Collecting COVID-19 Mask Mandate Information Using Artificial Intelligence to Contextualize 2022 NAEP Results
The objective of this study was to collect online information about COVID-19 mask mandates in the United States (U.S.) at the school district-level using artificial intelligence to help understand the performance results from the 2022 National Assessment of Educational Progress (NAEP), administered by the National Center for Education Statistics (NCES). To collect the data, a customized web scraping tool using the Python package BeautifulSoup was developed to automate Google searches of mask mandates in school districts in the U.S. These automated searches retrieved a pre-determined number of top search results in a tabular format. Next, Natural Language Processing (NLP) code was developed that read the search results and classified which school districts had implemented a mask mandate. This classification was achieved by developing and training a supervised machine learning algorithm using the search results data that were manually labelled by the authors. School district level mask mandate information for the state of Ohio was used to successfully pilot the tool. The algorithm trained using this data classified which school districts had implemented a mask mandate with an accuracy of 87 percent. The data predicted by the algorithm was used to verify the same data collected by NCES through monthly surveys of a sample of public schools from December 2021 – January 2022. This presentation will discuss these methods as well as some of the challenges, refinements, and successes of the tool. Ultimately, the results of the tool demonstrate that large scale data collection and validation activities can be conducted with high accuracy at a low cost and can be repeated more frequently and quickly than surveys can without incurring any additional burden on potential respondents.
View the presentation of Collecting COVID-19 Mask Mandate Information Using Artificial Intelligence to Contextualize 2022 NAEP Result below: