Selected recent Publications
Scrutable AIED
This chapter describes scrutability in AIED. Scrutable systems are designed so that learners can answer key questions about the way those systems work. This is becoming increasingly important as AIED applications become more pervasive, and their impact more extensive. We show how scrutability fits in the landscape of many similar terms; it reflects a human-centred perspective and describes the effort a learner needs to invest to understand the way an advanced educational system works, even for selected aspects they care about. We conclude with an agenda for future research on scrutability in AIED.
In Handbook of Artificial Intellidence in Education,
2023
Grand challenges for pervasive technology to transform pervasive education.
This paper begins with a scenario characterising learning on a day in 2030. It overviews broader educational needs and the pervasive computing elements for realising them: mobile devices; embedded devices; pervasive infrastructures; and multi-disciplinary foundations. The Grand Challenges are: (1) Smart learning environments that feel safe, trusted, scrutable and controllable; (2) Harness long-term, rich data for self-knowledge and shared understanding; (3) Long-term personal digital learning companions; (4) Augment classroom teacher’s awareness and memory; (5) Smart classrooms that seamlessly fit into teaching and learning; (6) Meta-research to understand if and when technology really supports learning.
In IEEE Pervasive Computing,
2022
Foundations for Systematic Evaluation and Benchmarking of a Mobile Food Logger in a Large-scale Nutrition Study
Mobile food logging is important but tedious and difficult. We created the EaT (Eat and Track) app with a novel Search-Accelerator. Our evaluation, in a 12-participant lab study and a field study with 1,027-participants and careful analysis of causes of failures in the food search. Our core contributions are: 1) EaT’s novel support for detailed food logging; 2) our study design; 3) new performance benchmarks for mobile food logging.
In Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies,
2020
Embedding a VR Game Studio in a Sedentary Workplace: Use, Experience and Exercise Benefits.
Many people do not get recommended levels of physical activity. Virtual reality (VR) games might help them get there since VR games can be both fun and physically demanding. This paper reports a study of 11 particiapnts using a VR game studio in a sedentary workplace over 8-weeks. All participants gained benefits for physical activity and mood. Our key contributions are insights about the use and benefits of a sedentary workplace VR game studio.
In Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies,
2020
From data to personal user models for life‐long, life‐wide learners
As technology has become ubiquitous in learning contexts, there has been an explosion in the amount of learning data. This creates opportunities to draw on the decades of learner modelling research from Artificial Intelligence in Education and more recent research on Personal Informatics. We use these bodies of research to introduce a conceptual model for a Personal User Model for Life‐long, Life‐wide Learners (PUMLs). … Our core contribution is a way to think about the design and evaluation of learning data and applications so that they give learner control and agency beyond simple data access and algorithmic transparency. This was an invited paper for the 50th Anniversary of BJET
In British Journal of Educational Technology,
2019
How Does a Nation Walk?: Interpreting Large-Scale Step Count Activity with Weekly Streak Patterns
This work explored ways to analyse step data fomr 140,000 individuals, walking a combined 74 billion steps in 305 days of a city-wide public health campaign. We add to emerging understanding of ways to interpret this data, using both patterns of device use and step counts to identify 16 user segments and show the predictive user outcomes from their first few days of tracking. The figure above shows an example of a person from the group we describe as self-driven power trackers. The paper won a Distinguished Paper Award for IMWUT Volume 3 (2019).
In Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies,
2019