I'm a PhD student and data scientist at the University of Minnesota's Learning Informatics Lab. My research focuses on iteratively 1) applying computational and qualitative methods to study student learning at various levels of analysis and 2) developing tools and interventions to augment learning in ways that promote student flourishing.

My interests lie broadly at the intersection of human-computer interaction and learning sciences, with previous projects involving modeling student smartphone use during school-hours, exploring student responses to failure in a puzzle-game using log and video-data, and investigating social interactions in online courses. My work and collaborations have been published in ISLS, LAK, ICQE, and other venues. For more context, please visit my GitHub or download my CV.

I also regularly teach at the University of Minnesota, with past courses including CI5371: Learning Analytics, CI4311: Technology and Ethics in Society, and CI3342: Social Media and Connected Learning.

Research Interests: Human-Computer Interaction, Human-Centered Data Science, Problem Solving, Learning @ Scale

Selected Projects

  • Learning from Impasses

    Studying the interplay between failure and learning in the context of Baba Is You.

  • Smartphone Use in Classrooms

    Modeling student smartphone use during school-hours.

  • Problem Solving

    As a research assistant for the Playful Problem Solving project, I have worked on sequence mining patterns in problem-solving behavior, written programs for analyzing eye-tracker data, conducted interaction analysis of video data, and other projects.

  • Overnight Adolescent Smartphone Use

    Observing overnight adolescent smartphone use using high-intensity objective observations.

  • Text-Network Analysis

    Conduct research on the promise of natural-language processing techniques in supporting student knowledge construction.

  • Sentiment Analysis of Tweets During COVID

    Topic-modeling using Tweets extracted before and after shift to online learning during COVID pandemic.

  • iLearn

    iLearn is an interface for supporting students in decomposing complex goals, monitoring progress on self-defined outcomes, and recommending relevant content to help students complete complex learning tasks.

  • Network Dynamics of Student's Online Annotations

    Modeling student interactions in an online course based on student attributes, course-design, and network factors.