Novel Fuzzy Deep Learning Approach for Automated Detection of Useful Covid-19 Tweets

Coronavirus disease (COVID-19) is a newly found viral disease from the SARS-CoV-2 family. A moral panic resulted, include both informative and uninformative information about COVID-19 and its effects. Twitter is a well-respected and well-known social media network in this current outbreak. This paper predicts the COVID-19 informative tweets of Twitter posts using a novel set of fuzzy rules involving deep learning techniques. The current study focuses on identifying informative tweets during the pandemic in order to provide the public with trustworthy information. The proposed architecture combines deep learning transformer models RoBERTa and CT-BERT with the fuzzy technique to categorize posts as INFORMATIVE or UNINFORMATIVE. We performed a comparative analysis of our method with machine learning models and deep learning approaches. Results show that our proposed model is able to classify informative and uninformative classes with an accuracy of 91.40% and F1-score of 91.94% using the COVID-19 English tweet dataset. Our model is accurate and ready for the real-world application.