Skip to content

BERT strategy-embedding and successful-strategy prediction from MATHia logs

Research Method · All research methods
Evidence · 1 claim (1 for) · 1 study (1 associational), q1 · 0 of 1 report an effect size · 1 claim rests on one study

Description

A BERT-based model the authors train to learn embeddings for math strategies from MATHia student log data, together with a prediction task that distinguishes between successful and unsuccessful strategy use. The authors analyze the model's results to reveal deeper insights into student strategies. Code for the fine-tuned BERT model is released in a public GitHub repository.

Accounts

  • BERT strategy-embedding model and successful-strategy prediction task for MATHia logs: A BERT-based model the authors train to learn embeddings for math strategies from MATHia student log data, together with a prediction task that distinguishes between successful and unsuccessful strategy use. The authors analyze the model's results to reveal deeper insights into student strategies. Code for the fine-tuned BERT model is released in a public GitHub repository. (Magar et al. (2025))

Claims

-

Key Sources

  • Magar, A.T., Fancsali, S.E., Rus, V., Murphy, A., Ritter, S., Venugopal, D. (2025). Analyzing Strategies in MATHia with BERT. In: Artificial Intelligence in Education. AIED 2025. Springer, Cham. https://doi.org/10.1007/978-3-031-98465-5_15
Page metadata
Field Value
type research-method
id bert-strategy-embedding-and-successful-strategy-prediction-from-mathia-logs
title BERT strategy-embedding and successful-strategy prediction from MATHia logs
description A BERT-based model the authors train to learn embeddings for math strategies from MATHia student log data, together with a prediction task that distinguishes between successful and unsuccessful strategy use.
status review
moved_from element/bert-strategy-embedding-model-mathia
generated by process:sweep-kinds on 2026-10-10
trust unverified — no one has confirmed this page's content
sources 1 — magar-2025

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