Stimuli-Sensitive Hawkes Processes for Personalized Student Procrastination Modeling

Stimuli-Sensitive Hawkes Processes for Personalized Student Procrastination Modeling
复制标题

用于个性化学生拖延建模的刺激敏感霍克斯过程

DOI:
10.1145/3442381.3450104
复制
发表时间:
2021
期刊:
Proceedings of the Web Conference 2021
影响因子:
--
通讯作者:
Feyzi Behnagh, Reza
Feyzi Behnagh, Reza
中科院分区:
--
文献类型:
--
作者:
Yao, Mengfan;Zhao, Siqian;Sahebi, Shaghayegh;Feyzi Behnagh, Reza

文献摘要

参考文献

被引文献

相似文献

学生拖延症和死记硬背是在线学习环境的主要挑战,对教育和健康都有负面影响。在连续时间内对学生活动进行建模并预测他们的下一次学习时间是重要的问题,可以帮助创建个性化的及时干预措施来减轻这些挑战。然而,之前对学生拖延症的动态建模的尝试存在一些主要问题:它们无法预测下一个活动时间,无法处理缺失的活动历史,没有个性化,并且忽略了重要的课程属性,例如作业截止日期,而这些属性对于解释填鸭式行为至关重要。为了解决这些问题,我们引入了一种新的个性化刺激敏感Hawkes过程模型(SSHP),通过联合建模所有学生作业对并利用它们的相似性,即使在没有历史观察的情况下,也可以预测学生的下一次活动时间。不像常规的点过程假设来自环境的恒定外部触发效应,我们根据作业的可用性、作业的截止日期和每个学生的时间管理习惯,建立了三种动态类型的外部刺激模型。我们在两个合成数据集和两个真实数据集上的实验表明,与最先进的模型相比,我们的模型在未来活动预测方面表现出色。此外,我们表明,我们的模型实现了灵活和准确的参数化学生的活动强度。
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.
基于作业开始时间的在线学习拖延指数
DOI: --
发表时间: 2020
期刊: Educational Data Mining
影响因子: --
作者:
L. Agnihotri;R. Baker;Steve Stalzer
通讯作者: Steve Stalzer
使用内容信息传输 Hawkes 进程
DOI: --
发表时间: 2018
期刊: Industrial Conference on Data Mining
影响因子: --
作者:
Tianbo Li;Pengfei Wei;Yiping Ke
通讯作者: Yiping Ke
DevEventTracker:跟踪开发事件以评估增量开发和拖延
DOI: 10.1145/3059009.3059050
发表时间: 2017
期刊: Proceedings of the 2017 ACM Conference on Innovation and Technology in Computer Science Education
影响因子: --
作者:
Ayaan M. Kazerouni;Stephen H. Edwards;T. Simin Hall;Clifford A. Shaffer
通讯作者: Clifford A. Shaffer
DOI: 10.1016/j.paid.2004.04.009
发表时间: 2005-01-01
影响因子: 4.3
作者:
Moon, SM;Illingworth, AJ
通讯作者: Illingworth, AJ
重复关于学生在线学习成功的 21 项研究结果
DOI: --
发表时间: 2017
期刊:
影响因子: --
作者:
J. M. Andres;R. Baker;George Siemens;D. Gašević;Catherine A. Spann
通讯作者: Catherine A. Spann