top of page

Our Work

Improving STEM Education Through Learning Analytics


Learning analytics, a discipline within educational data science, uses digital trace data, such as log files within a learning management system, to gain insights about how students learn. Informed by cognitive theories of learning and self-regulation, our lab develops metrics of engagement to understand learning and achievement. With these gained insights, we work with STEM faculty to implement best practices for teaching and promoting student learning.


Theoretical Frameworks

  • Self-Regulated Learning
  • Retrieval-based Learning

  • The Spacing Effect




Using clickstream data mining techniques to understand and support first-generation college students in an online chemistry course


Utilizing learning analytics to map students' self-reported study strategies to click behaviors in STEM courses

Understanding Reasoning in Educational and Everyday Settings

Our lab uses experimental methods to understand how college students reason and critically evaluate everyday sources of evidence. We specifically address how alluring information, such as anecdotal stories and scientific jargon, and interfere with critical thinking. Another strand of our work considers college students' ability to evaluate the credibility of social media posts. We are currently using eye-tracing methods to further uncover how college students read and perceive every sources of evidence on social media. This work is currently funded through UC Irvine's Postsecondary Education Research & Implementation Institute

Theoretical Frameworks

  • Dual-Process Reasoning
  • Information Literacy

  • Epistemological Beliefs


Examining the influence of anecdotal stories and the interplay of individual differences on reasoning


Do college students notice errors in evidence when critically evaluating research findings?

Education and Training


Our lab is committed broadening participation in learning analytics and educational data science. We have developed free training materials for learning the R and Python programming languages and regularly organize workshops for the research community at UC Irvine and the larger community of learning analytics researchers. 

Fernando Rodriguez co-directs CP-LEADS (Career Pathways for Research in Learning and Education, Analytics and Data Science), an undergraduate fellowship program that trains the next generation of researchers in the field of learning analytics and educational data science.

Introduction to R for Educational Data Science
Processing and Visualizing Clickstream Data Using R
Career Pathways for Research in Learning and Education, Analytics and Data Science
bottom of page