This paper applies theory and methodology from the learning design literature to large-scale learning environments through quantitative modeling of the structure and design of Massive Open Online Courses. For two institutions of higher education, we automate the task of encoding pedagogy and learning design principles for 177 courses (which accounted for for nearly 4 million enrollments). Course materials from these MOOCs are parsed and abstracted into sequences of components, such as videos and problems. Our key contributions are (i) describing the parsing and abstraction of courses for quantitative analyses, (ii) the automated categorization of similar course designs, and (iii) the identification of key structural components that show relationships between categories and learning design principles. We employ two methods to categorize similar course designs---one aimed at clustering courses using transition probabilities and another using trajectory mining. We then proceed with an exploratory analysis of relationships between our categorization and learning outcomes.
%0 Conference Paper
%1 Davis:2018:TLL:3231644.3231663
%A Davis, Dan
%A Seaton, Daniel
%A Hauff, Claudia
%A Houben, Geert-Jan
%B Proceedings of the Fifth Annual ACM Conference on Learning at Scale
%C New York, NY, USA
%D 2018
%I ACM
%K MOOCs analytics design learning
%P 4:1-4:10
%R 10.1145/3231644.3231663
%T Toward Large-scale Learning Design: Categorizing Course Designs in Service of Supporting Learning Outcomes
%U http://doi.acm.org/10.1145/3231644.3231663
%X This paper applies theory and methodology from the learning design literature to large-scale learning environments through quantitative modeling of the structure and design of Massive Open Online Courses. For two institutions of higher education, we automate the task of encoding pedagogy and learning design principles for 177 courses (which accounted for for nearly 4 million enrollments). Course materials from these MOOCs are parsed and abstracted into sequences of components, such as videos and problems. Our key contributions are (i) describing the parsing and abstraction of courses for quantitative analyses, (ii) the automated categorization of similar course designs, and (iii) the identification of key structural components that show relationships between categories and learning design principles. We employ two methods to categorize similar course designs---one aimed at clustering courses using transition probabilities and another using trajectory mining. We then proceed with an exploratory analysis of relationships between our categorization and learning outcomes.
%@ 978-1-4503-5886-6
@inproceedings{Davis:2018:TLL:3231644.3231663,
abstract = {This paper applies theory and methodology from the learning design literature to large-scale learning environments through quantitative modeling of the structure and design of Massive Open Online Courses. For two institutions of higher education, we automate the task of encoding pedagogy and learning design principles for 177 courses (which accounted for for nearly 4 million enrollments). Course materials from these MOOCs are parsed and abstracted into sequences of components, such as videos and problems. Our key contributions are (i) describing the parsing and abstraction of courses for quantitative analyses, (ii) the automated categorization of similar course designs, and (iii) the identification of key structural components that show relationships between categories and learning design principles. We employ two methods to categorize similar course designs---one aimed at clustering courses using transition probabilities and another using trajectory mining. We then proceed with an exploratory analysis of relationships between our categorization and learning outcomes.},
acmid = {3231663},
added-at = {2018-06-26T12:16:04.000+0200},
address = {New York, NY, USA},
articleno = {4},
author = {Davis, Dan and Seaton, Daniel and Hauff, Claudia and Houben, Geert-Jan},
biburl = {https://www.bibsonomy.org/bibtex/24f8cb3c5dd63382bcfb6f143007c5195/yish},
booktitle = {Proceedings of the Fifth Annual ACM Conference on Learning at Scale},
doi = {10.1145/3231644.3231663},
interhash = {ea659bba09e626fef277f7343a2ae373},
intrahash = {4f8cb3c5dd63382bcfb6f143007c5195},
isbn = {978-1-4503-5886-6},
keywords = {MOOCs analytics design learning},
location = {London, United Kingdom},
numpages = {10},
pages = {4:1-4:10},
publisher = {ACM},
series = {L@S '18},
timestamp = {2018-06-26T12:16:45.000+0200},
title = {Toward Large-scale Learning Design: Categorizing Course Designs in Service of Supporting Learning Outcomes},
url = {http://doi.acm.org/10.1145/3231644.3231663},
year = 2018
}