MODERN APPROACHES TO DETECTING AND COMBATING DISINFORMATION IN INFORMATION SYSTEMS: ANALYSIS AND IMPROVEMENT

Nataliia Savitska; Iryna Yurchak

This scientific article analyzes and characterizes various types of false information disseminated in modern information systems. The main focus is on detecting and identifying the dangers associated with the spread of unreliable information in society. The serious consequences of this phenomenon can reach a global scale, making effective countermeasures critically important. The study examines and compares various software methods to counter the dissemination of false information. In particular, different methods of analyzing and filtering information aimed at detecting and localizing unreliable messages were studied and compared. This helps identify the most effective approaches to data analysis in the field of information systems and determine optimal methods to combat the spread of fake news. The conclusions of this research have practical applications and can be used to improve the analysis of information from various sources in information systems. The implementation of the solutions developed in this research will contribute to increasing the level of credibility and objectivity in information processing, thereby enhancing the quality of information analysis and its utilization in various sectors of society.

fake information; machine learning (ML); deep learning; dataset; Long Short-Term Memory (LSTM); Convolutional Neural Network (CNN); Recurrent Neural

1. Karduni, A. (2019). Human-Misinformation interaction: Understanding the interdisciplinary approach needed to computationally combat false information. ACM Digital Library. https://doi.org/10.1145/1122445.1122456

2. Dennis, A., Moravec, P., & Kim, A. (2023). Search & Verify: Misinformation and source evaluations in Internet search results. Decision Support Systems, 171. https://doi.org/10.1016/j.dss.2023.113976

3. Rastogi, S., & Bansal, D. (2023). A review on fake news detection 3T’s: Typology, time of detection, taxonomies. International Journal of Information Security. https://doi.org/10.1007/s10207-022-00625-3

4. BABCOCK, M., BESKOW, D., & CARLEY, K. (2018). Different Faces of False: The Spread and Curtailment of False Information in the Black Panther Twitter Discussion. Data and Information Quality, 11. https://doi.org/10.1145/3339468

5. Rohera, D., Shethna, H., Patel, K., & Thakker, U. (2022). A Taxonomy of Fake News Classification Techniques: Survey and Implementation Aspects. IEEE Access, 10. https://doi.org/DOI:10.1109/ACCESS.2022.3159651

6. Hamed, S. K., Aziz, M. J. A. A. A., & Yaakub, M. R. (2021). A review of fake news detection approaches: A critical analysis of relevant studies and highlighting key challenges associated with the dataset, feature representation, and data fusion. Heliyon, 9(10). https://doi.org/10.1016/j.heliyon.2023.e20382

7. Alghamdi, J., Lin, Y., & Luo, S. (2023). Towards COVID-19 fake news detection using transformer-based models. Knowledge-Based Systems, 274. https://doi.org/10.1016/j.knosys.2023.110642

8. Syed, L., Alsaeedi, A., Alhuri, L., & Aljohani, H. (2023). Hybrid weakly supervised learning with deep learning technique for detection of fake news from cyber propaganda. Array, 19. https://doi.org/10.1016/j.array.2023.100309

9. Mohawesh, R., Liu, X., Arini, H. M., Wu, Y., & Yin, H. (2023). Semantic graph based topic modelling framework for multilingual fake news detection. AI Open, 4. https://doi.org/10.1016/j.aiopen.2023.08.004

10. Alabaz, M., & Awajan, A. (2022). Fake-News Detection System Using Machinelearning Algorithms For Arabic-Language Content. Journal of Theoretical and Applied Information Technology.[Online] (Accessed: 08/10/2023)