Using Computational Methods to Assess Racial, Ethnic, and Linguistic Diversity and Spatial Accessibility of the Clinical Social Work Workforce in the United States

Abstract

Objective: Racial and ethnic disparities in mental health service utilization highlight the need for a social work workforce aligned with community needs, but there is limited evidence on where such mismatches occur and which populations are underserved. This study explores (a) how computational methods can be used to assess the racial, ethnic, and linguistic diversity of the U.S. clinical social work workforce; (b) the geographic distribution of clinical social workers from different racial, ethnic, and linguistic backgrounds; and (c) how this distribution aligns with population-level needs for racially/ethnically and linguistically concordant providers. Method: We leveraged the following computational methods to analyze data from 388,471 clinical social workers in the National Provider Identifier Registry and 107,050 private practice clinical social workers from Psychology Today: (a) application programming interface and web scraping to build a population-level dataset; (b) machine learning to predict race, ethnicity, and diasporic origin of social workers; and (c) geospatial analysis to explore spatial distribution of accessibility. Results: Our analyses revealed significant geographic disparities in access to diverse providers. Conclusions: Computational and geospatial methods can identify patterns related to racial and ethnic inequities in service accessibility, providing foundational evidence to inform structural reforms for creating a more inclusive and culturally diverse clinical social work profession.

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 — 3 citations exist upstream.

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