Learning analytics is the measurement, collection, and analysis of data about learners and their contexts for the purposes of understanding and optimizing the process of learning and the underlying environment. Due to the complex nature of the learning process, existing works mostly focus on the modeling and analysis of single learning behavior and thus bears limited capacity in achieving good performance and interpretability of predictive tasks. We propose a research framework for learning analytics based on multilayer behavior fusion which achieves significantly better performance in various tasks including at-risk student prediction. Results of extensive evaluation on thousands of students demonstrate the effectiveness of multilayer behavior fusion. We will report the insights about mining learning behaviors at different layers including physical, social and mental layers from the data collected from multiple sources. We will also describe the quantitative relationships between these behaviors and the students’ learning performance.
|Title of host publication
|Blended Learning. Education in a Smart Learning Environment - 13th International Conference, ICBL 2020, Proceedings
|Simon K.S. CHEUNG, Richard LI, Kongkiti PHUSAVAT, Naraphorn PAOPRASERT, Lam-For KWOK
|Number of pages
|Published - 2020
|13th International Conference on Blended Learning, ICBL 2020 - Bangkok, Thailand
Duration: 24 Aug 2020 → 27 Aug 2020
|Lecture Notes in Computer Science
|13th International Conference on Blended Learning, ICBL 2020
|24/08/20 → 27/08/20
Bibliographical noteThe work is supported by Human-computer fusion cloud computing architecture and software definition method (project code: 2018YFB1004801). It is also supported by Learning Analytics and Educational Data Mining: Making Sense of Big Data in Education (project code: 1.61.xx.9A5V) and Multi-stage Big Data Analytics for Complex Systems: Methodologies and Applications (RGC No.: C5026-18G).
- At-risk student prediction
- Automatic text scoring
- Learning analytics
- Multilayer behavior extraction