Learning analytics: process and theory

Course Details

Course code: EDUA11339

Course leader: Professor Dragan Gasevic

Course delivery: Sep 2017, Sep 2018

Summary

This course provides a framework for understanding and critically discussing the emerging field of learning analytics. Students will learn about the distinction between learning analytics, educational data mining, and big data, and the relationship of learning analytics and existing fields. Perspectives on what learning analytics should be will be connected to philosophy and theory on the nature of design and inquiry. We will consider what it means for a learning analytics analysis or model to be valid, and the key challenges to the effective and appropriate use of learning analytics.

Learning Outcomes

On completion of the course you will be able to:

  • describe and critically analyse learning analytics process and theory;
  • review, integrate and critically assess emerging trends in learning analytics literature;
  • develop a proposal for a piece of research or application using learning analytics in an educational setting, based in a critical understanding of the literature
  • develop a detailed plan for the learning analytics application or research proposed, and critically assess its main elements.

Structure

The course is structured around a number of activities. 

  • Each week will have a set of readings introducing the topics of learning analytics covered by the course. The topics will be adjusted each to acknowledge the rapid development of the field of learning analytics and its theory and processes.
  • Each of these readings will be accompanied by a series of tutor-provided questions that will help scaffold participants’ posts to asynchronous online discussion posts. The purpose of these discussions is to create a space for the participants to engage with social knowledge construction activities, negotiate the meaning of the topics studied with their peers, and get to appreciate and critical discuss different viewpoints to learning analytics.
  • Each summative assessment will be accompanied with formative feedback to inform and guide later assessments in the course. The three main assessments guide the participants through a process of the development of their ideas – from early literature review to project proposal to project execution, and reporting and presentation of the findings.
  • To increase the flexibility necessary to a globally-distributed cohort, online activities are mainly asynchronous. To increase access to the tutor, the course will feature weekly synchronous discussion session with the instructor and scheduled weekly online chats.

Assessment

Assignments are designed to be cumulative while remaining distinct.

Assignment 1: Critical literature review paper (35% of your final mark). The goal of this assignment is to write a literature review paper (1,500) on a learning analytics topic. This assignment will help define a research problem for the project that the students will be pursuing in assignments 2 and 3.

Assignment 2: Collaborative formulation of application or research proposal (20% of your final mark). The goal of this assignment is to help students formulate their research proposals for the project in assignment 3 and discuss their research proposal with the peers. Students will provide constructive feedback to their peers about their proposed research, the quality of which will be assessed and contribute to the final mark. A research proposal of 500 words will be written by each student, which will be shared in the course space for peer feedback. All students will be expected both to provide feedback, and to respond constructively to feedback from others. The participation in the discussions about peers’ proposals will constitute 20% of the assessment weighting for assignment 2.

Assignment 3: Learning analytics planning paper (40% of your final mark). This assignment is the development of a detailed plan for the application or research proposed in learning analytics. The students will also conduct a pilot project based on their proposals and report on the findings. This assignment builds on the literature review from Assignment 1, and the research problem formulated and developed in Assignment 2. Students will write a research paper of 2,500 words which will constitute 65% of the assignment weighting; they will also give an online presentation of their work which will constitute the 25% of the of the assignment weighting. Students will provide constructive feedback to their peers about their proposed research, the quality of which will be assessed and contribute 10% of the assessment weighting for assignment 3.

Teaching Methods

Online methods will include moderated small and whole group discussion in synchronous and asynchronous modes, guided reading, reflection, self-directed exploration, discussion forums, and focused activities supported by peer and tutor formative feedback.

Reading

Indicative readings are:

Baker, R.S.J.d., Yacef, K. (2009) The State of Educational Data Mining in 2009: A Review and Future Visions. Journal of Educational Data Mining, 1 (1), 3-17.

Colvin, C., Rogers, T., Wade, A., Dawson, S., Gašević, D., Buckingham Shum, S., Nelson, K., Alexander, S., Lockyer, L., Kennedy, G., Corrin, L., Fisher, J. (2015). Student retention and learning analytics: A snapshot of Australian practices and a framework for advancement. Canberra, ACT, Australia: Australian Government’s Office for Learning and Teaching.

Ferguson, R. (2012) Learning analytics: drivers, developments and challenges. International Journal of Technology Enhanced Learning (IJTEL), 4 (5/6), 304-317.

Gašević, D., Dawson, S., & Siemens, G. (2015). Let’s not forget: Learning analytics are about learning. TechTrends59(1), 64-71.

Gašević, D., Dawson, S., Rogers, T., Gašević, D. (2016). Learning analytics should not promote one size fits all: The effects of course-specific technology use in predicting academic success. The Internet and Higher Education, 28, 68-84.

Siemens, G. (2013) Learning Analytics: The Emergence of a Discipline. American Behavioral Scientist, 57 (10), 1380-1400.

Requirements

You will need access to an internet-enabled computer and browser. It may be helpful to use Skype for synchronous communication with your supervisor.