Student Success by DesignA practitioner’s guide to theory, data, and AI in student success

5.2 · Technology, Data, and AI Applications

Learning analytics

Most learning analytics draw on LMS activity: logins, page views, submissions, discussion posts, and time-on-page.

Short shows the summary, takeaway, and questions.

Learning analytics map most directly onto Astin’s quantity of involvement and NSSE-style engagement. They capture the quantitative side of involvement well and the qualitative side poorly.

Systematic reviews find promising but uneven evidence that learning analytics interventions improve study success; effects depend on how the insight is acted on (Ifenthaler & Yau, 2020).

Typical implementations

  • Instructor dashboards showing inactive or falling-behind students.
  • Student-facing progress indicators and nudges.
  • Course-level reports linking activity to grades for course redesign.

Limitations and unintended consequences

  • Clicks are a proxy for time, not for quality of effort or learning.
  • Students in offline, lab, or studio-based courses look disengaged.
  • Visible monitoring can feel like surveillance and change behavior without changing learning.
  • Labels such as “at risk” can lower instructor expectations.

Implications for practice

  • Pair activity data with brief student check-ins before acting.
  • Show students their own data and explain what it means.

Theories behind this section

In the Campus Enterprise Model

Where this work sits in campus systems, capabilities, and data.