Reproduce “VLEngagement: A Dataset of Scientific Video Lectures for Evaluating Population-based Engagement” on OpenResearch

Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.

Universal app for Apple silicon and Intel. Requires macOS 11 or later.

About this paper

Sahan Bulathwela, Maria Perez-Ortiz, Emine Yilmaz, John Shawe-Taylor

The authors introduce VLEngagement, a public dataset and baselines for estimating lecture watch-time engagement. It contains 4,046 scientific lectures across 21 subjects, with labels from 155,850 viewing records. Gradient Boosting Machines ranked lectures better with content, Wikipedia, and video features, reaching SROCC 0.6761 and pairwise accuracy 0.7446 in five-fold cross-validation; this does not establish learning gains or broad generalization.

Summary by alphaXiv.

Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.