Stimuli-Sensitive Hawkes Processes for Personalized Student Procrastination Modeling

TL;DR

This paper introduces a personalized stimuli-sensitive Hawkes process model that predicts student activity timings in online learning, accounting for assignment deadlines, availability, and individual habits, outperforming existing models.

Contribution

The paper proposes a novel personalized stimuli-sensitive Hawkes process model that effectively predicts student activities by incorporating course properties and individual differences, even with missing data.

Findings

Superior prediction accuracy on synthetic and real datasets

Effective modeling of external stimuli like deadlines and availability

Flexible parameterization of student activity intensities

Abstract

Student procrastination and cramming for deadlines are major challenges in online learning environments, with negative educational and well-being side effects. Modeling student activities in continuous time and predicting their next study time are important problems that can help in creating personalized timely interventions to mitigate these challenges. However, previous attempts on dynamic modeling of student procrastination suffer from major issues: they are unable to predict the next activity times, cannot deal with missing activity history, are not personalized, and disregard important course properties, such as assignment deadlines, that are essential in explaining the cramming behavior. To resolve these problems, we introduce a new personalized stimuli-sensitive Hawkes process model (SSHP), by jointly modeling all student-assignment pairs and utilizing their similarities, to predict students' next activity times even when there are no historical observations. Unlike regular point processes that assume a constant external triggering effect from the environment, we model three dynamic types of external stimuli, according to assignment availabilities, assignment deadlines, and each student's time management habits. Our experiments on two synthetic datasets and two real-world datasets show a superior performance of future activity prediction, comparing with state-of-the-art models. Moreover, we show that our model achieves a flexible and accurate parameterization of activity intensities in students.