The increased usage of computer-based learning platforms and online tools in classrooms presents new opportunities to not only study the underlying constructs involved in the learning process, but also use this information to identify and aid struggling students. Many learning platforms, particularly those driving or supplementing instruction, are only able to provide aid to students who interact with the system. With this in mind, student persistence emerges as a prominent learning construct contributing to students success when learning new material. Conversely, high persistence is not always productive for students, where additional practice does not help the student move toward a state of mastery of the material. In this paper, we apply a transfer learning methodology using deep learning and traditional modeling techniques to study high and low representations of unproductive persistence. We focus on two prominent problems in the fields of educational data mining and learner analytics representing low persistence, characterized as student "stopout," and unproductive high persistence, operationalized through student "wheel spinning," in an effort to better understand the relationship between these measures of unproductive persistence (i.e. stopout and wheel spinning) and develop early detectors of these behaviors. We find that models developed to detect each within and across-assignment stopout and wheel spinning are able to learn sets of features that generalize to predict the other. We further observe how these models perform at each learning opportunity within student assignments to identify when interventions may be deployed to best aid students who are likely to exhibit unproductive persistence.
more »
« less
Investigating Elements of Student Persistence in an Introductory Computer Science Course
We explore how different elements of student persistence on computer programming problems may be related to learning outcomes and inform us about which elements may distinguish between productive and unproductive persistence. We collected data from an introductory computer science course at a large midwestern university in the U.S. hosted on an open-source, problem-driven learning system. We defined a set of features quantifying various aspect of persistence during problem solving and used a predictive modeling approach to predict student scores on subsequent and related quiz questions. We focused on careful feature engineering and model interpretation to shed light on the intricacies of both productive and unproductive persistence. Feature importance was analyzed using SHapley Additive exPlanations (SHAP) values. We found that the most impactful features were persisting until solving the problem, rapid guessing, and taking a break, while those with the strongest correlation between their values and their impact on prediction were the number of submissions, total time, and (again) taking a break. This
suggests that the former are important features for accurate prediction, while the latter are indicative of the differences between productive persistence and wheel spinning in a computer science context.
more »
« less
- Award ID(s):
- 1942962
- NSF-PAR ID:
- 10315016
- Date Published:
- Journal Name:
- 5th Educational Data Mining in Computer Science Education (CSEDM) Workshop
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Research on non-cognitive factors has shown that persistence in the face of challenges plays an important role in learning. However, recent work on wheel-spinning, a type of unproductive persistence where students spend too much time struggling without achieving mastery of skills, show that not all persistence is uniformly beneficial for learning. For this reason, it becomes increasingly pertinent to identify the key differences between unproductive and productive persistence toward informing interventions in computer-based learning environments. In this study, we use a classification model to distinguish between productive persistence and wheel-spinning in ASSISTments, an online math learning platform. Our results indicate that there are two types of students who wheel-spin: first, students who do not request any hints in at least one problem but request more than one bottom-out hint across any 8 problems in the problem set; second, students who never request two or more bottom out hints across any 8 problems, do not request any hints in at least one problem, but who engage in relatively short delays between solving problems of the same skill. These findings suggest that encouraging students to both engage in spaced practice and use bottom-out hints sparingly is likely helpful for reducing their wheel-spinning and improving learning. These findings also provide insight on when students are struggling and how to make students' persistence more productive.more » « less
-
A prominent issue faced by the education research community is that of student attrition. While large research efforts have been devoted to studying course-level attrition, widely referred to as dropout, less research has been focused on finer-grained assignment level attrition commonly observed in K-12 classrooms. This later instantiation of attrition, referred to in this paper as “stopout,” is characterized by students failing to complete their assigned work, but the cause of such behavior are not often known. This becomes a large problem for educators and developers of learning platforms as students who give up on assignments early are missing opportunities to learn and practice the material which may affect future performance on related topics; similarly, it is difficult for researchers to develop, and subsequently difficult for computer-based systems to deploy interventions aimed at promoting productive persistence once a student has ceased interaction with the software. This difficulty highlights the importance to understand and identify early signs of stopout behavior in order to provide aid to students preemptively to promote productive persistence in their learning. While many cases of student stopout may be attributable to gaps in student knowledge and indicative of struggle, student attributes such as grit and persistence may be further affected by other factors. This work focuses on identifying different forms of stopout behavior in the context of middle school math by observing student behaviors at the sub-problem level. We find that students exhibit disproportionate stopout on the first problem of their assignments in comparison to stopout on subsequent problems, identifying a behavior that we call “refusal,” and use the emerging patterns of student activity to better understand the potential causes underlying stopout behavior early in an assignment.more » « less
-
This work falls under the evidence-based practice type of paper. Online undergraduate engineering education is rapidly increasing in use. The online format not only provides greater flexibility and ease of access for students, but also has lower costs for universities when compared to face-to-face courses. Even with these generally positive attributes, online courses face challenges with respect to student attrition. Numerous studies have shown that the dropout rate in online courses is higher than that for in-person courses, and topics related to online student persistence remain of interest. Data describing student interactions with their Learning Management System (LMS) provide an important lens through which online student engagement and corresponding persistence decisions can be studied, but many engineering education researchers may lack experience in working with LMS interaction data. The purpose of this paper is to provide a concrete example for other engineering education researchers of how LMS interaction data from online undergraduate engineering courses can be prepared for analysis. The work presented here is part of a larger National Science Foundation-funded study dedicated to developing a theoretical model for online undergraduate engineering student persistence based on student LMS interaction activities and patterns. Our sample dataset includes six courses, two from electrical engineering and four from engineering management, offered during the fall 2018 semester at a large, public southwestern university. The LMS interaction data provides details about students’ navigations to and submissions of different course elements including quizzes, assignments, discussion forums, wiki pages, attachments, modules, the syllabus, the gradebook, and course announcements. Relatedly, the features created from the data in this study can be classified into three categories: 1) learning page views, which capture student interactions with course content, 2) procedural page views, which capture student navigation to course management activities, and 3) social page views, which capture learner-to-learner and learner-to-instructor interactions. The full paper will provide the rationale and details involved in choices related to data cleaning, manipulation, and feature creation. A complete list of features will also be included. These features will ultimately be combined with associative classification to discover relationships between student-LMS interactions and persistence decisions.more » « less
-
Background and Context: Students’ self-efficacy toward computing affect their participation in related tasks and courses. Self- efficacy is likely influenced by students’ initial experiences and exposure to computer science (CS) activities. Moreover, student interest in a subject likely informs their ability to effectively regulate their learning in that domain. One way to enhance interest in CS is through using collaborative pair programming. Objective: We wanted to explore upper elementary students’ self- efficacy for and conceptual understanding of CS as manifest in collaborative and regulated discourse during pair programming. Method: We implemented a five-week CS intervention with 4th and 5th grade students and collected self-report data on students’ CS attitudes and conceptual understanding, as well as transcripts of dyads talking while problem solving on a pair programming task. Findings: The students’ self-report data, organized by dyad, fell into three categories based on the dyad’s CS self-efficacy and conceptual understanding scores. Findings from within- and cross-case analyses revealed a range of ways the dyads’ self-efficacy and CS conceptual understanding affected their collaborative and regulated discourse. Implications: Recommendations for practitioners and researchers are provided. We suggest that upper elementary students learn about productive disagreement and how to peer model. Additionally, our findings may help practitioners with varied ways to group their students.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- The DOI is not currently available.
