Machine learning meets the Journal of Public Budgeting and Finance: Topics and trends over 40 years
The study identifies 15 key thematic topics that most optimally represent the 1028 articles that were published in the studied period from 1981 to 2020 and reveals the dynamic changes in the popularity of each thematic topic over time.
Abstract
This research aims to mark the 40th anniversary of Public Budgeting & Finance (PB&F) by providing a retrospective of its journey over the past 40 years using the method of an unsupervised machine learning technique—structural topic modeling (STM). The study identifies 15 key thematic topics that most optimally represent the 1028 articles that were published in the studied period from 1981 to 2020. Furthermore, the study reveals the dynamic changes in the popularity of each thematic topic over time. This research identifies past and emerging research trends in PB&F to help scholars and students keep sight of the overall landscape of public budgeting and finance literature.