Alternative Latent and Observable Factors for Knowledge Tracing; A time series approach
Event details
| Date | 13.07.2021 |
| Hour | 10:00 › 12:00 |
| Speaker | Jade Cock |
| Category | Conferences - Seminars |
EDIC candidacy exam
exam president: Prof. Martin Jaggi
thesis advisor: Prof. Tanja Käser
co-examiner: Prof. Pierre Dillenbourg
Abstract
Interactive simulations can foster inquiry learning,
but the complexity of those environments require adaptive
guidance for the students to efficiently use those systems. The
goal of our thesis is to build such an adaptive platform. To guide
us in our future endeavours, we examine three papers. The first
one is a review providing guidance about methodological choices
in the context of pipelines involving learner models. The second
one is a working example of the application of a cluster-rule
mining-classification framework. The last one is a novel approach
to classify asynchronous and irregular time series. We end with
our thesis proposal.
Background papers
exam president: Prof. Martin Jaggi
thesis advisor: Prof. Tanja Käser
co-examiner: Prof. Pierre Dillenbourg
Abstract
Interactive simulations can foster inquiry learning,
but the complexity of those environments require adaptive
guidance for the students to efficiently use those systems. The
goal of our thesis is to build such an adaptive platform. To guide
us in our future endeavours, we examine three papers. The first
one is a review providing guidance about methodological choices
in the context of pipelines involving learner models. The second
one is a working example of the application of a cluster-rule
mining-classification framework. The last one is a novel approach
to classify asynchronous and irregular time series. We end with
our thesis proposal.
Background papers
- Pelánek, R. (2017). Bayesian knowledge tracing, logistic models, and beyond: an overview of learner modeling techniques. User Modeling and User-Adapted Interaction, 27(3), 313-350.
- Horn, M., Moor, M., Bock, C., Rieck, B., & Borgwardt, K. (2020, November). Set functions for time series. In International Conference on Machine Learning (pp. 4353-4363). PMLR.
- Fratamico, L., Conati, C., Kardan, S., & Roll, I. (2017). Applying a framework for student modeling in exploratory learning environments: Comparing data representation granularity to handle environment complexity. International Journal of Artificial Intelligence in Education, 27(2), 320-352.
Practical information
- General public
- Free