Social Work Meta-Data

Empirical demonstrations · run locally, published openly

Demonstrations

The claims this project makes — that small, free, local AI models can query and search these databases — are tested, not asserted. Each report below is a complete, reproducible study run on a single MacBook Pro (Apple M5), with every result traceable to the code and raw outputs in the repository.

REPORT 01 · TEXT-TO-SQL

Can small local models query the databases?

Open-weight models — given nothing but the project's published skill files — answer 48 research questions across six task categories, from simple counts to multi-step analytical queries. Their SQL runs verbatim against the live databases; every answer is scored against pre-registered references. Includes the full question-by-question record with every model's SQL, and the skill-hardening feedback loop the first round produced.

Read the report
REPORT 02 · WORD EMBEDDINGS

Which embedding model best searches social work literature?

The benchmark behind this project's semantic search: embedding models — open-weight and commercial — compared head-to-head on retrieval over tens of thousands of social work abstracts, against a keyword-search baseline. The results determined the model every abstract in these databases is encoded with.

Brian E. Perron, Miao Wang, Nanyi Deng & Eunhye Ahn

Read the report
REPORT 03 · VERIFIED TOPICAL CORPUS

Artificial intelligence in social work, 1989–2026

Every article on AI in the disciplinary journals and every presentation at the SSWR conference — found by keyword and embedding search, verified by reading each abstract, and classified by what each study does rather than what it is about. The record starts with expert systems in 1989, long before generative chatbots, and the two venues turn out to publish almost inverse mixes of empirical work and commentary. Includes growth, publication outlets, an interactive co-authorship network, the labeled corpora, and the code.

Read the report
REPORT 04 · SUICIDE CORPUS

Suicide scholarship in social work, 1989–2026

Every suicide-related article in the disciplinary journals and every suicide-related presentation at SSWR, read and sorted by what kind of study each one is. A third of records that mention suicide turn out not to be about it; the literature that remains is 87 percent empirical and quantitative over qualitative five to one, and its evidence syntheses are almost all recent — none before 2004, two-thirds since 2020. Requested in two plain-English prompts, with a free local model reading all 2,034 abstracts one at a time and a frontier model spending minutes on the planning and the analysis.

Read the report