Public Policy and Broader Applications for the Use of Text Analytics During Pandemics

Abstract

The state of Iowa conducted an initial business survey in March 2020 as the novel coronavirus disease 2019 (COVID-19) broke out across the United States. The survey data have been used for decision and policy making at the state level. Relief incentive packages were provided via the Iowa Economic Development Authority (IEDA) to Iowa-based companies to support their operations. A team of policy makers, faculty, and industry professionals was formed to conduct text analyses, analyze the survey responses, validate insights, and ensure that the appropriate policies were enacted. The analysis yielded a reproducible process using the statistical software R to quickly analyze large volumes of free-text responses to open-ended survey questions and develop topics comparable to those found through human coding. This process, using biterm topic models (BTMs), was first used to verify and validate the results of human coding and, because of its increased speed to insights compared with that of human coding, to validate hypotheses empirically much more quickly in subsequent surveys. Analyzing free-text responses has given the IEDA confidence that open-ended survey questions provide value not previously captured. In addition to the original survey, the three subsequent ones, along with several additional projects, have been shaped by the original text-mining methods. History: This paper was refereed. This article has been selected for inclusion in the Special Issue on Analytics Remedies to COVID-19.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 6 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.