Please use this identifier to cite or link to this item: https://repository.isls.org/handle/1/6628
Full metadata record
DC FieldValueLanguage
dc.contributor.authorLee, Seung
dc.contributor.authorGui, Xiaofan
dc.contributor.authorHamilton, Eric
dc.date.accessioned2020-07-08T23:53:49Z
dc.date.accessioned2020-07-09T04:31:00Z-
dc.date.available2020-07-08T23:53:49Z
dc.date.available2020-07-09T04:31:00Z-
dc.date.issued2020-06
dc.identifier.citationLee, S., Gui, X., & Hamilton, E. (2020). Application of AutoML in the Automated Coding of Educational Discourse Data. In Gresalfi, M. and Horn, I. S. (Eds.), The Interdisciplinarity of the Learning Sciences, 14th International Conference of the Learning Sciences (ICLS) 2020, Volume 5 (pp. 2597-2600). Nashville, Tennessee: International Society of the Learning Sciences.en_US
dc.identifier.urihttps://doi.dx.org/10.22318/icls2020.2597
dc.identifier.urihttps://repository.isls.org//handle/1/6628-
dc.description.abstractThis paper examines the potential for using AutoML techniques to develop automated classification models for coding educational discourse data. In particular, it provides a direct comparison between automated classifiers developed through rule-based and AutoML approaches. Through a presentation of an applied example, the paper offers insights on the challenges and strategies associated with utilizing AutoML in the automation of discourse coding. Results indicate sufficient levels of reliability and validity for classification models developed through both approaches. These findings suggest that AutoML approaches can perform at a level similar to rule-based approaches in the automated coding of discourse data.en_US
dc.language.isoenen_US
dc.publisherInternational Society of the Learning Sciences (ISLS)en_US
dc.subjectScaleen_US
dc.titleApplication of AutoML in the Automated Coding of Educational Discourse Dataen_US
dc.typeShort Paperen_US
Appears in Collections:ICLS 2020

Files in This Item:
File SizeFormat 
2597-2600.pdf214.1 kBAdobe PDFView/Open


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.