Classification of Important Segments in Educational Videos using Multimodal Features
This addresses the challenge of extracting key sections from long educational videos for learners and platforms, but it is incremental as it builds on existing multimodal methods.
The paper tackles the problem of automatically assigning importance scores to segments in educational videos by introducing a new annotated dataset and a multimodal neural architecture that uses audio, visual, and textual features, with experiments showing the impact of these features on prediction.
Videos are a commonly-used type of content in learning during Web search. Many e-learning platforms provide quality content, but sometimes educational videos are long and cover many topics. Humans are good in extracting important sections from videos, but it remains a significant challenge for computers. In this paper, we address the problem of assigning importance scores to video segments, that is how much information they contain with respect to the overall topic of an educational video. We present an annotation tool and a new dataset of annotated educational videos collected from popular online learning platforms. Moreover, we propose a multimodal neural architecture that utilizes state-of-the-art audio, visual and textual features. Our experiments investigate the impact of visual and temporal information, as well as the combination of multimodal features on importance prediction.