Analyzing Attributes of Successful Learners by Using Machine Learning in an Undergraduate Computer Course

Over the past twenty years, the self-report scales have been used widely to measure learners' cognitive perceptions and behaviors in the contexts of learning. As the rapid development of analytical techniques, there is a need to incorporate appropriate computer algorithms to better analyze and comprehend learners' characteristics and their learning. This study therefore uses questionnaires data but applies machine learning (ML) techniques to discover which significant attributes that a successful learner often demonstrates in a computer course. Five ML algorithms include decision trees, naïve Bayes, support vector machines, multilayer perceptron and logistic regression are conducted to compare the performance of their accuracies, precisions and sensitivities. The results suggest that naïve Bayes is the most appropriate one for predicting students' final performance. The accuracy and sensitivity measure of this classifier achieve 77.53% and 88.68%, respectively. The classification model is presented in this paper and an attempt for improving classification accuracy is suggested.

[1]  D. Schunk Self-Regulated Learning: The Educational Legacy of Paul R. Pintrich , 2005 .

[2]  S. Cassidy,et al.  Developing the Computer User Self-Efficacy (Cuse) Scale: Investigating the Relationship between Computer Self-Efficacy, Gender and Experience with Computers , 2002 .

[3]  Salvador Sánchez-Alonso,et al.  The use of e-learning course management systems to support learning strategies and to improve self-regulated learning , 2007 .

[4]  อนิรุธ สืบสิงห์,et al.  Data Mining Practical Machine Learning Tools and Techniques , 2014 .

[5]  James V. Rauff Data Mining: A Tutorial-Based Primer , 2005 .

[6]  David McIlroy,et al.  Computer phobia and computer self-efficacy: their association with undergraduates' use of university computer facilities , 2007, Comput. Hum. Behav..

[7]  Deborah Compeau,et al.  Computer Self-Efficacy: Development of a Measure and Initial Test , 1995, MIS Q..

[8]  Sotiris B. Kotsiantis Use of machine learning techniques for educational proposes: a decision support system for forecasting students’ grades , 2011, Artificial Intelligence Review.

[9]  Peter Shea,et al.  Learning presence: Towards a theory of self-efficacy, self-regulation, and the development of a communities of inquiry in online and blended learning environments , 2010, Comput. Educ..

[10]  P. Pintrich,et al.  Motivation in Education: Theory, Research, and Applications , 1995 .

[11]  M. Dembo,et al.  The Relationship Between Self-Regulation and Online Learning in a Blended Learning Context , 2004 .

[12]  P. Pintrich,et al.  Reliability and Predictive Validity of the Motivated Strategies for Learning Questionnaire (Mslq) , 1993 .

[13]  Maria Puzziferro Online Technologies Self-Efficacy and Self-Regulated Learning as Predictors of Final Grade and Satisfaction in College-Level Online Courses , 2008 .

[14]  P. Pintrich The role of goal orientation in self-regulated learning. , 2000 .

[15]  A. Bandura Self-Efficacy: The Exercise of Control , 1997, Journal of Cognitive Psychotherapy.

[16]  Sotiris B. Kotsiantis,et al.  Machine learning: a review of classification and combining techniques , 2006, Artificial Intelligence Review.

[17]  Anastasios A. Economides,et al.  Learning Analytics and Educational Data Mining in Practice: A Systematic Literature Review of Empirical Evidence , 2014, J. Educ. Technol. Soc..

[18]  Pru Marriott,et al.  The use of on-line summative assessment in an undergraduate financial accounting course , 2008 .

[19]  D. Nicol,et al.  Formative assessment and self‐regulated learning: a model and seven principles of good feedback practice , 2006 .

[20]  William Stafford Noble,et al.  Support vector machine , 2013 .

[21]  Ryan S. Baker,et al.  The State of Educational Data Mining in 2009: A Review and Future Visions. , 2009, EDM 2009.