Skip to content

LT_NLP_SET_pub

Product or Programme · All products and programmes
Evidence · no claims cited

Description

A GitHub repository maintained by the review authors containing the code, study lists, prompts, codebooks, frozen response bases, and adjudication materials needed to audit and reconstruct the SET-NLP evidence map.

Components

  • Versioned reproducibility repository for the SET-NLP evidence map (code, study list, prompts, codebooks, adjudication bases): A public GitHub deposit containing the materials needed to audit and reconstruct the review's analyses. The review states: "The materials needed to audit and reconstruct this review's analyses are available in a versioned code repository" at https://github.com/rafa-rodriguess/LT_NLP_SET_pub. The deposit includes the classification and prevalence code, the canonical list of the 421 included studies, the inventories of the 38 original and 32 supplementary extraction questions, operational prompt texts for discovery, screening, eligibility, and extraction, the frozen M10/M11 denominator policy and codebook, the PRISMA-ScR checklist, and the canonical bases of model responses and human adjudications. Reconstruction from the frozen bases does not require calling the models. (Eicher et al. (2026))

Claims

Key Sources

  • Eicher, J., & da Silva, R. (2026). From Sentiment Classification to Actionable and Responsible Feedback: A Scoping Review and Evidence Map of NLP in Student Evaluation of Teaching, 2015–2026. arXiv. https://arxiv.org/abs/2609.27939. doi:10.48550/arxiv.2609.27939
Page metadata
Field Value
type product
id lt-nlp-set-pub
title LT_NLP_SET_pub
description A GitHub repository maintained by the review authors containing the code, study lists, prompts, codebooks, frozen response bases, and adjudication materials needed to audit and reconstruct the SET-NLP evidence map.
status review
product_kind dataset
generated by process:settle-candidates on 2026-10-11
trust unverified — no one has confirmed this page's content

Frontmatter is the page's machine-readable record — see the Schema & Guide.