Empowering People to Harness and Control their Multimodal Data in Scrutable User models

摘要

As technology pervades our lives in an increasingly rich ecosystem of digital devices, those devices can capture huge amounts of long-term personal data. A core theme of my research has been to create systems and interfaces that enable people to harness and control that personal data and its use. To do this, I have designed systems from their very foundations so that they support scrutability [2]. This means that the user should be able to scrutinise the user model that a system builds from their personal data. The term, scrutability highlights a user-centred view of Explainable AI (XAI) [4]. It has a particularly important role in supporting people in lifelong, life-wide learning, especially from long term data [3]. This is because it can support key metacognitive processes of self-monitoring, reflection and planning. In learning contexts, the user model is often called a learner model and the interfaces onto it are called Open Learner Models (OLMs). Increasingly, learning contexts have been able to make use of rich forms of multi-modal data [1]. This talk will share insights from a series of case studies. The first case studies explored how to harness data from wearables, such as smart watches, for personal informatics interfaces. These are designed to enable people learn about themselves over the long term. One case study created interfaces that enable people to take account of wearing adherence, with its implications for interpreting such data [6]. A second shares analysis of a large dataset (over 140,000 people) from a public health initiative [5] and another involves use of Virtual Reality games for exercise [7]. The second set of case studies are from formal education settings. These use diverse forms of data to support individual learners, teams of learners who are learning how to collaborate and teachers who want to understand how their students are progressing. I will share key insights that have emerged for a research agenda: OLMs for life-wide learning; the nature of the different interfaces needed for fast, versus slow and considered thinking; communicating uncertainty; scaffolding people to really learn about themselves from their multimodal data; and how these link to urgent challenges of education in an age of AI, fake news and truth decay.