An Integrated Cycle GAN and PEGASUS to Generate Synthetic Data for Detection of Fake News

An Integrated Cycle GAN and PEGASUS to Generate Synthetic Data for Detection of Fake News

© 2022 by IJETT Journal
Volume-70 Issue-8
Year of Publication : 2022
Authors : T V Divya, Barnali Gupta Banik
DOI : 10.14445/22315381/IJETT-V70I8P206

How to Cite?

T V Divya, Barnali Gupta Banik, "An Integrated Cycle GAN and PEGASUS to Generate Synthetic Data for Detection of Fake News," International Journal of Engineering Trends and Technology, vol. 70, no. 8, pp. 57-70, 2022. Crossref,

The proposed research to increase the size of the dataset with images, the regular image manipulation, which involves an image translation process using different graphical operations, makes the entire workflow design expensive. This process also involves designing complicated structures, which takes a lot of time to build the complete architecture. This image translation process has a major drawback, which involves controlled modification of the images. So, the proposed system implemented an Enhanced Cycle GAN, which does not perform any pairing activity between the images in the dataset. Since the detection of fake news involves both images and texts, the proposed research extracts the text using an ensemble mechanism in which the text summarizer is constructed using the pre-trained model known as “PEGASUS” combined LSTM to perform abstractive text summarization. After framing the summarization based on the context, the system is evaluated to prove its efficiency using ROUGE-N metrics.

PEGASUS, pre-trained model, ROGUE-N, Abstractive Summarization, Cycle GAN, Recurrent NN models, Gradient Recurrent, Unit (GRU), Optimizer.

[1] Zeng J, Zhang Y & Ma X, “Fake News Detection for Epidemic Emergencies via Deep Correlations between Text and Images,” Sustainable Cities and Society, 66, pp. 102652, 2021.
[2] Sahoo S. R & Gupta B. B, “Multiple Features-Based Approaches for Automatic Fake News Detection on Social Networks Using Deep Learning,” Applied Soft Computing, vol. 100, pp. 106983, 2021.
[3] Qian S, Wang J, Hu J, Fang Q & Xu C, “Hierarchical Multi-modal Contextual Attention Network for Fake News Detection,” Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval. SIGIR ’21: The 44th International ACM SIGIR Conference on Research and Development in Information Retrieval, 2021.
[4] Raj C & Meel P, “ConvNet Frameworks for Multi-Modal Fake News Detection,” Applied Intelligence, 2021.
[5] Singh B & Sharma D. K, “Predicting Image Credibility in Fake News over Social Media Using a Multi-Modal Approach,” Neural Computing and Applications, 2021.
[6] Tuan, Nguyen Manh Duc, and Pham Quang Nhat Minh. “Multimodal Fusion with BERT and Attention Mechanism for Fake News Detection,” ArXiv: 2104.11476 [Cs], 2021.
[7] Cheng M, Li Y, Nazarian S, et al., “From Rumour to Genetic Mutation Detection with Explanations: A GAN Approach,” Sci Rep., vol. 11, pp. 5861, 2021.
[8] B. Han, X. Han, H. Zhang, J. Li and X. Cao, "Fighting Fake News: Two Stream Network for Deepfake Detection via Learnable SRM," in IEEE Transactions on Biometrics, Behavior, and Identity Science, vol. 3, no. 3, pp. 320-331, 2021. Doi:10.1109/TBIOM.2021.3065735.
[9] A. Hande, K. Puranik, R. Priyadharshini, S. Thavareesan and B. R. Chakravarthi, "Evaluating Pretrained Transformer-based Models for COVID-19 Fake News Detection," 5th International Conference on Computing Methodologies and Communication (ICCMC), pp. 766-772, 2021. Doi: 10.1109/ICCMC51019.2021.9418446.
[10] S. Sridhar and S. Sanagavarapu, "Fake News Detection and Analysis using Multitask Learning with BiLSTMCapsNet Model," 11th International Conference on Cloud Computing, Data Science & Engineering (Confluence), pp. 905-911, 2021. Doi:10.1109/Confluence51648.2021.9377080.
[11] Braşoveanu A.M.P, Andonie R, “Integrating Machine Learning Techniques in Semantic Fake News Detection,” Neural Process Lett, vol. 53, pp. 3055–3072, 2021.
[12] Padmanabhuni, Ms. S. S. “An Extensive Study on Classification-Based Plant Disease Detection Systems,” Journal of Mechanics of Continua and Mathematical Sciences, vol. 15, no. 5, 2020.
[13] S. H. Kong, L. M. Tan, K. H. Gan and N. H. Samsudin, "Fake News Detection using Deep Learning," 2020 IEEE 10th Symposium on Computer Applications & Industrial Electronics (ISCAIE), 2020, pp. 102-107, doi: 10.1109/ISCAIE47305.2020.9108841.
[14] Kumar S, Asthana R, Upadhyay S, Upreti N & Akbar M, “Fake News Detection Using Deep Learning Models: A Novel Approach,” Transactions on Emerging Telecommunications Technologies, Wiley, vol. 31, no. 2, 2019.
[15] M. Umer, Z. Imtiaz, S. Ullah, A. Mehmood, G. S. Choi and B. -W. On, "Fake News Stance Detection Using Deep Learning Architecture (CNN-LSTM)," in IEEE Access, vol. 8, pp. 156695-156706, 2020. Doi: 10.1109/ACCESS.2020.3019735.
[16] Kaliyar R. K, Goswami A, Narang P & Sinha S, “FNDNet – A Deep Convolutional Neural Network for Fake News Detection,” Cognitive Systems Research, Elsevier BV, vol. 61, pp. 32–44, 2020.
[17] Sri Silpa Padmanabhuni and Pradeepini Gera, “Synthetic Data Augmentation of Tomato Plant Leaf using Meta Intelligent Generative Adversarial Network: Milgan,” International Journal of Advanced Computer Science and Applications (IJACSA), vol. 13, no. 6, 2022.
[18] Nguyen V.H, Sugiyama K, Nakov P, & Kan M.Y, “FANG,” In Proceedings of the 29th ACM International Conference on Information & Knowledge Management. CIKM ’20: The 29th ACM International Conference on Information and Knowledge Management. ACM, 2020.
[19] Faustini, P. H. A., & Covões, T. F, “Fake News Detection in Multiple Platforms and Languages,” In Expert Systems with Applications, Elsevier BV, vol. 158, pp. 113503, 2020..
[20] Iftikhar Ahmad, Muhammad Yousaf, Suhail Yousaf, Muhammad Ovais Ahmad, "Fake News Detection Using Machine Learning Ensemble Methods", Complexity, vol. 2020, Article ID. 8885861, pp. 11, 2020.
[21] Huang Y.F, & Chen P.H, “Fake News Detection Using an Ensemble Learning Model Based on Self-Adaptive Harmony Search Algorithms,” In Expert Systems with Applications, Elsevier BV, vol. 159, pp. 113584, 2020.
[22] Divya, T. V., & Banik, B. G, “Detecting Fake News Over Job Posts via Bi-Directional Long Short-Term Memory (BIDLSTM),” International Journal of Web-Based Learning and Teaching Technologies (IJWLTT), vol. 16, no. 6, pp. 1-18, 2021.