Modeling Student Affect in English Learning Achievement Using Association Rules

Abstract

Educational studies have been conducted to search for methods of optimum learning. Student-teacher interaction is important in classroom settings for an environment conducive to learning. Most instructional practices thus far have explicitly included many more cognitive factors than affective ones. The affective factors are often neglected because they are considered private matters, far too long-term to be assessed, and poorly understood phenomena. As part of learning, emotion has been shown empirically to affect the quality of thinking and cognitive information processing. Some educators have suggested certain teaching and learning activities are more likely to be successful when students are motivated by affective factors. An initial step to better understand student learning achievement based on affective domains is to build profiles to infer student learning achievement. In this study, association rules are used to infer the relationship between student affective factors and performance in a learning setting. This study shows methods of revealing how student affective profiles are linked to their achievement in learning a second language. Factors influencing student learning are selected, classified, and used to form student affective profiles and to generate rules associating the factors with learning outcomes. The results show that both integrative motivation and intrinsic motivation show a positive and significant correlation with achievement. The resulting profiles are applicable as a basis to develop empirically-based methods of education that explicitly include individual student affective aptitude.



Author Information
Fitra A. Bachtiar, Ritsumeikan University, Japan
Eric W. Cooper, Ritsumeikan University, Japan
Gunadi H. Sulistyo, State University of Malang, Indonesia
Katsuari Kamei, Ritsumeikan University, Japan

Paper Information
Conference: ACSET2014
Stream: Education and Technology: Teaching

This paper is part of the ACSET2014 Conference Proceedings (View)
Full Paper
View / Download the full paper in a new tab/window

Posted by amp21