LecEval: An Automated Metric for Multimodal Knowledge Acquisition in Multimedia Learning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yin, Joy Lim Jia, Zhang-Li, Daniel, Yu, Jifan, Li, Haoxuan, Tu, Shangqing, Wang, Yuanchun, Liu, Zhiyuan, Liu, Huiqin, Hou, Lei, Li, Juanzi, Xu, Bin
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913819735883776
author Yin, Joy Lim Jia
Zhang-Li, Daniel
Yu, Jifan
Li, Haoxuan
Tu, Shangqing
Wang, Yuanchun
Liu, Zhiyuan
Liu, Huiqin
Hou, Lei
Li, Juanzi
Xu, Bin
author_facet Yin, Joy Lim Jia
Zhang-Li, Daniel
Yu, Jifan
Li, Haoxuan
Tu, Shangqing
Wang, Yuanchun
Liu, Zhiyuan
Liu, Huiqin
Hou, Lei
Li, Juanzi
Xu, Bin
contents Evaluating the quality of slide-based multimedia instruction is challenging. Existing methods like manual assessment, reference-based metrics, and large language model evaluators face limitations in scalability, context capture, or bias. In this paper, we introduce LecEval, an automated metric grounded in Mayer's Cognitive Theory of Multimedia Learning, to evaluate multimodal knowledge acquisition in slide-based learning. LecEval assesses effectiveness using four rubrics: Content Relevance (CR), Expressive Clarity (EC), Logical Structure (LS), and Audience Engagement (AE). We curate a large-scale dataset of over 2,000 slides from more than 50 online course videos, annotated with fine-grained human ratings across these rubrics. A model trained on this dataset demonstrates superior accuracy and adaptability compared to existing metrics, bridging the gap between automated and human assessments. We release our dataset and toolkits at https://github.com/JoylimJY/LecEval.
format Preprint
id arxiv_https___arxiv_org_abs_2505_02078
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle LecEval: An Automated Metric for Multimodal Knowledge Acquisition in Multimedia Learning
Yin, Joy Lim Jia
Zhang-Li, Daniel
Yu, Jifan
Li, Haoxuan
Tu, Shangqing
Wang, Yuanchun
Liu, Zhiyuan
Liu, Huiqin
Hou, Lei
Li, Juanzi
Xu, Bin
Computation and Language
Artificial Intelligence
Evaluating the quality of slide-based multimedia instruction is challenging. Existing methods like manual assessment, reference-based metrics, and large language model evaluators face limitations in scalability, context capture, or bias. In this paper, we introduce LecEval, an automated metric grounded in Mayer's Cognitive Theory of Multimedia Learning, to evaluate multimodal knowledge acquisition in slide-based learning. LecEval assesses effectiveness using four rubrics: Content Relevance (CR), Expressive Clarity (EC), Logical Structure (LS), and Audience Engagement (AE). We curate a large-scale dataset of over 2,000 slides from more than 50 online course videos, annotated with fine-grained human ratings across these rubrics. A model trained on this dataset demonstrates superior accuracy and adaptability compared to existing metrics, bridging the gap between automated and human assessments. We release our dataset and toolkits at https://github.com/JoylimJY/LecEval.
title LecEval: An Automated Metric for Multimodal Knowledge Acquisition in Multimedia Learning
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2505.02078