ABSTRACT
A cognitive model is a descriptive account or computational representation of human thinking about a given concept, skill, or domain. A cognitive model of learning, includes both a way of organizing knowledge within a subject area and an account of how humans develop accurate and complete knowledge of that subject area. Learning designers engage in a variety of practices to unpack knowledge from subject matter experts and novices to develop cognitive models of learning and use those models to guide the design of instruction or instructional technologies. Traditional approaches to eliciting and organizing knowledge, such as conducting a cognitive task analysis (CTA) [14] with experts and novices, are labor-intensive and require specific expertise that many learning designers do not have. However, learning data generated from learners’ interaction with courses, can provide insight into how humans think and develop knowledge. As a continued effort, we extend the framework presented in our earlier work [17] to discover and refine cognitive models of learning with learning data. The framework includes 1. a Variational Autoencoder (VAE) and a Gaussian Mixture Model (GMM) that models and clusters cognitive learning patterns; 2. a multidimensional measure that quantifies validity and reliability of the discovered cognitive models of learning; 3. a topic-based solution that interprets the cognitive models from a linguistic perspective; and 4. a simulation-based analysis for both accuracy measures and course refinement insights. We demonstrate the end-to-end solution with two applications and four case studies that are deployed in an openly navigated learning system in a workforce learning environment. We also report the usefulness of the discovered cognitive models of learning with subject matter expert evaluation.
- Shreyansh Bhatt, Jinjin Zhao, Candace Thille, Dawn Zimmaro, and Neelesh Gattani. 2020. A novel approach for knowledge state repre sentation and prediction. In Proceedings of the Seventh ACM Conference on Learning@ Scale. 353–356.Google ScholarDigital Library
- Hao Cen, Kenneth Koedinger, and Brian Junker. 2006. Learning factors analysis–a general method for cognitive model evaluation and im- provement. In International Conference on Intelligent Tutoring Systems. Springer, 164–175.Google ScholarDigital Library
- Richard Edward Clark and Jan Elen. 2006. Handling complexity in learning environments: Theory and research. Elsevier.Google Scholar
- Michel C Desmarais. 2012. Mapping question items to skills with non- negative matrix factorization. ACM SIGKDD Explorations Newsletter 13, 2 (2012), 30–36.Google ScholarDigital Library
- Carl Doersch. 2016. Tutorial on variational autoencoders. arXiv preprint arXiv:1606.05908 (2016).Google Scholar
- Kenneth R Koedinger, Albert T Corbett, and Charles Perfetti. 2012. The Knowledge-Learning-Instruction framework: Bridging the science- practice chasm to enhance robust student learning. Cognitive science36, 5 (2012), 757–798.Google Scholar
- Mark A Kramer. 1991. Nonlinear principal component analysis using auto associative neural networks. AIChE journal 37, 2 (1991), 233–243.Google ScholarCross Ref
- Daniel D Lee and H Sebastian Seung. 2001. Algorithms for non- negative matrix factorization. In Advances in neural information pro- cessing systems. 556–562.Google Scholar
- Kart-Leong Lim, Xudong Jiang, and Chenyu Yi. 2020. Deep Clustering With Variational Autoencoder. IEEE Signal Processing Letters 27 (2020), 231–235.Google ScholarCross Ref
- Xihui Lin and Paul C Boutros. 2020. Optimization and expansion of non-negative matrix factorization. BMC bioinformatics 21, 1 (2020), 1–10.Google Scholar
- Noboru Matsuda, Tadanobu Furukawa, Norman Bier, and Christos Faloutsos. 2015. Machine Beats Experts: Automatic Discovery of Skill Models for Data-Driven Online Course Refinement. International Educational Data Mining Society (2015).Google Scholar
- Jonathan K Pritchard, Matthew Stephens, and Peter Donnelly. 2000. Inference of population structure using multilocus genotype data. Genetics 155, 2 (2000), 945–959.Google ScholarCross Ref
- Peter J Rousseeuw. 1987. Silhouettes: a graphical aid to the interpretation and validation of cluster analysis. Journal of computational and applied mathematics 20 (1987), 53–65.Google ScholarDigital Library
- Jan Maarten Schraagen, Susan F Chipman, and Valerie L Shalin.2000. Cognitive task analysis. Psychology Press.Google ScholarCross Ref
- Gideon Schwarzetal. 1978. Estimating the dimension of a model. The annals of statistics 6, 2 (1978), 461–464.Google Scholar
- Lijun Zhang, Zhengguang Chen, Miao Zheng, and Xiaofei He. 2011. Robust non-negative matrix factorization. Frontiers of Electrical and Electronic Engineering in China 6, 2 (2011), 192–200.Google Scholar
- Zhao, Jinjin, "A Novel Framework for Discovering Cognitive Models of Learning." Proceedings of the Eighth ACM Conference on LearningXXX@ Scale. 2021.Google Scholar
Index Terms
- Data Mining for Discovering Cognitive Models of Learning
Recommendations
A Novel Framework for Discovering Cognitive Models of Learning
L@S '21: Proceedings of the Eighth ACM Conference on Learning @ ScaleA cognitive model is a descriptive account or computational representation of human thinking about a given concept, skill, or domain. A cognitive model of learning, includes both a way of organizing knowledge within a subject area and an account of how ...
Automated Support for Building and Extending Expert Models
Building a knowledge-based system is like developing a scientific theory. Although a knowledge base does not constitute a theory of some natural phenomenon, it does represent a theory of how a class of professionals approaches an application task. As ...
Cooperation between expert knowledge and data mining discovered knowledge: Lessons learned
Expert systems are built from knowledge traditionally elicited from the human expert. It is precisely knowledge elicitation from the expert that is the bottleneck in expert system construction. On the other hand, a data mining system, which ...
Comments