educational data mining

Virtual presentation @ Learning Analytics Workshop

/ scupelli

July 31, 2015 6:04 PM

Paul Inventado virtually presented “Promoting Online Learning System Design Quality: Utilizing Design Patterns Produced by Data-driven Approaches” at the Learning Analytics workshop in Prague, Czech Republic.

Abstract:

Many students benefit from online learning systems each year. However, it is not easy to ensure the design quality of these systems due to their complexity. In this paper, the data-driven design pattern production (3D2) methodology is presented as a solution. Specifically, it uses learning analytics and educational data mining to help uncover relationships between student learning outcomes and system designs. Designs that lead to better learning can be formalized into design patterns, which stakeholders can use to guide them in upgrading the online learning system’s components, and adding new content. The approach is further extended into an open, collaborative framework, which allows stakeholders to collaborate in the production of design patterns. A collaborative effort can speed up the pattern production process, improve the quality of the design patterns produced, share benefits among all members, and ultimately, elevate the standards of online learning system development.

Last updated: 6:04 pm

Paper presentation @ EuroPLoP 2015 writer’s workshop

/ scupelli

July 11, 2015 3:54 PM

Peter Scupelli and Paul Inventado presented “Data-Driven Design Pattern Production: A Case Study on the ASSISTments Online Learning System” in a writing workshop 20th European Conference on Pattern Languages of Programs (EuroPLoP) 2015 in Bavaria, Germany.

Abstract:

Online learning systems popularity increased rapidly in recent decades in multiple domains such as cognitive tutors, online courses, and massive open online courses (MOOCS). The design quality of online learning systems is difficult to maintain. Multiple stakeholders are involved (e.g., software developers, interaction designers, learning scientists, teachers), the system is complex, there are rapid changes in software, platforms (e.g., mobile, tablet, desktop) and learning subject content, and so forth. Many existing online learning systems collect a significant amount of data that describe learning outcomes and student behaviors, which are indirect measures of system quality. Data analysis on online learning systems data can uncover linkages between particular design choices made and student learning outcomes. In this paper, we describe the Data-Driven Design Patterns Production (3D2P) methodology to prospect, mine, write and evaluate design patterns for online learning systems. Pattern prospecting helps designers decide what type of possible meaningful outcomes and features to scan for in the data and helps to focus on specific data subsets to limit the search space for pattern mining. Design patterns identified with 3D2P methodology can guide the addition of new content and the modification of system designs to maintain the online learning system’s quality. We present a case study of the ASSISTments math online learning system to illustrate the 3D2P methodology and discuss its benefits and limitations.

Last updated: 3:54 pm

New publication in eLearning Papers #42

/ scupelli

June 15, 2015 7:56 PM

Paul Salvador Inventado and Peter Scupelli’s paper entitled “Towards an open, collaborative repository for online learning system design patterns” has been published in eLearning Papers #42.

Abstract:

Design patterns are high-quality solutions to known problems in a specific context that guide design decisions. Typically, design patterns are mined and evaluated through four methods: expert knowledge, artifact analysis, social observations, and workshops. For example, experts discuss: knowledge, interpretations of artifacts, social patterns, and clarity of patterns. In this paper, we introduce a fifth method, a data-driven design pattern production (3D2P) method to produce design patterns and conduct randomized controlled trials as a means to evaluate applied design patterns. We illustrate the 3D2P method in the context of online learning systems (OLSs) that are difficult to create, update and maintain. To overcome such challenges, we propose an open repository for OLS design patterns, evaluation data, and implementation examples. On the repository, researchers can collaborate in the six stages of the pattern lifecycle (i.e., prospecting, mining, writing, evaluation, application, applied evaluation). The repository provides five benefits: researchers from different backgrounds can (a) collaborate on design pattern production; (b) perform distributed tasks in parallel; (c) share results for mutual benefit; (d) test patterns across varied systems and domains to explore pattern generalizability and robustness; and (e) promote design patterns to elevate OLS quality.

Last updated: 7:56 pm