Comparative Performance Evaluation of Bi-Directional LSTM with Attention, CNN, and DNN for Fake News Classification
Abstract
The expeditious dissemination of information has been accompanied by the expansion of fake news, constituting significant challenges in refine authentic news from fabricated narratives whereas Media plays a vital role in the public dissemination of information about events. Without the concern about the credibility of the information, the fictitious or fake news is spread in social networks and set foot on thousands of users. Fake news is typically generated for commercial and political interests to mislead and attract readers. The spread of fake news has raised a big challenge to society. Automatic credibility analysis of news articles is a current research interest. This study addresses the urgent need for effective fake news detection mechanisms. The spread of fake news on digital platforms has necessitated the development of sophisticated tools for accurate detection and classification. Deep learning models, particularly Bi-LSTM and attention-based Bi-LSTM architectures, have shown promise in tackling this issue. This research utilized Bi-LSTM and attention-based Bi-LSTM models, integrating an attention mechanism to assess the significance of different parts of the input data. The models were trained on an 80% subset of the data and tested on the remaining 20%, employing comprehensive evaluation metrics including F1-Score, Accuracy, and Loss. Comparative analysis with two baseline models: a CNN-based model and a simple Dense Neural Network. revealed the superior efficacy of the proposed architectures. The attention-based Bi-LSTM model demonstrated remarkable proficiency, outperforming other two baseline models in terms of accuracy (98.66%) and F1 Score (98.67%). The study highlighted the potential of integrating advanced deep learning techniques in fake news detection. The proposed models set new standards in the field, offering effective tools for combating misinformation. Limitations such as data dependency, potential for over fitting, and language and context specificity were acknowledged. The research underscores the importance of leveraging cutting-edge deep learning methodologies, particularly attention mechanisms, in fake news identification. The innovative models presented pave the way for more robust solutions to counter misinformation, thereby preserving the veracity of digital information. Future research should focus on enhancing data diversity, model efficiency, and applicability across various languages and contexts.
References
2. M. Samadi, M. Mousavian, S. Momtazi, Deep contextualized text representation and learning for fake news detection, Inf. Process. Manag., 58)6(,10272392021(
3. S. B. S. Mugdha, S. M. Ferdous, A. Fahmin, Evaluating Machine Learning Algorithms for Bengali Fake News Detection, ICCIT 2020 - 23rd Int. Conf. Comput. Inf. Technol. Proc., no. December 2020, 2020
4. P. Kumar Roy, A. Kumar, Convolutional Neural Network for Text: A Stepwise Working Guidance, SSRN Electron. J., (2021).
5. I. K. Sastrawan, I. P. A. Bayupati, D. M. S. Arsa, Detection of fake news using deep learning CNN–RNN based methods, ICT Express, 2021
6. J. A. Nasir, O. S. Khan, I. Varlamis, Fake news detection: A hybrid CNN-RNN based deep learning approach, Int. J. Inf. Manag. Data Insights, 1(1), 100007(2021)
7. N. Aslam, I. Ullah Khan, F. S. Alotaibi, L. A. Aldaej, A. K. Aldubaikil, Fake Detect: A Deep Learning Ensemble Model for Fake News Detection, Complexity, 2021.
8. Zhang, L., Zhang, Z., & Zhao, T. (2021). A Novel Spatio-Temporal Access Control Model for Online Social Networks and Visual Verification. International Journal of Cloud Applications and Computing (IJCAC), 11(2), 17-31.
9. Srinivasan, S. & Dhinesh Babu L D. (2019). A Parallel Neural Network Approach for Faster Rumor Identification in Online Social Networks. International Journal on Semantic Web and Information Systems (IJSWIS), 15(4), 69-89.
10. Sahoo, Somya Ranjan & Gupta, Brij B. (2019). Hybrid approach for detection of malicious profiles in twitter. Computers & Electrical Engineering. 76. 65-81.
11. A. Kishwar, A. Zafar, Fake news detection on Pakistani news using machine learning and deep learning, Expert Syst. Appl., 211( April 2022), 118558(2023).
12. L. Hu, S. Wei, Z. Zhao, B. Wu, Deep learning for fake news detection: A comprehensive survey, AI Open, 3(September), 133–155(2022)
13. R. Jehad, S. Yousif, Classification of fake news using multi-layer percepti on, AIP Conf. Proc., 2334(March), (2021)
14. Data set: https://www.kaggle.com/datasets/jainpooja/fake-news-detection
15. S. A. Yousif, Z. N. Sultani, V. W. Samawi, Utilizing arabic wordnet relations in Arabic text classification: New feature selection methods, IAENG Int. J. Comput. Sci., 46(4), 1–12(2019).
16. Mouratidis, Despina & Nikiforos, Maria Nefeli & Kermanidis, Katia. (2021). Deep Learning for Fake News Detection in a Pairwise Textual Input Schema. Computation.
17. Ouassil, Mohamed Amine & Cherradi, Bouchaib & Hamida, Soufiane & Mouaad, Errami & el Gannour, Oussama & Raihani, Abdelhadi. (2022). A Fake News Detection System based on Combination of Word Embedded Techniques and Hybrid Deep Learning Model. International Journal of Advanced Computer Science and Applications.
18. F. Farhangian, R. M. O. Cruz, and G. D. C. Cavalcanti, ‘‘Fake news detection: Taxonomy and comparative study,’’ Inf. Fusion, vol. 103, Mar. 2024, Art. no. 102140.
19. I. Goodfellow, Y. Bengio, and A. Courville, Deep Learning. Cambridge, MA, USA: MIT Press, 2016.
20. J. Devlin, M.-W. Chang, K. Lee, and K. Toutanova, ‘‘BERT: Pre-training of deep bidirectional transformers for language understanding,’’ 2018, arXiv:1810.04805.
