Exploring the Triangulation of Dimensionality Reduction When Interpreting Multimodal Learning Data from Authentic Settings
- 1.8k Downloads
Multimodal Learning Analytics (MMLA) has sparked researcher interest in investigating learning in real-world settings by capturing learning traces from multiple sources of data. Though multimodal data offers a more holistic picture of learning, its inherent complexity makes it difficult to understand and interpret. This paper illustrates the use of dimensionality reduction (DR) to find a simple representation of multimodal learning data collected from co-located collaboration in authentic settings. We employed multiple DR methods and used triangulation to interpret their result which in turn provided a more simplistic representation. Additionally, we also show how unexpected events in authentic settings (e.g., missing data) can affect the analysis results.
KeywordsCo-located collaboration Multimodal Learning Analytics Dimensionality reduction method Computer-supported collaborative learning
This research has been partially funded by the European Union via the European Regional Development Fund, in the context of CEITER and Next-Lab (Horizon 2020 Research and Innovation Programme, grant no. 669074 and 731685).
- 1.Pardo, A., Delgado Kloos, C.: Stepping out of the box: towards analytics outside the learning management system. In: 1st International Conference on Learning Analytics and Knowledge (LAK 2011), pp. 163–167. ACM, New York (2011)Google Scholar
- 3.Chua, Y.H.V., Dauwels, J., Tan, S.C.: Technologies for automated analysis of co-located, real-life, physical learning spaces. In: Proceedings of the 9th International Conference on Learning Analytics and Knowledge (LAK 2019), pp. 11–20. ACM, New York (2019)Google Scholar