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

TL;DR

This paper introduces a novel clickstream-based meta-learning approach with clustering guidance to predict student quiz performance in online videos, outperforming baseline models and providing valuable learning analytics insights.

Contribution

It develops a clustering guided meta-learning framework with self-supervised pre-training for improved student performance prediction from clickstream data.

Findings

Significant accuracy improvements over baseline models.

Effective use of self-supervised pre-training and clustering in meta-learning.

Insights into student click behavior related to knowledge acquisition.

Abstract

We study the problem of predicting student knowledge acquisition in online courses from clickstream behavior. Motivated by the proliferation of eLearning lecture delivery, we specifically focus on student in-video activity in lectures videos, which consist of content and in-video quizzes. Our methodology for predicting in-video quiz performance is based on three key ideas we develop. First, we model students' clicking behavior via time-series learning architectures operating on raw event data, rather than defining hand-crafted features as in existing approaches that may lose important information embedded within the click sequences. Second, we develop a self-supervised clickstream pre-training to learn informative representations of clickstream events that can initialize the prediction model effectively. Third, we propose a clustering guided meta-learning-based training that optimizes the prediction model to exploit clusters of frequent patterns in student clickstream sequences. Through experiments on three real-world datasets, we demonstrate that our method obtains substantial improvements over two baseline models in predicting students' in-video quiz performance. Further, we validate the importance of the pre-training and meta-learning components of our framework through ablation studies. Finally, we show how our methodology reveals insights on video-watching behavior associated with knowledge acquisition for useful learning analytics.