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

TL;DR

LecEval is an automated, theory-based metric for assessing multimodal knowledge acquisition in slide-based multimedia learning, addressing limitations of existing evaluation methods.

Contribution

It introduces LecEval, a novel automated evaluation metric grounded in multimedia learning theory, with a large annotated dataset and superior accuracy over existing metrics.

Findings

LecEval outperforms existing metrics in accuracy and adaptability.

A large-scale dataset of 2,000+ slides with human annotations was curated.

LecEval effectively bridges automated and human assessment gaps.

Abstract

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.