Bi-directional Long Short-Term Memory Network for Fake News Detection from Social Media

These days’ web-based media is one of the main news hotspots for individuals throughout the planet for its minimal expense, simple openness, and quick spreading. This web-based media can in some cases include uncertain messages and has a critical danger of openness to counterfeit or fake news, which may elude the pursuers. Therefore, finding fake news from social media is one of the important natural language processing tasks. In this work, we have proposed a bi-directional long short-term memory (Bi-LSTM) network to identify COVID-19 fake news posted on Twitter. The performance of the proposed Bi-LSTM network is compared to six different popular classical machine learning classifiers such as Naïve Bayes, KNN, Decision Tree, Gradient Boosting, Random Forest, and AdaBoost. In the case of classical machine learning classifiers uni-gram, bi-gram, and tri-gram word TF-IDF features are used whereas in the case of the Bi-LSTM model word embedding features are used. The proposed Bi-LSTM network performed best in comparison to other implemented models and achieved a weighted F1-score of 0.94 in identifying COVID-19 fake news from Twitter. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

From Chalk Boards to Smart Boards: An Integration of IoT into Educational Environment During Covid-19 Pandemic

Internet of Things (IoT) is a unique paradigm shift in the domain of Information Technology. It converts the real-life things into intelligent virtual devices to ensure a machine-to-machine transmission of information. With its increasingly technological magnitude, it ascertains an imperative role in almost all spheres of life, and the global education markets have incredibly reaped benefits. The present paper gives an insight into the radical evolution and integration of IoT trends in education sector—the transition from conventional chalk boards to modern smart boards, especially at the outset of Covid-19 pandemic when the exigencies of global education demanded it the most. The paper also lists out opportunities, obstructions, scalability of tools and technology, and services allied to IoT expertise, while at the same time bridges the gap between educational and technical applications amid Covid-19 pandemic. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

Breathing, virus transmission, and social distancing—An experimental visualization study

With the outbreak of COVID-19 in many countries, public awareness related to the droplet mode of virus transmission is well documented and communicated. With a large spike in COVID-19 positive cases and the mortality rate, most of the general public are following preventive measures such as wearing masks, maintaining social distancing, and frequent hand washing. However, recently, it has been reported that the virus may also transmit through aerosolized particles of diameter <10 µm. The majority of the past research focuses on understanding droplet generation and transport through the most violent spasmodic expiration: coughing and sneezing. However, “breathing,” the most common phenomenon, is scarcely studied as a virus transmission source. In the present study, we report an experimental visualization of the droplet’s transport through breathing to quantify the reach of a typical breath for various exhale to inhale ratios. The efficacy of various standard (surgical, five-layered, and N95) and non-standard (homemade) protective measures such as face masks and face shields is also evaluated. An exhaled breath at E:I = 1:1 can travel up to 4 ft in 5 s;however, this reach reduces to 3 ft for E:I = 1:2. Two-layer homemade and commercial cotton masks are unable to completely impede the leakage of the droplet in the forward direction. A combination of a two-layer mask and face shield is also not effective in preventing the leakage and diffusion of the droplets. The surgical mask alone is not recommended during normal conversations as the leakage of the droplets is noticeable. A commercial N95 mask completely impedes the leakage of the droplets in the forward direction. However, the leakage of the droplets from the gaps between the mask and the nose is observed to be significant. A commercial five-layered mask is observed to be the most effective preservative measure with minimum leakage of the droplets. © 2021 Author(s).