What Predicts Legislative Success of Early Care and Education Policies?: Applications of Machine Learning and Natural Language Processing in a Cross-State Early Childhood Policy Analysis
UW ±¬×ߺÚÁÏ faculty, Soojin Oh Park and Nail Hassairi, conducted a study that proposes a new analytic approach to unlocking the potential of legislative data to inform future policymaking in the early care and education frontier. Very few studies in the field of early childhood consider how policymaking occurs at state and federal levels and under what conditions state legislators achieve success in committees, on the floor, and at the enactment stage of the legislative process. The authors’ findings may help guide targeted advocacy efforts by assigning thing policy priorities to more senior legislators (or not intensely involving senior legislators with legislation that may be relatively easy to pass), identifying which policy priorities to push for in times or large/small majorities in the legislative bodies, or may be useful for early childhood researchers and organizations engaging in state legislative action.