Category: Education

Optimal’s Director of Data Science, Sadaf Asrar will be presenting at the 2023 AERA Annual Meeting on April 13 – 16, 2023 . Mr. Asrar will be presenting on Collecting COVID-19 Mask Mandate Information Using Artificial Intelligence to Contextualize 2022 NAEP Results.

Below is the abstract of the presentation:

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.  

To download the PowerPoint presentation, visit: https://optimalsolutionsgroup.com/2022/07/08/optimal-researchers-to-present-on-automating-mask-mandate-google-searches/

To learn more about AERA and to register for the 2023 Annual Meeting, visit https://www.aera.net/Events-Meetings/Annual-Meeting/2023-Annual-Meeting

Optimal’s Mark Turner recently joined the Council of Graduate Schools (CGS) Employer Roundtable. The CGS Employer Roundtable is a small group of senior leaders representing employers of graduate degree holders in various fields and organizations serving higher education. CGS serves to advance graduate education and research in the U.S. and globally. Dr. Turner brings the perspective of small businesses that employ graduate degree holders to the roundtable that is mostly composed of global businesses and organizations — Amazon, Corning, IBM, and TIAA. For more information, see CGS Employer Roundtable.

Optimal’s executive, Tracye Turner, recently delivered career lessons learned and best practices remarks to new graduates at the 2022 spring commencement at the University of Maryland’s School of Information Studies. The fast-growing school has high job offer rates and in-demand graduates. She frequently collaborates with the iSchool, serves on the iLead Advisory Council, and was the Inaugural Chair. She shared her top 10 career lessons learned in cyclical job markets. For more information, see Spring 2022 Commencement Ceremony | University of Maryland (umd.edu)

Optimal’s education research team will be presenting at the International Population Data Linkage Network (IPDLN) conference on September 7-9, 2022. The team will present the methodological approach developed to collect mask mandate information by automating Google searches and using NLP to classify the results by developing a customized robotic process automation program. This year’s theme for the conference includes using AI and collecting data to validate and improve official statistics.

For more information on the conference, visit https://ipdln.org/2022-conference.

Authors: Ebony Walton, Statistician, NCES; Daniel Loew, Research Associate, Optimal Solutions Group; Imer Arnautovic, Research Associate, Optimal Solutions Group; and Enis Dogan, Chief Psychometrician, NCES

As is well known in education research, performance differences in achievement persist between groups of students in the U.S. and addressing them by ensuring equal access to high-quality education for all is a part of the U.S. Department of Education’s mission. This mission requires defining and measuring educational equity. The National Center for Education Statistics’ Equity Indicators Project aims to provide a solid data resource for researchers, policymakers, and the general public regarding educational equity.  A set of dozens of equity measures, which were informed by literature review, provide the framework for this data resource. Optimal Solutions Group has conducted a systematic review of survey instruments and codebooks for seven current NCES data sources as a pilot effort, resulting in a repository of over 3,000 data items relevant to the set of equity measures. Further data sources will be mined to provide a sufficient set of data items from which to measure educational equity. The authors will classify the set of equity measures into a logic model, designated with the logic model labels of inputs, processes, outputs, and outcomes. This logic model will be used to develop a theoretical model to measure and define educational equity, which will support a deeper understanding of how to evaluate it in a variety of settings. In so doing, this work will further the U.S. Department of Education’s central mission to provide equal access to a high level of quality education for all students in the United States.  

To learn more about the 2022 NCES STATS-DC Data Conference, visit https://ies.ed.gov/whatsnew/conferences/?id=15617&cid=2