Daghriri Talal, Proctor Michael, Matthews Sarah, Bashiri Abdullateef H
Department of Industrial Engineering, Jazan University, Jazan 82822, Saudi Arabia.
Department of Industrial Engineering & Management Systems, University of Central Florida, Orlando, FL 32816, USA.
Vaccines (Basel). 2023 Mar 22;11(3):709. doi: 10.3390/vaccines11030709.
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.
社交媒体的情绪分析对于预测大流行期间的行为具有开创性意义。作为一项应用贡献，我们提出了基于情绪的回归模型，用于预测2021年6月1日至2022年3月31日期间美国新冠疫苗第一剂、第二剂和加强剂的每日接种量。这些模型合并了代表对病毒的恐惧和疫苗犹豫的自变量。第一剂和加强剂模型中超过77%和84%的高相关性激发了人们对自变量合并的信心。作为恐惧传统衡量指标的死亡人数是接种量的滞后指标，而推特上的正面和负面推文是接种量的有力预测指标。因此，情绪分析在预测接种量方面的应用得到了有力支持，行政事件是推文的催化剂。2021年6月1日时间框架之前的数据未纳入第二剂回归模型，这似乎限制了第二剂模型的结果——仅达到略高于53%的中等相关性。将推文收集限制在地理位置定位的推文范围内并不能涵盖整个美国推特用户群体。尽管如此，凯撒家庭基金会（KFF）的调查结果似乎总体上支持第一剂和加强剂回归模型及其结果中的共同回归因素。
