Modeling Behavior and Vaccine Hesitancy Using Twitter-Derived US Population Sentiment during the COVID-19 Pandemic to Predict Daily Vaccination Inoculations.

The sentiment analysis of social media for predicting behavior during a pandemic is seminal in nature. As an applied contribution, we present sentiment-based regression models for predicting the United States COVID-19 first dose, second dose, and booster daily inoculations from 1 June 2021 to 31 March 2022. The models merge independent variables representing fear of the virus and vaccine hesitancy. Large correlations exceeding 77% and 84% for the first-dose and booster-dose models inspire confidence in the merger of the independent variables. Death count as a traditional measure of fear is a lagging indicator of inoculations, while Twitter-positive and -negative tweets are strong predictors of inoculations. Thus, the use of sentiment analysis for predicting inoculations is strongly supported with administrative events being catalysts for tweets. Non-inclusion in the second-dose regression model of data occurring before the 1 June 2021 timeframe appear to limit the second-dose model results-only achieving a moderate correlation exceeding 53%. Limiting tweet collection to geolocated tweets does not encompass the entire US Twitter population. Nonetheless, results from Kaiser Family Foundation (KFF) surveys appear to generally support the regression factors common to the first-dose and booster-dose regression models and their results.

Electroencephalogram Signals for Detecting Confused Students in Online Education Platforms with Probability-Based Features

Online education has emerged as an important educational medium during the COVID-19 pandemic. Despite the advantages of online education, it lacks face-to-face settings, which makes it very difficult to analyze the students' level of interaction, understanding, and confusion. This study makes use of electroencephalogram (EEG) data for student confusion detection for the massive open online course (MOOC) platform. Existing approaches for confusion detection predominantly focus on model optimization and feature engineering is not very well studied. This study proposes a novel engineering approach that uses probability-based features (PBF) for increasing the efficacy of machine learning models. The PBF approach utilizes the probabilistic output from the random forest (RF) and gradient-boosting machine (GBM) as a feature vector to train machine learning models. Extensive experiments are performed by using the original features and PBF approach through several machine learning models with EEG data. Experimental results suggest that by using the PBF approach on EEG data, a 100% accuracy can be obtained for detecting confused students. K-fold cross-validation and performance comparison with existing approaches further corroborates the results.