Developing a fake news identification model with advanced deep language\rtransformers for Turkish COVID-19 misinformation data
No Thumbnail Available
Date
2022
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
Abstract
The massive use of social media causes rapid information dissemination that amplifies harmful messages\rsuch as fake news. Fake-news is misleading information presented as factual news that is generally used to manipulate\rpublic opinion. In particular, fake news related to COVID-19 is defined as ‘infodemic’ by World Health Organization.\rAn infodemic is a misleading information that causes confusion which may harm health. There is a high volume\rof misinformation about COVID-19 that causes panic and high stress. Therefore, the importance of development of\rCOVID-19 related fake news identification model is clear and it is particularly important for Turkish language from\rCOVID-19 fake news identification point of view. In this article, we propose an advanced deep language transformer\rmodel to identify the truth of Turkish COVID-19 news from social media. For this aim, we first generated Turkish\rCOVID-19 news from various sources as a benchmark dataset. Then we utilized five conventional machine learning\ralgorithms (i.e. Naive Bayes, Random Forest, K-Nearest Neighbor, Support Vector Machine, Logistic Regression) on\rtop of several language preprocessing tasks. As a next step, we used novel deep learning algorithms such as Long ShortTerm Memory, Bi-directional Long-Short-Term-Memory, Convolutional Neural Networks, Gated Recurrent Unit and\rBi-directional Gated Recurrent Unit. For further evaluation, we made use of deep learning based language transformers,\ri.e. Bi-directional Encoder Representations from Transformers and its variations, to improve efficiency of the proposed\rapproach. From the obtained results, we observed that neural transformers, in particular Turkish dedicated transformer\rBerTURK, is able to identify COVID-19 fake news in 98.5% accuracy.