ABSTRACT
In 2019, the Covid-19 pandemic led to emergency changes in the educational sector as a precautionary measure to limit the spread of the Covid-19 virus and protect the health and safety of students. Educational institutes couldn't escape this havoc;by April 2020, 189 countries had suspended school, affecting 89 percent of the world's students. Since the epidemic began, online learning has completely taken over the educational industry, leaving students with no choice but to adapt to the brand-new virtual learning environment. Consequently, people turned to social media, such as Twitter, to express their feelings, opinions, and concerns about online learning as an alternative to traditional physical classes. The new online learning platforms, associated technologies, and procedures have been widely discussed on Twitter. In the proposed study, we have presented a systematic approach to analyze the public opinions and perceptions about online learning using Twitter sentiment analysis (TSA) through Twitter's API and term frequency-inverse document frequency (TF-IDF) technique. Further, we classified the sentiments into certain clusters, such as positive, negative, and neutral, using a text mining approach (i.e., lexicons). Moreover, we have uncovered these sentiments and visualized the clusters using visualization techniques such as word clouds and bar charts. Additionally, by using TF-IDF, we measured the strength of words that people use to express their opinions about online schooling and explored to what extent it affects the overall results of our analysis. © 2022 IEEE.
ABSTRACT
In December 2019, a pandemic named COVID-19 broke out in Wuhan, China, and in a few weeks, it spread to more than 200 countries worldwide. Every country infected with the disease started taking necessary measures to stop the spread and provide the best possible medical facilities to infected patients and take precautionary measures to control the spread. As the infection spread was exponential, there arose a need to model infection spread patterns to estimate the patient volume computationally. Such patients' estimation is the key to the necessary actions that local governments may take to counter the spread, control hospital load, and resource allocations. This article has used long short-term memory (LSTM) to predict the volume of COVID-19 patients in Pakistan. LSTM is a particular type of recurrent neural network (RNN) used for classification, prediction, and regression tasks. We have trained the RNN model on Covid-19 data (March 2020 to May 2020) of Pakistan and predict the Covid-19 Percentage of Positive Patients for June 2020. Finally, we have calculated the mean absolute percentage error (MAPE) to find the model's prediction effectiveness on different LSTM units, batch size, and epochs. Predicted patients are also compared with a prediction model for the same duration, and results revealed that the predicted patients' count of the proposed model is much closer to the actual patient count. IEEE
ABSTRACT
Semantic knowledge graphs provide very significant benefits for structuring and analysing huge amounts of aggregated data across diverse heterogeneous sources. Beyond quick and efficient data query and analysis, they facilitate inference from data and generation of insights for several purposes. With the multi-faceted global challenges posed by the COVID-19 pandemic, this research focused on the use of a semantic knowledge graph to model, structure and store COVID-related news articles centrally and semantically towards knowledge discovery, knowledge acquisition and advanced data analytics for understanding varying metrics relating to the virus towards curbing its spread. The semantic knowledge graph provides a platform for researchers, data analysts and data scientists across societal sectors to investigate and recommend strategies towards addressing the challenges it poses to the global society. © 2020 IEEE.