Abstract
In this study we conducted behavioral analyses to gain insights into patterns of user interaction in a video discussion platform, Vialogues. Vialogues provides an asynchronous online discussion environment around video. Using a hierarchical clustering analysis on users’ clickstream data, we identified four different behavior patterns: (1) video watchers with no discussion activity, (2) opinion seekers and active repliers with little to no video watching activity, (3) users who watched and discussed videos, and (4) users focused on viewing and/or creating metadata. Despite being the largest group, Cluster (3) had the least classifiable characteristics. Consequently we conducted additional analyses to examine finer-grained user segments. For each segment we created a transition network using weighted directed networks in order to understand the transition pattern between two consecutive click activities.
| Original language | English |
|---|---|
| State | Published - 2018 |
| Event | 11th International Conference on Educational Data Mining, EDM 2018 - Buffalo, United States Duration: 15 Jul 2018 → 18 Jul 2018 |
Conference
| Conference | 11th International Conference on Educational Data Mining, EDM 2018 |
|---|---|
| Country/Territory | United States |
| City | Buffalo |
| Period | 15/07/18 → 18/07/18 |
Bibliographical note
Publisher Copyright:© 2018 International Educational Data Mining Society. All rights reserved.
Keywords
- Hierarchical clustering
- Online discussion
- Transition network
- User behavior
- Video learning