Platform design in educational contexts
Abstract/Contents
- Abstract
- Educational platforms have grown increasingly important as learning occurs in digitally mediated environments, and this growth has only been accelerated by the COVID-19 pandemic. My dissertation explores three domains of platform design in education research. I frame my work with the conceptual tools of operations research and industrial engineering. In the first paper I cast online learning as a blending/mixture problem. I explore the relationship between video playback speed and student learning outcomes in massive open online courses. Using an experimental design, I present the results of a pre-registered study that assigns users to watch videos embedded in courses at either 1.0x or 1.25x speed. I find that students who consume temporally accelerated content are more likely to get better grades in a course, attempt more content, and obtain more certificates. I also find that when videos are sped up, students spend less time consuming videos and are marginally more likely to complete more video content. In the second paper I examine postsecondary degree completion as a production scheduling problem, and build a forecasting toolkit to identify and anticipate students' career trajectories. Using transcript data capturing the academic careers of 26,892 undergraduates enrolled at a private university between 2000 and 2020, I describe enrollment histories using natural-language methods and vector embeddings to forecast terminal major on the basis of students' sequences of enrolled courses early in their college careers. I find (I) a student's very first enrolled course predicts major thirty times better than random guessing and more than a third better than majority-class voting; (II) modeling strategies substantially influence forecasting accuracy; and (III) that course portfolios vary substantially within majors, raising novel questions what majors mean or signify in relation to undergraduate course histories. In the third paper I deal with the issues of course shopping and course staffing as an optimal stocking problem. I describe the phenomenon of course shopping at scale at a large private research university. At this case institution shopping has increased over the past ten years. There also is substantial variation in shopping behavior by gender and academic tenure. Aided by the natural language methods developed in describing academic course histories, I predict which students will retain their enrollment decisions. I find that machine learning algorithms are both fairer and more efficient in this instance than more traditional rationing mechanisms that are used at many institutions.
Description
Type of resource | text |
---|---|
Form | electronic resource; remote; computer; online resource |
Extent | 1 online resource. |
Place | California |
Place | [Stanford, California] |
Publisher | [Stanford University] |
Copyright date | 2022; ©2022 |
Publication date | 2022; 2022 |
Issuance | monographic |
Language | English |
Creators/Contributors
Author | Lang, David Nathan |
---|---|
Degree supervisor | Domingue, Ben |
Thesis advisor | Domingue, Ben |
Thesis advisor | Bettinger, Eric |
Thesis advisor | Haber, Nick |
Thesis advisor | Stevens, Mitchell L |
Degree committee member | Bettinger, Eric |
Degree committee member | Haber, Nick |
Degree committee member | Stevens, Mitchell L |
Associated with | Stanford University, Graduate School of Education |
Subjects
Genre | Theses |
---|---|
Genre | Text |
Bibliographic information
Statement of responsibility | David Nathan Lang. |
---|---|
Note | Submitted to the Graduate School of Education. |
Thesis | Thesis Ph.D. Stanford University 2022. |
Location | https://purl.stanford.edu/sp617cb2743 |
Access conditions
- Copyright
- © 2022 by David Nathan Lang
- License
- This work is licensed under a Creative Commons Attribution Non Commercial 3.0 Unported license (CC BY-NC).
Also listed in
Loading usage metrics...