Adapting recurrent neural networks for classifying public discourse on COVID-19 symptoms in Twitter content

Abstract

The COVID-19 infection, which began in December 2019, has claimed many lives and impacted all aspects of human life. With time, COVID-19 was identified as a pandemic outbreak by the World Health Organization (WHO), putting massive pressure on global health. During this ongoing pandemic, the exponential growth of social media platforms has provided valuable resources for distributing information, as well as a source for self-reported disease symptoms in public discourse. Therefore, there is an urgent need for effective approaches to detect self-reported symptoms or cases in social media content. In this study, we scrapped public discourse on COVID-19 symptoms in Twitter content. For this, we developed a huge dataset of COVID-19 self-reported symptoms and gold-annotated the tweets into four categories: confirmed, death, suspected, and recovered. Then, we use a machine and deep machine learning models, each with its own set of features, such as feature representation. Furthermore, the experimentations were achieved with recurrent neural networks (RNNs) variants and compared their performance with traditional machine learning algorithms. Experimental results report that optimizing the area under the curve (AUC) enhances model performance, and the long short-term memory (LSTM) has the highest accuracy in detecting COVID-19 symptoms in real-time public messaging. Thus, the LSTM classifier in the proposed pipeline achieves a classification accuracy of 90.7%, outperforming existing state-of-the-art algorithms for multi-class classification.

Smart E-Learning Framework for Personalized Adaptive Learning and Sequential Path Recommendations Using Reinforcement Learning

“…For example, Wang et al [50] proposed a prototype RL structure to produce sentence interpretations with a customizable attention-based neural network, which dynamically regulates the explanatory performance. Since a machine learning technique emphasizes how an intelligent agent engages with its surroundings, RL [45], [46], develops the policy through trial and error exploration, which is advantageous to sequential making decisions. As a result, it may offer methods for modelling the interactions between the user and the agent.…”

A Robust Heart Disease Prediction System Using Hybrid Deep Neural Networks

“…LSTM belongs to the domain of DL. It falls under the category of recurrent neural networks and is renowned for its ability to grasp long-term dependencies, particularly in tasks involving sequence prediction [50], [11]. As it progresses, it takes input and transmits it to others.…”

“…DL approaches have always been of interest because of their accuracy in problem-solving [6], [7]. A good example of the use of DL is in intelligent healthcare systems is processing of medical images [8], electronic health records [9], gene research [10], disease detection in text data [11] etc. are all carried out with DL.…”

Robust Benchmark for Propagandist Text Detection and Mining High-Quality Data

“…Additionally, the COVID-19 pandemic led to the publication of the first global infodemic news in 2020 [16]. Propaganda tactics are ineffective if the individuals are aware of the propaganda techniques employed in the news on social media [17].…”