Automated estimates of state interest group lobbying populations
- PDF / 829,684 Bytes
- 14 Pages / 439.37 x 666.142 pts Page_size
- 19 Downloads / 186 Views
Automated estimates of state interest group lobbying populations Alex Garlick1 · John Cluverius2
© Springer Nature Limited 2020
Abstract A number of strides have been taken in recent years to measure interest group populations in the American states, but sorting these groups by economic sector requires substantial investment in time and personnel. This paper introduces an automated process to estimate the industry of interest groups, using only their names. We discuss the advantages and hurdles of using automated methods and then employ a supervised learning method that produces a reliable set of estimations of the sector of more than six hundred thousand interest groups in the states. We validate these estimates in a number of ways, showing that they closely correlate to datasets employed in the literature, can replicate published results and reflect real-world events. Keywords Interest groups · Data science · State politics · Legislative studies · Text as data · Automated methods Interest groups were once central to the study of American politics, a position which has been ceded in recent decades (Anzia 2019). One reason for this disparity in attention is a lack of data availability at the subnational level compared to the national level. An encouraging trend is a series of annual censuses of the groups registered to lobby in all 50 states, conducted by the National Institute for Money in We thank anonymous reviewers and participants at the 2017 State Politics and Policy Conference in St. Louis, Missouri, for helpful comments, as well as Virginia Gray and David Lowery for sharing data. Supplementary materials and the data described in this article are available for download at the Harvard Dataverse: https://dataverse.harvard.edu/dataverse/garlick_auto. * Alex Garlick [email protected] John Cluverius [email protected] 1
The College of New Jersey, Ewing, NJ, USA
2
University of Massachusetts Lowell, Lowell, MA, USA
Vol.:(0123456789)
A. Garlick, J. Cluverius
State Politics (NIMSP). These data have been used to show the relationship between interest groups and partisan polarization (Gray et al. 2015), fiscal policy (Holyoke and Cummins 2019) and lobbying regulations (Strickland 2019). However, the offthe-shelf NIMSP data are not prepared for applied research. The economic sector of more than half of the listed groups registered to lobby in each state is missing, and there is no consistent pattern to the missingness. Each of the above projects based on NIMSP data conducted independent, intensive hand-coding procedures using different code books. These processes are difficult to replicate and require substantial resource commitments. Automated methods hold promise in this context as they require less human capital, provide transparent and replicable decision rules and can provide measures of uncertainty associated with each estimate. However, they cannot be applied in every case and pose a risk in terms of measurement error compared to human methods. We argue that estimating the density and d
Data Loading...
