sfa_simplify: Response-Free Scale Simplification

In semanticfa: Semantic Factor Analysis of Language Model Embeddings

Response-Free Scale Simplification

Description

Selects a reduced (short-form) item set per group using only the items' semantic structure — no human response data — and reports how well the reduced set preserves the factor structure of the full scale (in the spirit of Wang et al., 2026; Jung & Seo, 2025). It selects items by centroid/medoid proximity within a grouping, rather than reimplementing those papers' specific clustering pipelines. The output is a candidate short form that should be validated psychometrically before use.

Usage

sfa_simplify(
  x,
  target_n,
  method = c("anchor", "medoid"),
  groups = c("theoretical", "fitted"),
  ...
)

Arguments

x	An object of class "sfa" with stored input embeddings (fit with this version of sfa()).
target_n	Integer number of items to keep per group. Groups with <= target_n items are kept in full.
method	"anchor" (default) or "medoid".
groups	How items are grouped before trimming: "theoretical" (default; the factor labels supplied to sfa()) or "fitted" (each item assigned to its strongest extracted factor — lets the groups emerge from the items, after Jung & Seo 2025, and needs no theoretical key).
...	Currently unused.

Details

Two selection strategies are offered:

"anchor"

(default) Keep the items most similar to their own group's centroid (un-flipped, leave-one-out; see sfa_anchor); drop the weakest. Simple and interpretable, but can retain near-duplicate items (see sfa_redundancy).

"medoid"

Within each group, greedily select items that are both representative (close to the group centroid) and non-redundant (spread apart in embedding space). Trades a little central tendency for broader coverage.

After selection the scale is re-fit on the kept items and compared with the full-scale solution: number of factors retained and structure recovery against the theoretical grouping (NMI and ARI).

Value

An object of class "sfa_simplify": a list with keep (kept item codes), drop (dropped items with reasons), the re-fit reduced_fit, and a fidelity report.

References

Wang, B., Zhang, Y., Hu, Y., Hou, H., Peng, K., & Ni, S. (2026). Discovering semantic latent structures in psychological scales: A response-free pathway to efficient simplification. arXiv:2602.12575 (preprint).

Jung, S.-J., & Seo, J.-W. (2025). A transformer-based embedding approach to developing short-form psychological measures. Frontiers in Psychology, 16, Article 1640864. \Sexpr[results=rd]{tools:::Rd_expr_doi("10.3389/fpsyg.2025.1640864")}

See Also

sfa_anchor, sfa_redundancy, sfa_congruence

Examples

data(big5)
fit <- sfa(
  data.frame(code = big5$codes, item = big5$items,
             factor = big5$factors, scoring = big5$scoring),
  embeddings = big5$embeddings, scoring = big5$scoring, nfactors = 5)

# keep the 5 most representative items per construct
short <- sfa_simplify(fit, target_n = 5, method = "anchor")
short$keep

# group by the fitted factors instead of the supplied key (needs no labels)
sfa_simplify(fit, target_n = 5, groups = "fitted")$keep

semanticfa documentation built on Sept. 2, 2026, 1:07 a.m.