Learning Analytics

What it is and why it matters

Learning Analytics is the analysis of student activity data in order to make predictions about likely learning outcomes and prescribe appropriate interventions where needed to improve those outcomes. Italics have been added to emphasize the three phases of the learning analytics process which are necessary to reach this goal of improving student learning outcomes.

Since each case is unique and action is determined based on correlational inferences, further data should be collected to evaluate the success of the intervention(s). Therefore, the Learning Analytics process is cyclical as it continues throughout each iteration of teaching a course. A foundation of Learning Analytics is Continuous Quality Improvement (CQI). CQI is a quality control technique based on the belief that there is always room for improvement.


Learning Analytics is also a part of the student-centered approach to teaching which has been advocated for, and slowly shifted towards, throughout the past three decades. The epitome of the student-centered philosophy is in the teaching adage — serve as a guide on the side not a sage on the stage. It emphasizes self-regulated learners in that the responsibility for meaningful learning gains is on the student, given ample direction by the teacher. Thus, learning analytics is another mechanism for guiding students towards success. Teachers intervene whenever they are presented with data predicting the learning objectives are not being met in the course. This could be accomplished by contacting a student directly about their performance and methods for improvement, or offering additional instructional materials on a topic. Additionally, students could be made aware of the predictions directly for self-initiated corrective action. Examples of this in practice are below.


The University of Maryland University College has an annotated bibliography of many higher education-specific publications on learning analytics. A few noteworthy examples include:

  • Check My Activity – University of Maryland: A learning management system dashboard that shows students their activity in the course compared to the average of their peers’ activity. At this institution, 40% or less activity than the class average is correlated with a D or F so students are encouraged to engage in their courses regularly.
  • Sherpa – South Orange County Community College District: Sherpa software provides personalized higher education recommendations to students similar to recommendations seen on Amazon on Netflix. These recommendations (such as tutoring service information) appear on portal news feeds and course To Do lists. Additionally, the “nudges” are delivered via e-mail, SMS, and text-to-voice phone calls depending on students’ opt-in settings.

What separates these Learning Analytics examples from typical instructor interventions (think revisitation of topic based on poor class performance on an exam question) is that “big data” is often used to guide the statistical models and inspire intervention ideas. UFIT is actively working towards creating a process for data mining in online courses to facilitate individual instructor use of Learning Analytics on a regular basis.

To start introducing Learning Analytics into your courses, we have put together an overview explaining how to collect and analyze quantitative and qualitative data that could be collected by an individual instructor, and how to take action.  Ideally, Learning Analytics data would be incorporated into a course for adaptive learning purposes (helping students currently in a course improve their learning) but they can also be used to guide change in future offerings of a course.

Training Opportunities

Further Reading

Canvas Instructor Guides:

Web and Scholarly Articles

Arnold, K. E. & Pistilli, M. D. (2012). Course signals at Purdue: Using learning analytics to increase student success. In Proceedings of the 2nd International Conference on Learning Analytics and Knowledge. Vancouver, BC, Canada (pp. 267-270)

CITT Blog: What a Test Can Tell You? Brief overview of how to use quiz statistics from within UF’s e-Learning.

UF Academic Technology Handbook on Testing and Grading: In-depth guide on writing, administering, and scoring an effective test.

Getting Feedback from Students, Center for Teaching & Learning at Boston University.

Learning analytics in higher education: An annotated bibliography, University of Maryland University College, Center for Innovation in Learning.

Malterud, L, (2001). Qualitative Research: Standards, Challenges, and Guidelines, Qualitative Research Series, The Lancet, Vol. 358, 483-488.

Qualitative Measures, Web Center for Social Research Methods.

Wise, A. F. (2014). Designing pedagogical interventions to support student use of learning analytics. Published in LAK’14 Proceedings of the Fourth International Conference on Learning Analytics and Knowledge. 203-211.

Shea, P. (Ed.). 2016. Online Learning, 20(2), Special Issue: Learning analytics. Online Learning Consortium.