English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

We study the problem of predicting student knowledge acquisition in onlinecourses from clickstream behavior. Motivated by the proliferation of eLearninglecture delivery, we specifically focus on student in-video activity inlectures videos, which consist of content and in-video quizzes. Our methodologyfor predicting in-video quiz performance is based on three key ideas wedevelop. First, we model students' clicking behavior via time-series learningarchitectures operating on raw event data, rather than defining hand-craftedfeatures as in existing approaches that may lose important information embeddedwithin the click sequences. Second, we develop a self-supervised clickstreampre-training to learn informative representations of clickstream events thatcan initialize the prediction model effectively. Third, we propose a clusteringguided meta-learning-based training that optimizes the prediction model toexploit clusters of frequent patterns in student clickstream sequences. Throughexperiments on three real-world datasets, we demonstrate that our methodobtains substantial improvements over two baseline models in predictingstudents' in-video quiz performance. Further, we validate the importance of thepre-training and meta-learning components of our framework through ablationstudies. Finally, we show how our methodology reveals insights onvideo-watching behavior associated with knowledge acquisition for usefullearning analytics.

Click-Based Student Performance Prediction: A Clustering Guided Meta-Learning Approach