ABSTRACT
The ability to customize instruction to individuals is a great potential for adaptive educational software. Unfortunately, beyond mastery learning and learner control, there has not been much work with adapting instruction to individuals. This paper provides an approach to determine what type of learner does best with a different intervention. We focused on constructing a decision tree that discriminated difference between tutoring interventions, and thus to make customization for each student. We evaluated our model on simulated and on real data. In the simulated data set, it outperformed other methods and the constructed models captured a pre-defined customization structure. With the real data, the customized learning approach achieved stronger learning gains than simply picking the best overall teaching option. Surprisingly, it was difficult to outperform a decision tree that simply used how quickly students tended to learn a skill. That is, more features and more complex models did not result in a more effective system.
- Benjamin S Bloom, The 2 sigma problem: The search for methods of group instruction as effective as one-to-one tutoring. Educational researcher, 1984. 13(6): p. 4--16. Google ScholarCross Ref
- Jack Mostow and Joseph Beck, When the rubber meets the road: Lessons from the in-school adventures of an automated Reading Tutor that listens. Scale-Up in Education, 2006. 2: p. 183--200.Google Scholar
- Hyun Jin Cha, Yong Se Kim, Seon Hee Park, Tae Bok Yoon, Young Mo Jung, and Jee-Hyong Lee. Learning styles diagnosis based on user interface behaviors for the customization of learning interfaces in an intelligent tutoring system. in International Conference on Intelligent Tutoring Systems. 2006. Springer. Google ScholarDigital Library
- Harold Pashler, Mark McDaniel, Doug Rohrer, and Robert Bjork, Learning styles concepts and evidence. Psychological science in the public interest, 2008. 9(3): p. 105--119. Google ScholarCross Ref
- Anthony Botelho, Hao Wan, and Neil Heffernan. The prediction of student first response using prerequisite skills. in Proceedings of the Second (2015) ACM Conference on Learning@ Scale. 2015. ACM. Google ScholarDigital Library
- Hao Wan and Joseph Barbosa Beck, Considering the Influence of Prerequisite Performance on Wheel Spinning. International Educational Data Mining Society, 2015.Google Scholar
- Jong Woo Kim, Byung Hun Lee, Michael J Shaw, Hsin-Lu Chang, and Matthew Nelson, Application of decision-tree induction techniques to personalized advertisements on internet storefronts. International Journal of Electronic Commerce, 200 5(3): p. 45--62.Google Scholar
- Gerhard Weber, Hans-Christian Kuhl, and Stephan Weibelzahl. Developing adaptive internet based courses with the authoring system NetCoach. in Workshop on Adaptive Hypermedia. 2001. Springer.Google Scholar
- Joseph Jay Williams, Na Li, Juho Kim, Jacob Whitehill, Samuel Maldonado, Mykola Pechenizkiy, Larry Chu, and Neil Heffernan, The MOOClet framework: Improving online education through experimentation and personalization of modules. Available at SSRN 2523265, 2014.Google Scholar
- Hendrik Blockeel and Luc De Raedt, Top-down induction of first-order logical decision trees. Artificial intelligence, 1998. 101(1): p. 285--297. Google ScholarDigital Library
- Leo Breiman, Jerome Friedman, Charles J Stone, and Richard A Olshen, Classification and regression trees. 1984: CRC press.Google Scholar
- J Ross Quinlan, C4. 5: programs for machine learning. 2014: Elsevier.Google Scholar
Index Terms
- One Decision Tree is Enough to Make Customization
Recommendations
Incorporating customization and personalization into game-based learning
In recent years, customization and personalization were widely applied to accommodate the needs of different cognitive style groups. Such two approaches have different advantages and disadvantages but there is a lack of studies to compare these two ...
A Decision Tree Approach to Conducting Dynamic Assessment in a Context-Aware Ubiquitous Learning Environment
WMUTE '08: Proceedings of the Fifth IEEE International Conference on Wireless, Mobile, and Ubiquitous Technology in EducationThe advance of communication and sensor technologies have lead to a new research issue in education, that is, the development of an authentic learning environment with personalized supports from the learning system. In the meantime, it also becomes a ...
QoS customization in distributed object systems
Special issue: MiddlewareApplications built on networked collections of computers are increasingly using distributed object platforms such as CORBA, Java Remote Method Invocation (RMI), and DCOM to standardize object interactions. With this increased use comes the increased ...
Comments