Characterizing Students’ Learning Behaviors Using Unsupervised Learning Methods
Abstract
In this paper, we present an unsupervised approach for characterizing students’ learning behaviors in an open-ended learning environment. We describe our method for generating metrics that describe a learner’s behaviors and performance using Coherence Analysis. Then we combine feature selection with a clustering method to group students by their learning behaviors. We characterize the primary behaviors of each group and link these behaviors to the students’ ability to build correct models as well as their learning gains derived from their pre- and post-test scores. Finally, we discuss how this behavior characterization may contribute to a framework for adaptive scaffolding of learning behaviors.
Keywords
Open-ended learning environments Coherence analysis Learner behaviors Unsupervised learning Feature selectionNotes
Acknowledgements
This work has been supported by NSF Cyberlearning Grant #1441542.
References
- 1.Land, S.: Cognitive requirements for learning with open-ended learning environments. Educ. Tech. Res. Dev. 48(3), 61–78 (2000)CrossRefGoogle Scholar
- 2.Winslow, L.E.: Programming pedagogy—a psychological overview. ACM SIGCSE Bull. 28(3), 17–22 (1996)CrossRefGoogle Scholar
- 3.Sengupta, P., et al.: Integrating computational thinking with K-12 science education using agent-based computation: a theoretical framework. Educ. Inf. Technol. 18(2), 351–380 (2013)CrossRefGoogle Scholar
- 4.Basu, S., Biswas, G., Kinnebrew, J.S.: Learner modeling for adaptive scaffolding in a computational thinking-based science learning environment. User Model. User-Adapt. Interact. (2017). doi: 10.1007/s11257-017-9187-0
- 5.Kinnebrew, J., Segedy, J.R., Biswas, G.: Integrating model-driven and data-driven techniques for analyzing learning behaviors in open-ended learning environments. IEEE Trans. Learn. Technol. (2017). doi: 10.1109/TLT.2015.2513387
- 6.Segedy, J.R., Kinnebrew, J.S., Biswas, G.: Using coherence analysis to characterize self-regulated learning behaviours in open-ended learning environments. J. Learn. Anal. 2(1), 13–48 (2015)CrossRefGoogle Scholar
- 7.Wilensky, U.: NetLogo. Center for Connected Learning and Computer-Based Modeling. Northwestern University, Evanston, IL. https://ccl.northwestern.edu/netlogo/
- 8.Witten, D.M., Tibshirani, R.: A framework for feature selection in clustering. J. Am. Stat. Assoc. 105(490), 713–726 (2010)CrossRefMATHMathSciNetGoogle Scholar
- 9.Charrad, M., et al.: NbClust: an R package for determining the relevant number of clusters in a data set. J. Stat. Softw. 61(6), 1–36 (2014)CrossRefGoogle Scholar
- 10.Berland, M., et al.: Using learning analytics to understand the learning pathways of novice programmers. J. Learn. Sci. 22(4), 564–599 (2013)CrossRefGoogle Scholar
- 11.Basu, S., Sengupta, P., Biswas, G.: A scaffolding framework to support learning of emergent phenomena using multi-agent based simulation environments. Res. Sci. Educ. 45(2), 293–324 (2015)CrossRefGoogle Scholar
- 12.Basu, S., Biswas, G.: Providing adaptive scaffolds and measuring their effectiveness in open-ended learning environments. In: 12th International Conference of the Learning Sciences Singapore, pp. 554–561 (2016)Google Scholar