Making Math Tutors More Engaging and Effective through Interaction Design Patterns and Educational Data Mining

Ryan Baker, Neil Heffernan and Peter Scupelli

The growth in the American economy is linked to industries based upon science, technology, engineering, and mathematics (STEM). Unfortunately, American students lack the degree of proficiency in mathematics needed to pursue careers in these areas. Increasingly, online software for mathematics problem-solving — whether used in class or as homework — is used by hundreds of thousands of students each year. However, the quality of student learning experiences can differ considerably between different content, even when the content is developed largely by the same team. In recent years, researchers have attempted to formalize lessons learned from past successful design projects into design principles. These efforts have been instructive, but there are several challenges to instantiating design principles in new contexts and many cases where principles may conflict. In this research, we use Design Patterns, an alternate approach which has been successful in other domains which can be used at scale as templates for realizing effective design (i.e., architecture, programming, security). We are using a data mining approach to extract the design patterns in addition to traditional design pattern development approaches. The design patterns are used to fix math problems associated with poor learning outcomes. The revised math problems are then tested with online experiments to ensure that the design pattern lead to improved learning outcomes.


Inventado, P. S. and Scupelli, P. (2015). Towards an open, collaborative repository for online learning system design patterns. eLearning Papers, 42(Design Patterns for Open Online Teaching):14-27. 

Inventado, P.S. and Scupelli, P. (2015). Data-Driven Design Pattern Production: A Case Study on the ASSISTments Online Learning System. In Proceedings of the 20th European Conference on Pattern Languages of Programs (EuroPLoP 2015). 

Inventado, P. S. and Scupelli, P. (2015). Promoting Online Learning System Design Quality: Utilizing Design Patterns Produced by Data-driven Approaches. Learning Analytics Summer Camp, Prague, Czech Republic. 

Inventado, P.S. and Scupelli, P. (in press). A Data-driven Methodology for Producing Online Learning System Design Patterns. In Proceedings of the 22nd Conference on Pattern Languages of Programs (PLoP 2015).

Scupelli, P. and Inventado, P.S., (2014) Data-driven Design Pattern Development (3DPD) Workshop in Pattern Languages of Programs Conference 2014 September 14-17, 2014 (PLOP 2014) Allerton Park in Monticello, IL.  

Read more about the project