Yossi Ben David
ABSTRACT
Despite the prevalence of e-learning systems in schools, most of today's systems do not personalize educational data to the individual needs of each student. This paper proposes a new algorithm for sequencing questions to students that is empirically shown to lead to better performance and engagement in real schools when compared to a baseline approach. It is based on using knowledge tracing to model students' skill acquisition over time, and to select questions that advance the student's learning within the range of the student's capabilities, as determined by the model. The algorithm is based on a Bayesian Knowledge Tracing (BKT) model that incorporates partial credit scores, reasoning about multiple attempts to solve problems, and integrating item difficulty. This model is shown to outperform other BKT models that do not reason about (or reason about some but not all) of these features. The model was incorporated into a sequencing algorithm and deployed in two classes in different schools where it was compared to a baseline sequencing algorithm that was designed by pedagogical experts. In both classes, students using the BKT sequencing approach solved more difficult questions and attributed higher performance than did students who used the expert-based approach. Students were also more engaged using the BKT approach, as determined by their interaction time and number of log-ins to the system, as well as their reported opinion. We expect our approach to inform the design of better methods for sequencing and personalizing educational content to students that will meet their individual learning needs.
- F. B. Baker and S.-H. Kim. Item response theory: Parameter estimation techniques. CRC Press, 2004.Google Scholar
Cross Ref
- M. Bieliková, M. Šimko, M. Barla, J. Tvarožek, M. Labaj, R. Móro, I. Srba, and J. Ševcech. Alef: from application to platform for adaptive collaborative learning. In Recommender Systems for Technology Enhanced Learning, pages 195--225. Springer, 2014.Google ScholarCross Ref
- J. H. Block, P. W. Airasian, B. S. Bloom, and J. B. Carroll. Mastery learning: Theory and practice. Holt, Rinehart and Winston New York, 1971.Google Scholar
- P. Brusilovsky, L. N. Cassel, L. M. Delcambre, E. A. Fox, R. Furuta, D. D. Garcia, F. M. Shipman, and M. Yudelson. Social navigation for educational digital libraries. Procedia Computer Science, 1(2):2889--2897, 2010.Google ScholarCross Ref
- B. Clement, P.-Y. Oudeyer, D. Roy, and M. Lopes. Online optimization of teaching sequences with multi-armed bandits. In International Conference on Educational Data Mining (EDM), 2014.Google Scholar
- A. T. Corbett and J. R. Anderson. Knowledge tracing: Modeling the acquisition of procedural knowledge. User Modelling and User-Adapted Interaction, 4(4):253--278, 1995.Google ScholarCross Ref
- A. T. Corbett and A. Bhatnagar. Student Modeling in the ACT Programming Tutor: Adjusting a Procedural Learning Model With Declarative Knowledge. In User Modeling, pages 243--254. Springer Vienna, Vienna, 1997.Google ScholarCross Ref
- R. S. d Baker, A. T. Corbett, and V. Aleven. More accurate student modeling through contextual estimation of slip and guess probabilities in bayesian knowledge tracing. In Intelligent Tutoring Systems, pages 406--415, 2008. Google ScholarDigital Library
- A. P. Dempster, N. M. Laird, and D. B. Rubin. Maximum likelihood from incomplete data via the em algorithm. Journal of the royal statistical society. Series B (methodological), pages 1--38, 1977.Google Scholar
- M. C. Desmarais and R. S. J. de Baker. A review of recent advances in learner and skill modeling in intelligent learning environments. User Modeling and User-Adapted Interaction, 22(1-2):9--38, 2012. Google ScholarDigital Library
- W. J. Hawkins, N. T. Heffernan, and R. S. J. de Baker. Learning Bayesian Knowledge Tracing Parameters with a Knowledge Heuristic and Empirical Probabilities. Intelligent Tutoring Systems, 8474(Chapter 18):150--155, 2014.Google Scholar
- T.-C. Hsieh, M.-C. Lee, C.-Y. Su, et al. Designing and implementing a personalized remedial learning system for enhancing the programming learning. Educational Technology & Society, 16(4):32--46, 2013.Google Scholar
- Y.-M. Huang, T.-C. Huang, K.-T. Wang, and W.-Y. Hwang. A markov-based recommendation model for exploring the transfer of learning on the web. Educational Technology & Society, 12(2):144, 2009.Google Scholar
- K. Ostrow, C. Donnelly, S. Adjei, and N. Heffernan. Improving student modeling through partial credit and problem difficulty. In Proceedings of the 2nd ACM Conf on L@ S, pages 11--20, 2015. Google ScholarDigital Library
- Z. Pardos and N. Heffernan. Modeling individualization in a Bayesian networks implementation of knowledge tracing. In User Modeling, Adaptation, and Personalization, volume 6075, pages 255--266. 2010. Google ScholarDigital Library
- Z. A. Pardos, Y. Bergner, D. T. Seaton, and D. E. Pritchard. Adapting Bayesian Knowledge Tracing to a Massive Open Online Course in edX. EDM, pages 137--144, 2013.Google Scholar
- Z. A. Pardos and N. T. Heffernan. KT-IDEM: Introducing Item Difficulty to the Knowledge Tracing Model. In UMAP, 2011. Google ScholarDigital Library
- R. Pelánek. Metrics for evaluation of student models. Journal of Educational Data Mining, 2015.Google Scholar
- L.-p. Shen and R.-m. Shen. Learning content recommendation service based-on simple sequencing specification. In Advances in Web-Based Learning-ICWL 2004, pages 363--370. Springer, 2004.Google ScholarCross Ref
- Y. Wang and N. Heffernan. Extending knowledge tracing to allow partial credit: Using continuous versus binary nodes. In Artificial Intelligence in Education, pages 181--188. Springer, 2013.Google ScholarCross Ref
- J. V. Wertsch. Vygotsky and the social formation of mind. Harvard University Press, 1988.Google ScholarCross Ref
- Sequencing educational content in classrooms using Bayesian knowledge tracing
Recommendations
Flipped University Classrooms: Using Technology to Enable Sound Pedagogy
The three case studies in this paper show how flipped classroom approaches can facilitate the renewal of university teaching. The case studies form part of a scholarship of teaching and learning that provides opportunities for educators to learn from ...
Toward the Evaluation of Educational Videos using Bayesian Knowledge Tracing and Big Data
L@S '15: Proceedings of the Second (2015) ACM Conference on Learning @ ScaleAlong with the advent of MOOCs and other online learning platforms such as Khan Academy, the role of online education has continued to grow in relation to that of traditional on-campus instruction. Rather than tackle the problem of evaluating large ...
Genetic Algorithm for Bayesian Knowledge Tracing: A Practical Application
Advances in Swarm IntelligenceAbstractOnline intelligent tutoring systems have developed rapidly in recent years. Analyzing educational data to help students personalize learning has become a research hotspot. Knowledge Tracing (KT) aims to assess students’ changing cognitive states ...
Comments