Using Process Mining and Learning Analytics for Modeling and Analyzing Learning Processes

When: Friday, August 29, 
2014
Where: PGH 563
Time: 11:00 AM

Speaker: Dr. Carlos Monroy, Rice Center for Digital Learning and Scholarship

Host: Prof. Ricardo Vilalta

Learning Analytics (LA) is an emerging discipline that focuses on the analysis of the data and contexts where learning takes place. Our work in LA seeks to model inquiry-based science learning and its application to enhance curriculum design and ultimately improve learning practices. This work relies on large datasets generated by a blended-learning, inquiry-based science curriculum. We have created a set of indices for quantifying curriculum usage along with a process mining methodology for examining inquiry-based pedagogical processes. These are the initial steps toward measuring fidelity of implementation (or process conformance), advancing personalization in education, and improving learners’ outcomes.

Ongoing technological advancements are pushing learning beyond the boundaries of the classroom, making it a life-long experience that takes place both in formal and informal settings. Thus, LA can be applied to training in data-rich and data-intensive environments. For example, personalized medicine in the health sciences, where physicians access personal medical records, genetic information, and imaging data to learn about a patient; or scientists querying genomics data and results from thousands of studies to understand biological processes and devise new drugs and treatments.

Given the heterogeneity, size, and growth of the data produced, we are exploring the use of new frameworks such as Hadoop and MapReduce. Although big data is a hot topic both in industry and academia, I argue that beyond the computing and infrastructure-related challenges derived from the size and complexity of the data, interpretation and sense making are two key areas of research, making this a multidisciplinary endeavor. I will conclude with examples of visualizations we have developed and thoughts about the importance of learning analytics for innovation in the 21st century, from K-12 to higher education and beyond.

Bio:

Dr. Carlos Monroy is a Data Scientist with the Rice Center for Digital Learning and Scholarship where he works in learning analytics, big data, and information visualization. His areas of interest are data mining, information retrieval and visualization, digital humanities and multidisciplinary collaboration. For more than fifteen years, Dr. Monroy’s work and research have enabled numerous interdisciplinary collaborations with domain experts in education, linguistics, art history and nautical archaeology. He received his Ph.D. from Texas A&M University in Computer Science in 2010.

Throughout his career, he has received numerous awards and recognitions such as: Young Researcher Award – Heidelberg Laureate Forum (Germany, 2014); Outstanding Publication Award – American Educational Research Association (USA, 2014); and National Outstanding Undergraduate Thesis (Guatemala, 1996). He is a member of the International Network of Guatemalan Scientists, the Association for Computing Machinery, the Association for Linguistic and Literary Computing and the IEEE Computer Society. He serves as reviewer for conferences and journals related to computer science, linguistic computing, computer-human interaction and technology.