Conference Proceedings
The International Conference on Emerging Technologies in Electronics, Computing and Communication 2022
(ICETECC`22)
Optimized Deep Learning Hybrid Framework for Robust Detection of Fake News on Twitter
Syed Fakhar Bilal1*; Hasham Shokat2; Saba Bashir3; Farhan Hassan Khan4; Muhammad Dawood Majid5; Muhammad Atif Khan6;| 1Department of Software Engineering Beijing University of Technology Beijing, China 2Dept. of Computer Science Federal Urdu University of Arts, Science and Technology Islamabad, Pakistan 3Dept. of Software Engineering Federal Urdu University of Arts, Science and Technology Islamabad, Pakistan 4Department of Computer Science, College of E&ME, NUST Islamabad, Pakistan 5Department of Robotics and Artificial Intelligence Shaheed Zulfikar Ali Bhutto Institute of Science and Technology Islamabad, Pakistan 6College of Economics and Management Beijing University of Technology Beijing, China |
ABSTRACT
The rapid increase of fake news on social media platforms shows major challenges, specifically when telling real information apart from false content. This research investigates how deep learning models and machine learning algorithms can be used to identify fake news. The suggested model is based on a hybrid model that combines Decision Tree (DT), Gradient Boosted Tree (GBT), and Long Short-Term Memory (LSTM) networks, utilizing ensemble methods to improve detection accuracy. The dataset for this research consists of both real and fake news articles gathered from Twitter, which were preprocessed using Natural Language Processing (NLP) techniques and transformed into word embedding with GloVe and Skip-Gram models. Experimental findings show that the hybrid model is significantly better than individual classifiers, achieving an accuracy rate of up to 99.7% when combining gradient-boosted tree (GBT) and Long Short-Term Memory LSTM. This proposed method effectively detects misinformation, providing a strong solution to combat the spread of fake news in critical situations.