Scalable and Explainable Learner-Video Interaction Prediction using Multimodal Large Language Models
This work addresses the need for scalable and explainable tools for instructors to pre-screen educational video design, with incremental improvements in applying multimodal large language models to this domain.
The paper tackled the problem of predicting learners' video control interactions (e.g., pausing, skipping) from video content alone to assess cognitive load and instructional design, achieving reliable prediction of interaction peaks and generalization to unseen academic fields using a dataset of 77 million events from 66 courses.
Learners' use of video controls in educational videos provides implicit signals of cognitive processing and instructional design quality, yet the lack of scalable and explainable predictive models limits instructors' ability to anticipate such behavior before deployment. We propose a scalable, interpretable pipeline for predicting population-level watching, pausing, skipping, and rewinding behavior as proxies for cognitive load from video content alone. Our approach leverages multimodal large language models (MLLMs) to compute embeddings of short video segments and trains a neural classifier to identify temporally fine-grained interaction peaks. Drawing from multimedia learning theory on instructional design for optimal cognitive load, we code features of the video segments using GPT-5 and employ them as a basis for interpreting model predictions via concept activation vectors. We evaluate our pipeline on 77 million video control events from 66 online courses. Our findings demonstrate that classifiers based on MLLM embeddings reliably predict interaction peaks, generalize to unseen academic fields, and encode interpretable, theory-relevant instructional concepts. Overall, our results show the feasibility of cost-efficient, interpretable pre-screening of educational video design and open new opportunities to empirically examine multimedia learning theory at scale.