How to Code a Million Missions: Developing Bespoke Nonprofit Activity Codes Using Machine Learning Algorithms

• Published in: Voluntas (Manchester, England) Vol. 34; no. 1; pp. 29 - 38
• Main Authors: Santamarina, Francisco J., Lecy, Jesse D., van Holm, Eric Joseph
• Format: Journal Article
• Language: English
• Published: New York Springer US 01.02.2023; Springer Nature B.V
• Subjects: Accuracy; Algorithms; Automation; Classification; Codes; Datasets; Human performance; Machine learning; Mission statements; Nonprofit organizations; Political Science; Research Papers; Set sizes; Social Policy; Social Sciences; Tax exempt organizations; Taxonomy; Training; Validity; Voluntary organizations; Nonprofit organizations; Custom taxonomies; Classification; Machine learning
• ISSN: 0957-8765; 1573-7888
• DOI: 10.1007/s11266-021-00420-z

National Taxonomy of Exempt Entities (NTEE) codes have become the primary classifier of nonprofit missions since they were developed in the mid-1980s in response to growing demands for a taxonomy of nonprofit activities (Herman in Nonprofit and Voluntary Sector Quarterly 19(3):293–306, 1990, Barman in Social Science History 37:103–141, 2013). However, the increasingly complex nature of nonprofits means that NTEE codes may be outdated or lack specificity. As an alternative, scholars and practitioners can create a bespoke taxonomy for a specific purpose by hand-coding a training dataset and using machine learning classifiers to apply the codes to a large population. This paper presents a framework for determining training set sizes needed to scale custom taxonomies using machine learning algorithms.