Using the Unizin Common Data Model to standardize course data, a team at Michigan built a scalable, open source tool for students to visualize their own learning.
Using the Unizin Common Data Model to standardize course data, a team at Michigan built a scalable, open source tool for students to visualize their own learning.
“The UDP and public cloud present interesting opportunities for us. They offer foundational infrastructure, technical innovation, and data security at consortial scale.”
Sean DeMonner, Executive Director of Teaching and Learning, ITS, University of Michigan at Ann Arbor
As a nationally-ranked public university, the University of Michigan (U-M) is dedicated to its research and teaching missions. In 2014 Michigan was one of several founding members of Unizin, a non-profit consortium dedicated to improving student success by focusing on data integration, learning analytics, and digital content. Unizin’s Data Platform (UDP) enables its member institutions to easily share data and tools through the interoperable Unizin Common Data Model (UCDM). Built on Google Cloud, the UDP meets the highest institutional privacy and data security standards while aggregating institutional data for better insights into student behaviors. By drawing on a collective data pool from the nearly 800,000 students in Unizin’s member organizations, the UDP hosts the largest, richest, and broadest collection of depersonalized learner data in higher education. Aaron Neal, CEO of Unizin, says of Unizin’s members, “Their success is our success. We want to help them get away from the challenges of data-wrangling.”
“The UDP and public cloud present interesting opportunities for us,” says Sean DeMonner, Executive Director of Teaching and Learning at U-M’s Information and Technology Services (ITS). “They offer foundational infrastructure, technical innovation, and data security at consortial scale.” Working with Google and Unizin, DeMonner gathered the team that developed My Learning Analytics (MyLA), a data analytics tool that visualizes course data and activities so students can monitor their own learning behaviors. With MyLA, for example, students can see how their online course activities—like completing a certain assignment or watching a lecture capture video—compare to the aggregated behavior of the other students in the class. The assignment-planning page lets them work through “what if” scenarios to see what assignments have the biggest impact on their grade, and help them decide how best to spend their limited time. By visualizing resource utilization, grade distribution, and assignment planning, MyLA helps students develop what is called self-regulated learning: they become conscious of their behaviors and the outcomes that follow. Students can then use that knowledge to improve their habits to achieve better results in a virtuous cycle.
John Johnston, the ITS Program Manager at U-M who serves as technical liaison with Unizin, points out that supporting the development of metacognitive skills—students monitoring, regulating, and reflecting on their own learning—is especially important for first-generation college students and those from under-resourced school districts, who may have had less exposure to those strategies in high school. “MyLA helps level the playing field in that regard,” Johnston argues. “It guides students to effectively budget their study time on the most impactful learning activities.” To date, MyLA has been used by over 2,300 U-M students over three semesters in 32 courses across different disciplines.
“MyLA helps level the playing field.... It guides students to effectively budget their study time on the most impactful learning activities.”
John Johnston, ITS Program Manager, University of Michigan at Ann Arbor
For teachers, advisers, and researchers, “MyLA’s descriptive data offers a powerful new way to understand how different learning behaviors affect different students,” says DeMonner. “Our large-scale vision is to aggregate and depersonalize these data, and we’re just starting to reap the research benefits across Unizin’s members.” He emphasizes that teachers can turn off visualizations they don’t want their students to see, like the grade distribution charts: “We’re all interested in student success, but we have different students, and student success means different things to different people. We’re not taking away control or being prescriptive, but helping students form good habits. We call it ‘data-informed’ not ‘data-driven’ decision-making.” The team embedded MyLA into the normal course workflows of their learning management system and studied how students used it. Johnston reports that there is a correlation between students using MyLA and improved performance in class. “Surveys also show users consistently report feeling empowered,” he says.
Johnston explains that each Unizin institution has its own private instance of the UDP, but that having all of the data commonly modeled enables the consortium to conduct multi-institutional research, build portable learning tools, and collaborate more seamlessly. MyLA is one example of the value of this approach. The tool was developed at U-M, but was able to be deployed for seven other Unizin institutions because they were able to leverage that common data backend.
The team is moving forward with their next steps: to encourage more research into MyLA’s data and to roll out new data visualizations. For DeMonner, though, MyLA is not only a technological tool: “We want to respect people’s privacy and establish an ethical framework for digital resources. As a flagship public institution, U-M has a special social responsibility. We’re training society’s future leaders, who will be making difficult decisions about complicated problems. We need people who can use data and understand its complexity, and bring their own human values and ethical principles to bear when making difficult decisions.”
For content more relevant to your region, we suggest: