About Me

I’m Yuanru Tan (“Yoo-en-roo”, close to Mandarin pinyin Yuǎnrú), a Ph.D. candidate in the Learning Sciences program at the University of Wisconsin–Madison. I’m advised by Professor David Williamson Shaffer in the Epistemic Analytics Lab, part of the Center for Research on Complex Thinking.

I’m a methodologist-in-training, working at the intersection of learning theories, data, and design. I develop analytical methods and statistical tools to model complex learning processes in ways that are mathematically rigorous and visually expressive.

I think of my work as an iterative cycle: identifying mathematical structures underlying learning phenomena, empirically testing those structures, and ultimately developing tools that researchers can use to tell faithful and meaningful stories about how people learn. Along the way, I learn from talented colleagues, while contributing my own perspective to advance the field.

Current Projects

Ordered Network Analysis (ONA)

I led the development of ONA, a network technique to model, visualize, and statistically compare temporal structures in discourse data. Built on the widely used Epistemic Network Analysis (ENA), ONA has been applied in education, healthcare, and other domains.

• Read the method paper
• Use the R tutorial
• Try it in the web tool

iPlan

iPlan is a simulation game where users design urban land-use models and explore the effects of planning decisions on environmental and social outcomes. Its open-ended structure poses unique challenges for assessment. We developed a novel approach to generate simulated learning analytics models directly from system log data, offering “thick descriptions” for otherwise “thin” clickstream data. We're also exploring how these models can help us better understand real learner behaviors.

• Read the analytics method paper
• Explore the iPlan simulation

Network Trajectories

I’m currently developing a method to model, visualize, and compare high-dimensional time series data to better understand how learning unfolds over time. This work explores dimensionality reduction, smoothing techniques, and trajectory visualization to explain meaningful patterns in complex educational datasets. What excites me the most is adapting and expanding time series analysis—traditionally used in finance or sensor data—for the unique challenges of learning analytics.

• Have data suited for this project? Email me!
• Trajectory tools (coming soon)

Before the Ph.D.

Before starting my Ph.D., I worked as a Learning Experience Designer for Accessibility at the Center for Academic Innovation at the University of Michigan–Ann Arbor, under the mentorship of Professor Rebecca Quintana. It was my first full-time role after graduate school, and a place where I grew as both a designer and a researcher.

In this role, I worked with instructors who were passionate about making online learning more inclusive and accessible. I also contributed to research projects focused on understanding learning experience design. One of my favorite projects with Rebecca explored how different forms of representation—both beaded artifacts and digital visualizations—can shape the way designers think. (P.S. We ended up decorating our desks with those beaded artifacts, and it remains one of my favorite memories.)

I hold an M.A. in Education from the University of Michigan–Ann Arbor advised by Professor Chris Quintana, and a B.S. in Information Management Systems from Tianjin University of Technology in China.

These educational and professional experiences—and the people I’ve been lucky to work with—continue to shape how I approach problems: creatively, collaboratively, and with care.