There are various methods for classifying nonprofit organizations (NPOs) according to their field of activity. We report our experiences using two semi-automated methods based on textual data: rule-based classification and machine learning with curated keywords. We use those methods to classify Austrian nonprofit organizations based on the International Classification of Nonprofit Organizations. Those methods can provide a solution to the widespread research problem that quantitative data on the activities of NPOs are needed but not readily available from administrative data, long high-quality texts describing NPOs’ activities are mostly unavailable, and human labor resources are limited. We find that in such a setting, rule-based classification performs about as well as manual human coding in terms of precision and sensitivity, while being much more labor-saving. Hence, we share our insights on how to efficiently implement such a rule-based approach. To address scholars with a background in data analytics as well as those without, we provide non-technical explanations and open-source sample code that is free to use and adapt.
|Pages (from-to)||227 - 237|
|Journal||Voluntas: International Journal of Voluntary and Nonprofit Organizations|
|Publication status||Published - 2020|
Austrian Classification of Fields of Science and Technology (ÖFOS)
- 506009 Organisation theory
- 502023 NPO research
- 509005 Gerontology