Please use this identifier to cite or link to this item:
|Title:||An Exploratory Study of Automated Clustering of Themes to Identify Conceptual Threads in Knowledge Building Discourse|
|Publisher:||International Society of the Learning Sciences (ISLS)|
|Citation:||Zhu, G., Ma, L., Toulis, A., & Resendes, M. (2019). An Exploratory Study of Automated Clustering of Themes to Identify Conceptual Threads in Knowledge Building Discourse. In Lund, K., Niccolai, G. P., Lavoué, E., Hmelo-Silver, C., Gweon, G., & Baker, M. (Eds.), A Wide Lens: Combining Embodied, Enactive, Extended, and Embedded Learning in Collaborative Settings, 13th International Conference on Computer Supported Collaborative Learning (CSCL) 2019, Volume 2 (pp. 943-944). Lyon, France: International Society of the Learning Sciences.|
|Abstract:||In this study, we adopted Jaccard index and tf-idf without stop words to automatically cluster the ideas students discussed in on an online knowledge building platform called Knowledge Forum. We visualized the clusters, provided keywords that most represent the context of each cluster and compared the generated themes with manual coding themes. The results suggest that most of the generated themes were consistent with human coding results.|
|Appears in Collections:||CSCL 2019|
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.