Hawkes processes have been shown to be efficient in modeling bursty sequences in a variety of applications, such as finance and social network activity analysis. Traditionally, these models parameterize each process independently and assume that the history of each point process can be fully observed. Such models could however be inefficient or even prohibited in certain real-world applications, such as in the field of education, where such assumptions are violated. Motivated by the problem of detecting and predicting student procrastination in students Massive Open Online Courses (MOOCs) with missing and partially observed data, in this work, we propose a novel personalized Hawkes process model (RCHawkes-Gamma) that discovers meaningful student behavior clusters by jointly learning all partially observed processes simultaneously, without relying on auxiliary features. Our experiments on both synthetic and real-world education datasets show that RCHawkes-Gamma can effectively recover student clusters and their temporal procrastination dynamics, resulting in better predictive performance of future student activities. Our further analyses of the learned parameters and their association with student delays show that the discovered student clusters unveil meaningful representations of various procrastination behaviors in students.
Temporal Processes Associating with Procrastination Dynamics
Procrastination, as an act of voluntarily delaying tasks, is particularly pronounced among students. Recent research has proposed several solutions to modeling student behaviors with the goal of procrastination modeling. Particularly, temporal and sequential models, such as Hawkes processes, have proven to be successful in capturing students’ behavioral dynamics as a representation of procrastination. However, these discovered dynamics are yet to be validated with psychological measures of procrastination through student self-reports and surveys. In this work, we fill this gap by discovering associations between temporal procrastination modeling in students with students’ chronic and academic procrastination levels and their goal achievement. Our analysis reveals meaningful relationships between the learning dynamics discovered by Hawkes processes with student procrastination and goal achievement based on student self-reported data. Most importantly, it shows that students who exhibit inconsistent and less regular learning activities, driven by the goal to outperform or perform not worse than other students, also reported a higher degree of procrastination.
- Award ID(s):
- 1917949
- Publication Date:
- NSF-PAR ID:
- 10334657
- Journal Name:
- Artificial Intelligence in Education: 22nd International Conference
- Page Range or eLocation-ID:
- 459–471
- ISSN:
- 1611-3349
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
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 parameterizationmore »
-
Need/Motivation (e.g., goals, gaps in knowledge) The ESTEEM implemented a STEM building capacity project through students’ early access to a sustainable and innovative STEM Stepping Stones, called Micro-Internships (MI). The goal is to reap key benefits of a full-length internship and undergraduate research experiences in an abbreviated format, including access, success, degree completion, transfer, and recruiting and retaining more Latinx and underrepresented students into the STEM workforce. The MIs are designed with the goals to provide opportunities for students at a community college and HSI, with authentic STEM research and applied learning experiences (ALE), support for appropriate STEM pathway/career, preparation and confidence to succeed in STEM and engage in summer long REUs, and with improved outcomes. The MI projects are accessible early to more students and build momentum to better overcome critical obstacles to success. The MIs are shorter, flexibly scheduled throughout the year, easily accessible, and participation in multiple MI is encouraged. ESTEEM also establishes a sustainable and collaborative model, working with partners from BSCS Science Education, for MI’s mentor, training, compliance, and building capacity, with shared values and practices to maximize the improvement of student outcomes. New Knowledge (e.g., hypothesis, research questions) Research indicates that REU/internship experiences canmore »
-
Abstract: Modeling student learning processes is highly complex since it is influenced by many factors such as motivation and learning habits. The high volume of features and tools provided by computer-based learning environments confounds the task of tracking student knowledge even further. Deep Learning models such as Long-Short Term Memory (LSTMs) and classic Markovian models such as Bayesian Knowledge Tracing (BKT) have been successfully applied for student modeling. However, much of this prior work is designed to handle sequences of events with discrete timesteps, rather than considering the continuous aspect of time. Given that time elapsed between successive elements in a student’s trajectory can vary from seconds to days, we applied a Timeaware LSTM (T-LSTM) to model the dynamics of student knowledge state in continuous time. We investigate the effectiveness of T-LSTM on two domains with very different characteristics. One involves an open-ended programming environment where students can self-pace their progress and T-LSTM is compared against LSTM, Recent Temporal Pattern Mining, and the classic Logistic Regression (LR) on the early prediction of student success; the other involves a classic tutor-driven intelligent tutoring system where the tutor scaffolds the student learning step by step and T-LSTM is compared with LSTM, LR,more »
-
Student-instructor interactions have an influence on student achievement and perceptions of learning. In college and university settings, large introductory STEM courses are increasingly including Peer-Led Team Learning (PLTL), an evidence-based technique associated with improved student achievement, recruitment, and retention in STEM fields, especially for underserved populations. Within this technique, peer leaders hold a unique position in a student’s education. Peer leaders have relevant experience in that they have had recent success in the courses in which they facilitate student learning, yet, compared to student-faculty or student-teaching assistant relationships, there is minimal imbalance of authority or power. Students might find their peer leaders to be more relatable than faculty or graduate teaching assistants, and may even consider them to be role models. We explored students’ perceptions of peer leader relatability and role model status in relation to students’ achievement and their perceived learning gains in the context of an introductory biology course with an associated PLTL program. The final course grades and self-assessed learning gains of PLTL students who felt they related to their peer leader were compared to those who did not. We also compared final course grades and self-assessed learning gains between PLTL students who viewed their peer leadermore »
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Publisher's Version of Record
- https://doi.org/10.1007/978-3-030-78292-4_37
