Methods for Classifying Nonprofit Organizations According to their Field of Activity: A Report on Semi-automated Methods Based on Text

Abstract

Abstract 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.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 40 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.