An official website of the United States government
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.
more »
« less
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.
more »
« less
- Award ID(s):
- 1917949
- PAR ID:
- 10334657
- Date Published:
- Journal Name:
- Artificial Intelligence in Education: 22nd International Conference
- ISSN:
- 1611-3349
- Page Range / eLocation ID:
- 459–471
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Procrastination is a major issue faced by students which can lead to negative impacts on their academic performance and mental health. Productivity tools aim to help individuals to alleviate this behavior by providing self-regulatory support. However, the processes of how these applications help students conquer academic procrastination are under-explored. Particularly, it is essential to understand what aspects of these applications help which kinds of students in accomplishing their academic tasks. In this paper, we address this gap by presenting an academic planning and time management app (Proccoli) and a study designed to understand the association between student procrastination modeling, in-app behaviors, and perceived performance with app evaluation. As the core of our study, we analyze student perceptions of Proccoli and its impact on their study tasks and time management skills. Then, we model student procrastination behaviors by Hawkes process mining, assess student in-app behaviors by specifying planning and performance-related measures and evaluate the relationship between student behaviors and the evaluation survey results. Our study shows a need for personalized self-regulation support in Proccoli, as students with different in-app studying behaviors are found to have different perceptions of the app functionalities and the association between the prompts for social accountability students received by using Proccoli and their procrastination behavior is significant.more » « less
-
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.more » « less
-
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 leader as a role model versus those who did not. Self-reported learning gains were significantly higher for students who relate to their peer leader, as well as for students who viewed their peer leaders as a role model. There is some support that this trend is stronger for STEM majors versus those who are not enrolled in a STEM program, though the interaction is not significant. Significant differences in overall course grade were only observed between students who reported that they related to their peer leader versus those who did not relate to their peer leader.more » « less
-
Students’ view of intelligence (i.e., their mindset beliefs) has been found to be related to their self-efficacy and goal orientations as well as to influence their course outcomes. Comparisons of students’ chemistry mindset between different groups found that organic chemistry I students held more of a growth mindset than general chemistry I students at the beginning of a term. Additionally, men tended to hold more growth mindset beliefs than women. Given these differences, structural equation modeling was used to explore the relations between students’ mindset, self-efficacy, and goal orientations, along with their relation to achievement outcomes within a course. An indirect effect of mindset on summative achievement was found to be mediated through performance-avoidance goals, whereas the relation between self-efficacy and summative achievement was mediated through performance-approach, mastery-avoidance, and performance-avoidance goal orientations. While mindset was not found to be directly or indirectly related to formative achievement outcomes, self-efficacy was found to have an indirect effect on formative achievement through mastery-approach and mastery-avoidance goal orientations. Additionally, an interaction between mindset and self-efficacy was found to be related to performance-avoidance goals, as has been suggested in prior studies. These results point to the importance of mindset on achievement outcomes while also considering influences from self-efficacy and goal orientations. Future work is encouraged to investigate how these variables are related when they are measured throughout a term.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- https://doi.org/10.1007/978-3-030-78292-4_37
