Research Article
Detection of Misinformation Related to Pandemic Diseases using Machine Learning Techniques in Social Media Platforms
@ARTICLE{10.4108/eetpht.10.6459, author={J Naeem and Omer Melih Gul and I B Parlak and K Karpouzis and Y B Salman and S N Kadry}, title={Detection of Misinformation Related to Pandemic Diseases using Machine Learning Techniques in Social Media Platforms}, journal={EAI Endorsed Transactions on Pervasive Health and Technology}, volume={10}, number={1}, publisher={EAI}, journal_a={PHAT}, year={2024}, month={6}, keywords={COVID-19, machine learning, deep learning, sentimental analysis, social networks, Term Frequency -- Inverse Document Frequency, TF-IDF, Recurrent Neural Network, RNN}, doi={10.4108/eetpht.10.6459} }- J Naeem
Omer Melih Gul
I B Parlak
K Karpouzis
Y B Salman
S N Kadry
Year: 2024
Detection of Misinformation Related to Pandemic Diseases using Machine Learning Techniques in Social Media Platforms
PHAT
EAI
DOI: 10.4108/eetpht.10.6459
Abstract
INTRODUCTION: The advent of the COVID-19 pandemic has brought with it not only a global health crisis but also an infodemic characterized by the rampant spread of misinformation on social media platforms. OBJECTIVES: In response to the urgent need for effective misinformation detection, this study presents a comprehensive approach harnessing machine learning and deep learning techniques, culminating in ensemble methods, to combat the proliferation of COVID-19 misinformation on Facebook, Twitter, Instagram, and YouTube. METHODS: Drawing from a rich dataset comprising user comments on these platforms, encompassing diverse COVID-19- related discussions, our research applies Support Vector Machine (SVM), Decision tree, logistic regression, and neural networks to perform indepth analysis and classification of comments into two categories: positive and negative information. The innovation of our approach lies in the final phase, where we employ ensemble methods to consolidate the strengths of various machine learning and deep learning algorithms. This ensemble approach significantly improves the model’s overall accuracy and adaptability. RESULTS: Experimental results underscore the efficacy of our methodology, showcasing marked improvements in detection performance compared to individual models. After applying ensemble learning, we achieve an accuracy of 91% for Facebook data, 79% for Instagram data, 80% for Twitter data and 95% for YouTube data. CONCLUSION: Our system not only aids in curbing the dissemination of COVID-19 misinformation but also provides a robust framework for addressing misinformation across various contexts on social media platforms.
Copyright © 2024 J. Naeem et al., licensed to EAI. This is an open access article distributed under the terms of the CC BY-NC-SA 4.0, which permits copying, redistributing, remixing, transformation, and building upon the material in any medium so long as the original work is properly cited.
