conference on Information Technology–New Generations (ITNG 2020), vol. 1134. Cham: Springer International Publishing, 2020. Doi: 10.1007/978-3- 030-43020-7.

[9] M. Amjad, S. Butt, H. I. Amjad, A. Zhila, G. Sidorov, and A. Gelbukh, ‘Overview of the Shared Task on Fake News Detection in Urdu at FIRE 2021’, Jul. 2022, [Online]. Available: http://arxiv.org/abs/2207.05133

[10] A. Faiz Ur, R. Khilji, S. Rahman Laskar, P. Pakray, and S. Bandyopadhyay, ‘Urdu Fake News Detection using Generalized Auto regressors’, 2020. [Online]. Available: https://github.com/urduhack

[11] M. Zuckerman, B. M. DePaulo, and R. Rosenthal, ‘Verbal and Nonverbal Communication of

Deception’, 1981, pp. 1–59. Doi: 10.1016/S0065-2601(08)60369-X.

[12] G. Loewenstein, ‘The psychology of curiosity: A review and reinterpretation.’, Psychol Bull, vol. 116, no. 1, pp. 75–98, Jul. 1994, Doi: 10.1037/0033-2909.116.1.75.

[13] B. E. Ashforth and F. Mael, ‘Social Identity Theory and the Organization’, Academy of Management Review, vol. 14, no. 1, pp. 20–39, Jan. 1989, Doi: 10.5465/amr.1989.4278999.

[14] M. Deutsch and H. B. Gerard, ‘A study of normative and informational social influences upon individual judgment.’, The Journal of Abnormal and Social Psychology, vol. 51, no. 3, pp. 629–636, Nov. 1955, Doi: 10.1037/h0046408.

[15] D. Ali, M. M. S. Missen, and M. Husnain, ‘Multiclass Event Classification from Text’, Sci Program, vol. 2021, pp. 1–15, Jan. 2021, Doi: 10.1155/2021/6660651.

[16] M. Amjad, G. Sidorov, and A. Zhila, ‘Data Augmentation using Machine Translation for Fake News Detection in the Urdu Language’, 2020. [Online]. Available: https://translate.google.com

[17] M. P. Akhter, J. Zheng, F. Afzal, H. Lin, S. Riaz, and A. Mehmood, ‘Supervised ensemble learning methods towards automatically filtering Urdu fake news within social media’, Peer J Comput Sci, vol. 7, p. e425, Mar. 2021, Doi: 10.7717/peerj-cs.425.

[18] M. S. Farooq, A. Naseem, F. Rustam, and I. Ashraf, ‘Fake news detection in Urdu language using machine learning’, Peer J Comput Sci, vol. 9, p. e1353, May 2023, Doi: 10.7717/peer j- cs.1353.

[19] N. Lin, S. Fu, and S. Jiang, ‘Fake News Detection in the Urdu Language using Char CNN-RoBERTa’. [Online]. Available: https://huggingface.co/urduhack/urdu-roberta

[20] F. Balouchzahi and H. L. Shashirekha, ‘Learning Models for Urdu Fake News Detection’, 2020. [Online]. Available: https://mangaloreuniversity.ac.in/dr-h-l-shashirekha.