A Comparison of Classification Technique for Metacognitive Knowledge

Abstract:

Metcognitive learning has been developed to 1) enhance students to have awareness for conducting self study, 2) verify metacognitive knowledge and 3) provide proper lessons for each student. The test of metacognitive knowledge was implemented, and at least two out of three metacognitive knowledges; knowledge of self, knowledge of task, and knowledge of strategy, should be presented so that students’ metacognitive regulation can be proved. Therefore classification techniques were proposed to classify metacognitive knowledge of students via accuracy comparison of four classification techniques: Bayesian classifier, Decision Tree, Rule Based, and General Classification as 92.04%, 91.22%, 86.56%, and 92.87% respectively. Nonetheless, Bayesian Classifier is selected to be algorithm for metacognitive learning environment.

• Periodical: Advanced Materials Research (Volumes 403-408)
• Pages: 4538-4542
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.403-408.4538
• Online since: November 2011
• Authors: Phongthanat Sae Joo, Charan Sanrach, Sumalee Chaijaroen
• Keywords: Classification, Metacognition, Metacognitive Knowledge

References

[1] John H. Flavell, Speculations About the Nature and Development of Metacognition, Metacognition Motivation, and Understanding, Lawrence Erlbaum Associates Publishers : New Jersey, (1987).

[2] John H. Flavell, Metacognition and Cognitive Monitoring, American Psychologist, vol. 34, no. 10, pp.906-911, (1979).

DOI: 10.1037/0003-066x.34.10.906

[3] Trevor Wasilow, Implications of Metacognition on Instructional Technology for Today's Differentiated Learners, Educational Communications and Technology 802, University of Saskatchewan, 2009 pp.1-10.

[4] Feryal Cubukcu, Metacognition in the Classroom, World Conference on Educational Sciences 2009, Procedia Social and Behavioral Science 1 , 559-563, (2009).

DOI: 10.1016/j.sbspro.2009.01.101

[5] Ian H. Witten & Eibe Frank, Data Minig Practical Machine Learning Tools and Techniques, Morgan Kaufmann Publishers, San Francisco, USA, (2005).

DOI: 10.1186/1475-925x-5-51

[6] Christina Andrade, What is Metacognition?, Advanced Topics in Cognitive & Affective Bases of Behavior, Fielding Graduate University, 2006, pp.1-20.

[7] Pang-Ning Tan, Michael Steinbach, and Vipin Kumar, Introduction to Data Mining, Addison Wesley, 2005, pp.146-149.

[8] Jiawei Han and Micheline Kamber, Data Mining Concepts and Techniques, Morgan Kaufmann Publishers, San Francisco, USA, 2006, pp.5-6.

[9] S.K. Shevade, S.S. Keerthi, C. Bhattacharyya, and K.R.K. Murthy, Improvements to SMO Algorithm for SVM Regression, IEEE Transactions on Neural Networks, 11, 2000, pp.1188-1193.

DOI: 10.1109/72.870050

[10] Gregory Schraw and Rayne Sperling dennison, Assessing Metacognitive Awareness, Contemporary Education Psychology, 19, 1994, pp.460-475.

DOI: 10.1006/ceps.1994.1033