Preprocessed English subset of the MARS dataset for multimodal teaching resource recommendation

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

Description

A preprocessed English-language subset of the MARS multimodal teaching-resource dataset, containing resource metadata and learner interaction logs for evaluating personalized recommendation models.

Components

Claims

• The CF–KG hybrid model achieves higher offline NDCG than all eight baselines on the MARS English subset, reaching about 0.625 at epoch 40 [+W]
• CF–KG achieves the best NDCG and hit rate on text, video, and interactive resource subsets, with modest but consistent gains over KGAT [+W]
• The CF–KG hybrid model achieves the highest hit rate among all compared methods, rising from 0.718 to 0.751 across training [~W]

Related Products and Programmes

-

Key Sources

• Bin Liu, Xiaoli Sun, Jia Song. (2026). A hybrid collaborative filtering and knowledge graph-based cross-domain recommendation method for multimodal teaching resources. Computers and Education: Artificial Intelligence. https://doi.org/10.1016/j.caeai.2026.100678

Page metadata

Field	Value
type	product
id	preprocessed-english-subset-of-the-mars-dataset-for-multimodal-teaching-resource-recommend
title	Preprocessed English subset of the MARS dataset for multimodal teaching resource recommendation
description	A preprocessed English-language subset of the MARS multimodal teaching-resource dataset, containing resource metadata and learner interaction logs for evaluating personalized recommendation models.
status	review
product_kind	dataset
generated	by process:settle-candidates on 2026-10-12
trust	unverified — no one has confirmed this page's content

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