saydo: Link What People Say to What They Do with LLM-Coded Themes
Measures the say-do gap in mixed-methods data: whether themes
in what people say go with differences in what they do. Codes free text
against a codebook with large language models through 'ellmer', or any
coder function, and validates the codes against a human-coded sample
with Cohen's kappa, precision and recall. Links the codes to
participants' behavioural or outcome data, aggregating segment-level
transcripts to participants where needed, and tests each theme against
each metric with Welch's t-test and multiple-comparison adjustment.
Developed by Neudata Consulting Ltd.
| Version: |
0.1.0 |
| Depends: |
R (≥ 4.1) |
| Imports: |
cli, ellmer (≥ 0.3.0), ggplot2 (≥ 3.5.0), rlang, stats, tibble, withr |
| Suggests: |
knitr, rmarkdown, testthat (≥ 3.0.0) |
| Published: |
2026-10-28 |
| DOI: |
10.32614/CRAN.package.saydo (may not be active yet) |
| Author: |
Bernard Isekah Osangir [aut, cre],
Neudata Consulting Ltd [cph, fnd] |
| Maintainer: |
Bernard Isekah Osangir <b.osangir at gmail.com> |
| BugReports: |
https://github.com/neu-data/saydo/issues |
| License: |
MIT + file LICENSE |
| URL: |
https://neu-data.github.io/saydo/,
https://github.com/neu-data/saydo |
| NeedsCompilation: |
no |
| Materials: |
README, NEWS |
| CRAN checks: |
saydo results |
Documentation:
Downloads:
Linking:
Please use the canonical form
https://CRAN.R-project.org/package=saydo
to link to this page.