Detection of Misinformation Related to Pandemic Diseases using Machine Learning Techniques in Social Media Platforms
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 p...
Saved in:
| Published in: | EAI endorsed transactions on pervasive health and technology Vol. 10 |
|---|---|
| Main Authors: | , , , , , |
| Format: | Journal Article |
| Language: | English |
| Published: |
28-06-2024
|
| Online Access: | Get full text |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | 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. |
|---|---|
| ISSN: | 2411-7145 2411-7145 |
| DOI: | 10.4108/eetpht.10.6459 |