Faculty Publications

Public Policy And Broader Applications For The Use Of Text Analytics During Pandemics

Document Type

Article

Keywords

decision-making, operations management, public policy, text analytics

Journal/Book/Conference Title

Interfaces

Volume

52

Issue

6

First Page

568

Last Page

581

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.

Department

Department of Management

Department

Department of Accounting

Original Publication Date

11-1-2022

DOI of published version

10.1287/inte.2022.1137

Link to Full Text

Comments?

Share

COinS