2. • Can we reframe Learning Analytics as ways of
seeing the richness and complexity of the learning
process?
• Learning Analytics are about learning (Gašević
2015)
• Data and models can provide a mirror for self-
reflection and metacognition (Koedinger 2009)
• What about the student’s role in data-rich learning
environments? (Kitto 2016)
• How can probabilistic machine learning techniques
& learning models (Millán 2010) be integrated in
existing learning analytics systems
3. • What opportunities have you
identified?
• Model students’ conceptual
understanding of their own learning
• Support Metacognition & Reflection
• Reduce the need for formal testing and
examinations
• Enable more Problem-based Learning
assessment
• Provide more Formative Feedback for
students
• What challenges exist?
• Student engagement
• Complexity of models for learners
• Data interoperability – bringing data from
disparate sources together
• Ethical challenges in terms of data
ownership and informed student action
• Identifying and gathering useful data for
and with students
Central to education’s purpose is “the coming into presence of unique individual beings”
Education “spaces might open up for uniqueness to come into the world”
– Gert Biesta – ‘Good Education in an Age of Measurement: Ethics, Politics, Democracy’
4. • Enhance a connected Learning Analytics system with more effective
probabilistic machine learning models to make learning more visible and
transparent to students
• Share the system with students in a module of a BSc in Computing degree
course and scaffold their use of the system to inform metacognitive and
reflective activities
• Conduct a mixed-methods study of their experience and the impact on
their learning
5. • Gašević, D., Dawson, S., & Siemens, G. (2015). Let’s not forget: Learning analytics are about learning.
TechTrends, 59(1), 64–71. https://doi.org/10.1007/s11528-014-0822-x
• Koedinger, K. R., Aleven, V., Roll, I., & Baker, R. (2009). In vivo experiments on whether supporting
metacognition in intelligent tutoring systems yields robust learning. Handbook of Metacognition in
Education, 897–964.
• Millán, E., Loboda, T., & Pérez-de-la-Cruz, J. L. (2010). Bayesian networks for student model engineering.
Computers & Education, 55(4), 1663–1683.
• Kitto, K., Lupton, M., Davis, K., & Waters, Z. (2016). Incorporating student-facing learning analytics into
pedagogical practice.
• Ting, C.-Y., Cheah, W.-N., & Ho, C. C. (2013). Student Engagement Modeling Using Bayesian Networks (pp.
2939–2944). IEEE. https://doi.org/10.1109/SMC.2013.501
• Piech (2015) - Deep Knowledge Tracing - looked at how students learn to program, modelled their learning
path, identified where they got stuck, how they got unstuck (Piech 2015)