Please use this identifier to cite or link to this item: https://repository.isls.org/handle/1/8333
Full metadata record
DC FieldValueLanguage
dc.contributor.authorSharma, Priya
dc.contributor.authorLi, Qiyuan
dc.contributor.authorAkgun, Mahir
dc.date.accessioned2023-04-09T13:47:07Z-
dc.date.available2023-04-09T09:44:22Z
dc.date.available2023-04-09T13:47:07Z-
dc.date.issued2022
dc.identifier.citationSharma, P., Li, Q., & Akgun, M. (2022). Design of machine learning powered visualizations to support rapid assessment of online student discussions. In Weinberger, A. Chen, W., Hernández-Leo, D., & Chen, B. (Eds.), Proceedings of the 15th International Conference on Computer-Supported Collaborative Learning - CSCL 2022 (pp. 455-458). International Society of the Learning Sciences.en
dc.identifier.urihttps://doi.dx.org/10.22318/cscl2022.455
dc.identifier.urihttps://repository.isls.org//handle/1/8333-
dc.descriptionShort Paperen
dc.description.abstractThis paper reports on the design of machine learning powered analytic visualizations to support instructors in rapidly assessing student behavioral and cognitive engagement in online discussions. We used Chi’s (2009) Interactive-Constructive-Active-Passive framework to assess cognitive engagement and social network analysis to assess behavioral engagement. We used the Long-Short-Term-Memory (LSTM) model to automatically classify discourse data. The model was trained based on 4000 human-rater coded posts and despite imbalanced data, the model shows relatively high accuracy. Three use case scenarios of the visualizations show that network and discourse analyses together support the instructor in ascertaining students’ cognitive and behavioral engagement. Next steps for addressing model accuracy and improving visualizations are presented.en
dc.publisherInternational Society of the Learning Sciences
dc.relation.ispartofurn:ISBN:978-1-7373306-4-6
dc.relation.ispartofProceedings of the 15th International Conference on Computer-Supported Collaborative Learning - CSCL 2022, pp. 455-458
dc.subjectCSCLen
dc.titleDesign of Machine Learning Powered Visualizations to Support Rapid Assessment of Online Student Discussionsen
dc.typeconferencePaper
dc.identifier.doi10.22318/cscl2022.455
Appears in Collections:ISLS Annual Meeting 2022

Files in This Item:
File SizeFormat 
CSCL2022_455-458.pdf535.24 kBAdobe PDFView/Open


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