ENHANCING SOCIAL MEDIA CYBERSECURITY: HOAX DETECTION ON FACEBOOK VIA MARKOV CHAIN MONTE CARLO
Keywords:
Cybersecurity, Hoax Detection, Markov Chain Monte Carlo, Bayesia Inference, Natural Language ProcessingAbstract
The rapid proliferation of misinformation on social media platforms, particularly Facebook, poses significant challenges to cybersecurity by undermining public trust, influencing societal stability, and enabling malicious information campaigns. This study analyse past studies related to ML based hoax detection as well as proposing a hoax detection framework leveraging Bayesian inference with Markov Chain Monte Carlo (MCMC) sampling to enhance the accuracy and reliability of misinformation identification. The proposed method models textual features extracted from Facebook posts using natural language processing (NLP) techniques, followed by probabilistic classification via MCMC to estimate posterior probabilities of hoax likelihood. Experimental evaluations were conducted on a labelled dataset of Indonesian-language Facebook posts containing both verified hoax and non-hoax content. Results demonstrate that the MCMC-based approach outperforms conventional machine learning baselines in terms of precision, recall, and F1-score, while offering a probabilistic interpretability that aids decision-making in cybersecurity monitoring systems. The findings highlight the potential of MCMC-driven Bayesian models as a robust tool for mitigating misinformation threats and strengthening the cybersecurity posture of social media ecosystems.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 SEMINAR PEMBELAJARAN SEPANJANG HAYAT (SPSH) 2025

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