Improving Pedagogy by Analyzing Relevance and Dependency of Course Learning Outcomes

Many educators utilize an outcomes-based approach these days and maintain student performance records with regards to the individual learning outcomes. However, extracting meaningful information from these ever-growing datasets is a daunting task for even a skilled statistician. In this paper, we describe the implementation of a user-friendly software tool called DMOBE (Data Miner for Outcome Based Education). This tool was developed to extract key learning patterns from student performance records accumulated by educational programs following an outcome-based instructional paradigm. This tool allows instructors of such courses to mine their data and interpret the results in such a way as to provide insights into course optimization and more effective teaching methods. Specifically, this tool uses supervised feature selection to discover the relevant learning outcomes in a course based on their ability to predict student performance in a subsequent course and then uses dependency mining to determine whether mastery of any other outcomes in the course will influence mastery of a given outcome.

[1]  Sebastián Ventura,et al.  Data mining in course management systems: Moodle case study and tutorial , 2008, Comput. Educ..

[2]  Rajeev Motwani,et al.  Beyond Market Baskets: Generalizing Association Rules to Dependence Rules , 1998, Data Mining and Knowledge Discovery.

[3]  W. F. Punch,et al.  Predicting student performance: an application of data mining methods with an educational Web-based system , 2003, 33rd Annual Frontiers in Education, 2003. FIE 2003..

[4]  R. Crowley,et al.  Mining Student Learning Data to Develop High Level Pedagogic Strategy in a Medical ITS , 2006 .

[5]  Tomasz Imielinski,et al.  Mining association rules between sets of items in large databases , 1993, SIGMOD Conference.

[6]  César Hervás-Martínez,et al.  Data Mining Algorithms to Classify Students , 2008, EDM.

[7]  R. Agarwal.  Fast Algorithms for Mining Association Rules , 1994, VLDB 1994.

[8]  Robustness of Filter-Based Feature Ranking: A Case Study , 2011, FLAIRS Conference.

[9]  William F. Punch,et al.  Enhancing Online Learning Performance: An Application of Data Mining Methods , 2004, CATE.

[10]  Gwo-Dong Chen,et al.  Discovering Decision Knowledge from Web Log Portfolio for Managing Classroom Processes by Applying Decision Tree and Data Cube Technology , 2000 .

[11]  Zorica Bogdanović,et al.  An application of data mining in adaptive web based education system , 2008 .

[12]  William F. Punch,et al.  Using Genetic Algorithms for Data Mining Optimization in an Educational Web-Based System , 2003, GECCO.