Publicly released fine-tuned BERT model and code for coding self-affirmation essays

Product or Programme · All products and programmes
Evidence · 4 claims (3 for, 1 mixed) · 2 studies (1 causal, 1 design), q2–q3 · 0 of 2 report an effect size · 4 claims rest on one study

Description

Ye et al.'s publicly released Keras implementation and fine-tuned BERT classifier automate coding student essays as self-affirming or general for research use.

Components

Claims

• The fine-tuned BERT model's classification performance is consistent across stereotype-threatened and non-threatened students and other demographic subgroups [+W]
• The fine-tuned BERT model generalizes to an external dataset collected by a different research team, maintaining almost perfect agreement with human coders [+W]
• A fine-tuned BERT model achieves almost perfect agreement with human coders when classifying student self-affirmation essays, matching human-human reliability [+W]
• Mid-range degradation is conditioned on task-specific adaptation: it is most severe for few-shot LLMs with few examples, decreases with more task-specific data, and is mildest for the fine-tuned encoder [~W]

Related Products and Programmes

-

Key Sources

• Ye, C., Borman, T. H., & Borman, G. D. (2026). Automating Self-Affirmation Essay Coding: Fine-Tuned BERT Performance Comparable to Human Coders and Comparison with GPT-4. Journal of Educational Data Mining, Volume 18, No 1. https://github.com/visortown/bert-self-affirm

Page metadata

Field	Value
type	product
id	publicly-released-fine-tuned-bert-model-and-code-for-coding-self-affirmation-essays
title	Publicly released fine-tuned BERT model and code for coding self-affirmation essays
description	Ye et al.'s publicly released Keras implementation and fine-tuned BERT classifier automate coding student essays as self-affirming or general for research use.
status	review
moved_from	element/bert-self-affirmation-essay-classifier-released-model
product_kind	software
generated	by process:sweep-kinds on 2026-10-10
trust	unverified — no one has confirmed this page's content
sources	1 — ye-2026

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