Statistical Analysis of Deep Learning Models Used for Social Media Forensics from An Empirical Perspective

Authors

  • Mayuri Gaikwad  PG Student, Department of Computer Science and Engineering, TGPCET, Nagpur , Maharashtra, India
  • Prof. Abhimanyu Dhutonde  Head of Department of Computer Science and Engineering, TGPCET, Nagpur, Maharashtra, India

Keywords:

Deep Learning Models, Social Media Forensics, Empirical Perspective, Statistical Analysis, Deceptive Contents

Abstract

The prevalence of social media platforms in the digital age has brought forth hitherto unheard-of difficulties in assuring the accuracy and integrity of information shared through these channels. The growing prevalence of fake news, misinformation, and manipulative content highlights the need for effective tools and approaches to evaluate the reliability of online content. This work launches a thorough investigation of deep learning models used for social media forensics in answer to this pressing requirement, founded in actual data and statistical analysis. The importance of social media platforms in influencing public conversation, opinions, and even the political and social landscapes makes this study necessary. Maintaining informed democratic societies and preserving the credibility of online information sources depend on our capacity to distinguish between genuine and misleading content. By rigorously examining the effectiveness of deep learning models in tackling the issues presented by the proliferation of false material on social media, this study aims to close the gap in previous studies. The review procedure used here uses a two-pronged strategy. An extensive survey is first done to find and compile a range of deep learning models specifically designed for social media forensics. These models incorporate a wide variety of methodologies, such as network analysis, image analysis, and natural language processing. The ensuing empirical phase, which makes use of a wide range of actual social media datasets for rigorous review, is contextualised by this first stage of the process. The empirical evaluation looks closely at how well these models perform on many dimensions. To assess their capacity to distinguish between authentic and manipulative content, precision, recall, and accuracy metrics are selectively applied. To ensure the models' viability in the actual world, computational effectiveness and scalability are also taken into account. These dimensions' intersection offers a comprehensive picture of the models' advantages and disadvantages.

References

  1. A. Theophilo, R. Giot and A. Rocha, "Authorship Attribution of Social Media Messages," in IEEE Transactions on Computational Social Systems, vol. 10, no. 1, pp. 10-23, Feb. 2023, doi: 10.1109/TCSS.2021.3123895.
  2. S. A. Khan et al., "Visual User-Generated Content Verification in Journalism: An Overview," in IEEE Access, vol. 11, pp. 6748-6769, 2023, doi: 10.1109/ACCESS.2023.3236993.
  3. D. Shullani, D. Baracchi, M. Iuliani and A. Piva, "Social Network Identification of Laundered Videos Based on DCT Coefficient Analysis," in IEEE Signal Processing Letters, vol. 29, pp. 1112-1116, 2022, doi: 10.1109/LSP.2022.3167631.
  4. F. Alonso-Fernandez, N. M. S. Belvisi, K. Hernandez-Diaz, N. Muhammad and J. Bigun, "Writer Identification Using Microblogging Texts for Social Media Forensics," in IEEE Transactions on Biometrics, Behavior, and Identity Science, vol. 3, no. 3, pp. 405-426, July 2021, doi: 10.1109/TBIOM.2021.3078073.
  5. J. Yang, Z. Yang, J. Zou, H. Tu and Y. Huang, "Linguistic Steganalysis Toward Social Network," in IEEE Transactions on Information Forensics and Security, vol. 18, pp. 859-871, 2023, doi: 10.1109/TIFS.2022.3226909.
  6. E. Arin and M. Kutlu, "Deep Learning Based Social Bot Detection on Twitter," in IEEE Transactions on Information Forensics and Security, vol. 18, pp. 1763-1772, 2023, doi: 10.1109/TIFS.2023.3254429.
  7. X. Xu et al., "Edge Server Quantification and Placement for Offloading Social Media Services in Industrial Cognitive IoV," in IEEE Transactions on Industrial Informatics, vol. 17, no. 4, pp. 2910-2918, April 2021, doi: 10.1109/TII.2020.2987994.
  8. M. Fazil, A. K. Sah and M. Abulaish, "DeepSBD: A Deep Neural Network Model With Attention Mechanism for SocialBot Detection," in IEEE Transactions on Information Forensics and Security, vol. 16, pp. 4211-4223, 2021, doi: 10.1109/TIFS.2021.3102498.
  9. Elhoseny, M., Selim, M.M. & Shankar, K. Optimal Deep Learning based Convolution Neural Network for digital forensics Face Sketch Synthesis in internet of things (IoT). Int. J. Mach. Learn. & Cyber. 12, 3249–3260 (2021). https://doi.org/10.1007/s13042-020-01168-6
  10. Gowada, R., Pawar, D. & Barman, B. Unethical human action recognition using deep learning based hybrid model for video forensics. Multimed Tools Appl 82, 28713–28738 (2023). https://doi.org/10.1007/s11042-023-14508-9
  11. Choudhary, A.K., Rahamatkar, S. & Purbey, S. DQNANFCT: design of a deep Q-learning network for augmented network forensics via integrated contextual trust operations. Int. j. inf. tecnol. 15, 2729–2739 (2023). https://doi.org/10.1007/s41870-023-01298-4
  12. Chakraborty, S., Chatterjee, K. & Dey, P. Discovering Tampered Image in Social Media Using ELA and Deep Learning. SN COMPUT. SCI. 3, 392 (2022). https://doi.org/10.1007/s42979-022-01311-w
  13. Bhardwaj, S., Dave, M. Crypto-Preserving Investigation Framework for Deep Learning Based Malware Attack Detection for Network Forensics. Wireless Pers Commun 122, 2701–2722 (2022). https://doi.org/10.1007/s11277-021-09026-6
  14. Mitra, A., Mohanty, S.P., Corcoran, P. et al. A Machine Learning Based Approach for Deepfake Detection in Social Media Through Key Video Frame Extraction. SN COMPUT. SCI. 2, 98 (2021). https://doi.org/10.1007/s42979-021-00495-x
  15. Suratkar, S., Kazi, F. Deep Fake Video Detection Using Transfer Learning Approach. Arab J Sci Eng 48, 9727–9737 (2023). https://doi.org/10.1007/s13369-022-07321-3
  16. Glavan, A., Talavera, E. InstaIndoor and multi-modal deep learning for indoor scene recognition. Neural Comput & Applic 34, 6861–6877 (2022). https://doi.org/10.1007/s00521-021-06781-2
  17. Jin, X., He, Z., Xu, J. et al. Video splicing detection and localization based on multi-level deep feature fusion and reinforcement learning. Multimed Tools Appl 81, 40993–41011 (2022). https://doi.org/10.1007/s11042-022-13001-z
  18. Vaishali, S., Neetu, S. Enhanced copy-move forgery detection using deep convolutional neural network (DCNN) employing the ResNet-101 transfer learning model. Multimed Tools Appl (2023). https://doi.org/10.1007/s11042-023-15724-z
  19. Pocher, N., Zichichi, M., Merizzi, F. et al. Detecting anomalous cryptocurrency transactions: An AML/CFT application of machine learning-based forensics. Electron Markets 33, 37 (2023). https://doi.org/10.1007/s12525-023-00654-3
  20. Azhar, A., Rubab, S., Khan, M.M. et al. Detection and prediction of traffic accidents using deep learning techniques. Cluster Comput 26, 477–493 (2023). https://doi.org/10.1007/s10586-021-03502-1
  21. Sushir, R.D., Wakde, D.G. & Bhutada, S.S. Enhanced blind image forgery detection using an accurate deep learning based hybrid DCCAE and ADFC. Multimed Tools Appl (2023). https://doi.org/10.1007/s11042-023-15475-x
  22. Bharathiraja, S., Rajesh Kanna, B. & Hariharan, M. A Deep Learning Framework for Image Authentication: An Automatic Source Camera Identification Deep-Net. Arab J Sci Eng 48, 1207–1219 (2023). https://doi.org/10.1007/s13369-022-06743-3
  23. Goel, A., Goel, A.K. & Kumar, A. The role of artificial neural network and machine learning in utilizing spatial information. Spat. Inf. Res. 31, 275–285 (2023). https://doi.org/10.1007/s41324-022-00494-x
  24. Leone, M. From Fingers to Faces: Visual Semiotics and Digital Forensics. Int J Semiot Law 34, 579–599 (2021). https://doi.org/10.1007/s11196-020-09766-x
  25. Suman, C., Chaudhary, R.S., Saha, S. et al. An attention based multi-modal gender identification system for social media users. Multimed Tools Appl 81, 27033–27055 (2022). https://doi.org/10.1007/s11042-021-11256-6
  26. Shivadekar, S., Kataria, B., Limkar, S. et al. Design of an efficient multimodal engine for preemption and post-treatment recommendations for skin diseases via a deep learning-based hybrid bioinspired process. Soft Comput (2023).
  27. Shivadekar, Samit, et al. "Deep Learning Based Image Classification of Lungs Radiography for Detecting COVID-19 using a Deep CNN and ResNet 50." International Journal of Intelligent Systems and Applications in Engineering 11.1s (2023): 241-250.
  28. P. Nguyen, S. Shivadekar, S. S. Laya Chukkapalli and M. Halem, "Satellite Data Fusion of Multiple Observed XCO2 using Compressive Sensing and Deep Learning," IGARSS 2020 - 2020 IEEE International Geoscience and Remote Sensing Symposium, Waikoloa, HI, USA, 2020, pp. 2073-2076, doi: 10.1109/IGARSS39084.2020.9323861.
  29. Banait, Satish S., et al. "Reinforcement mSVM: An Efficient Clustering and Classification Approach using reinforcement and supervised Techniques." International Journal of Intelligent Systems and Applications in Engineering 10.1s (2022): 78-89.
  30. Shewale, Yogita, Shailesh Kumar, and Satish Banait. "Machine Learning Based Intrusion Detection in IoT Network Using MLP and LSTM." International Journal of Intelligent Systems and Applications in Engineering 11.7s (2023): 210-223.
  31. Vanjari, Hrishikesh B., Sheetal U. Bhandari, and Mahesh T. Kolte. "Enhancement of Speech for Hearing Aid Applications Integrating Adaptive Compressive Sensing with Noise Estimation Based Adaptive Gain." International Journal of Intelligent Systems and Applications in Engineering 11.7s (2023): 138-157.
  32. Vanjari, Hrishikesh B., and Mahesh T. Kolte. "Comparative Analysis of Speech Enhancement Techniques in Perceptive of Hearing Aid Design." Proceedings of the Third International Conference on Information Management and Machine Intelligence: ICIMMI 2021. Singapore: Springer Nature Singapore, 2022.

International Journal of Scientific Research in Science and Technology

Downloads

Published

2023-10-30

Issue

Volume 10, Issue 5, September-October-2023

Section

Research Articles

License

Copyright (c) IJSRST

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

How to Cite

[1]
Mayuri Gaikwad, Prof. Abhimanyu Dhutonde "Statistical Analysis of Deep Learning Models Used for Social Media Forensics from An Empirical Perspective" International Journal of Scientific Research in Science and Technology(IJSRST), Online ISSN : 2395-602X, Print ISSN : 2395-6011,Volume 10, Issue 5, pp.46-64, September-October-2023.