Towards an integration of text and graph clustering methods as a lens for studying social interaction in MOOCs

In this paper, we describe a novel methodology, grounded in techniques from the field of machine learning, for modeling emerging social structure as it develops in threaded discussion forums, with an eye towards application in the threaded discussions of massive open online courses (MOOCs). This mo...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Diyi Yang, Miaomiao Wen, Abhimanu Kumar, Eric P. Xing, Carolyn Penstein Rose
Formato:	article
Lenguaje:	EN
Publicado:	Athabasca University Press 2014
Materias:	online learning MOOCs Learning Analytics Special aspects of education LC8-6691
Acceso en línea:	https://doaj.org/article/e68822bd4cb04142bece9b502ef31b54
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:e68822bd4cb04142bece9b502ef31b54
record_format	dspace
spelling	oai:doaj.org-article:e68822bd4cb04142bece9b502ef31b542021-12-02T18:03:17ZTowards an integration of text and graph clustering methods as a lens for studying social interaction in MOOCs10.19173/irrodl.v15i5.18531492-3831https://doaj.org/article/e68822bd4cb04142bece9b502ef31b542014-10-01T00:00:00Zhttp://www.irrodl.org/index.php/irrodl/article/view/1853https://doaj.org/toc/1492-3831 In this paper, we describe a novel methodology, grounded in techniques from the field of machine learning, for modeling emerging social structure as it develops in threaded discussion forums, with an eye towards application in the threaded discussions of massive open online courses (MOOCs). This modeling approach integrates two simpler, well established prior techniques, namely one related to social network structure and another related to thematic structure of text. As an illustrative application of the integrated technique’s use and utility, we use it as a lens for exploring student dropout behavior in three different MOOCs. In particular, we use the model to identify twenty emerging subcommunities within the threaded discussions of each of the three MOOCs. We then use a survival model to measure the impact of participation in identified subcommunities on attrition along the way for students who have participated in the course discussion forums of the three courses. In each of three MOOCs we find evidence that participation in two to four subcommunities out of the twenty is associated with significantly higher or lower dropout rates than average. A qualitative post-hoc analysis illustrates how the learned models can be used as a lens for understanding the values and focus of discussions within the subcommunities, and in the illustrative example to think about the association between those and detected higher or lower dropout rates than average in the three courses. Our qualitative analysis demonstrates that the patterns that emerge make sense: It associates evidence of stronger expressed motivation to actively participate in the course as well as evidence of stronger cognitive engagement with the material in subcommunities associated with lower attrition, and the opposite in subcommunities associated with higher attrition. We conclude with a discussion of ways the modeling approach might be applied, along with caveats from limitations, and directions for future work. Diyi YangMiaomiao WenAbhimanu KumarEric P. XingCarolyn Penstein RoseAthabasca University Pressarticleonline learningMOOCsLearning AnalyticsSpecial aspects of educationLC8-6691ENInternational Review of Research in Open and Distributed Learning, Vol 15, Iss 5 (2014)
institution	DOAJ
collection	DOAJ
language	EN
topic	online learning MOOCs Learning Analytics Special aspects of education LC8-6691
spellingShingle	online learning MOOCs Learning Analytics Special aspects of education LC8-6691 Diyi Yang Miaomiao Wen Abhimanu Kumar Eric P. Xing Carolyn Penstein Rose Towards an integration of text and graph clustering methods as a lens for studying social interaction in MOOCs
description	In this paper, we describe a novel methodology, grounded in techniques from the field of machine learning, for modeling emerging social structure as it develops in threaded discussion forums, with an eye towards application in the threaded discussions of massive open online courses (MOOCs). This modeling approach integrates two simpler, well established prior techniques, namely one related to social network structure and another related to thematic structure of text. As an illustrative application of the integrated technique’s use and utility, we use it as a lens for exploring student dropout behavior in three different MOOCs. In particular, we use the model to identify twenty emerging subcommunities within the threaded discussions of each of the three MOOCs. We then use a survival model to measure the impact of participation in identified subcommunities on attrition along the way for students who have participated in the course discussion forums of the three courses. In each of three MOOCs we find evidence that participation in two to four subcommunities out of the twenty is associated with significantly higher or lower dropout rates than average. A qualitative post-hoc analysis illustrates how the learned models can be used as a lens for understanding the values and focus of discussions within the subcommunities, and in the illustrative example to think about the association between those and detected higher or lower dropout rates than average in the three courses. Our qualitative analysis demonstrates that the patterns that emerge make sense: It associates evidence of stronger expressed motivation to actively participate in the course as well as evidence of stronger cognitive engagement with the material in subcommunities associated with lower attrition, and the opposite in subcommunities associated with higher attrition. We conclude with a discussion of ways the modeling approach might be applied, along with caveats from limitations, and directions for future work.
format	article
author	Diyi Yang Miaomiao Wen Abhimanu Kumar Eric P. Xing Carolyn Penstein Rose
author_facet	Diyi Yang Miaomiao Wen Abhimanu Kumar Eric P. Xing Carolyn Penstein Rose
author_sort	Diyi Yang
title	Towards an integration of text and graph clustering methods as a lens for studying social interaction in MOOCs
title_short	Towards an integration of text and graph clustering methods as a lens for studying social interaction in MOOCs
title_full	Towards an integration of text and graph clustering methods as a lens for studying social interaction in MOOCs
title_fullStr	Towards an integration of text and graph clustering methods as a lens for studying social interaction in MOOCs
title_full_unstemmed	Towards an integration of text and graph clustering methods as a lens for studying social interaction in MOOCs
title_sort	towards an integration of text and graph clustering methods as a lens for studying social interaction in moocs
publisher	Athabasca University Press
publishDate	2014
url	https://doaj.org/article/e68822bd4cb04142bece9b502ef31b54
work_keys_str_mv	AT diyiyang towardsanintegrationoftextandgraphclusteringmethodsasalensforstudyingsocialinteractioninmoocs AT miaomiaowen towardsanintegrationoftextandgraphclusteringmethodsasalensforstudyingsocialinteractioninmoocs AT abhimanukumar towardsanintegrationoftextandgraphclusteringmethodsasalensforstudyingsocialinteractioninmoocs AT ericpxing towardsanintegrationoftextandgraphclusteringmethodsasalensforstudyingsocialinteractioninmoocs AT carolynpensteinrose towardsanintegrationoftextandgraphclusteringmethodsasalensforstudyingsocialinteractioninmoocs
_version_	1718378781300752384

Towards an integration of text and graph clustering methods as a lens for studying social interaction in MOOCs

Ejemplares similares