Transfer learning and GRU-CRF augmentation for Covid-19 fake news detection

Abstract

The spread of fake news on online media is very dangerous and can lead to casualties, effects on psychology, character assassination, elections for political parties, and state chaos. Fake news that concerning Covid-19 massively spread during the pandemic. Detecting misinformation on the Internet is an essential and challenging task since humans face difficulty detecting fake news. We applied BERT and GPT2 as pre-trained using the BiGRU-Att-CapsuleNet model and BiGRU-CRF features augmentation to solve Fake News detection in Constraint @ AAAI2021 - COVID19 Fake News Detection in English Dataset. This research proved that our hybrid model with augmentation got better accuracy compared to our baseline model. It also showed that BERT gave a better result than GPT2 in all models; the highest accuracy we achieved for BERT is 0.9196, and GPT2 is 0.8986.

Text Data Augmentation Techniques for Fake News Detection in the Romanian Language

“…There are novel approaches to text augmentation that aim to solve the same problems. These approaches include DL or transformer-based methods, and, in general, they manage to outperform some of the current methods [19][20][21][22][23]. Future investigations related to transformer-based augmentation methods can be conducted to develop high-performance models for fake news detection.…”

TB-BCG: Topic-Based BART Counterfeit Generator for Fake News Detection

“…In addition to being used to detect fake news [10,11], natural language processing has been widely utilized for various more sophisticated tasks, i.e., Human Activity Recognition (HAR) [12], sentiment analysis [13][14][15], and spoken notifications for intelligent environments [16]. This paper aims for involvement in the Constraint @ AAAI2021-COVID19 Fake News Detection dataset shared task using the pre-trained model and deep learning.…”