[School of Engineering PhD Scholarships] Generative User Interfaces that Adapt to the Contextual Needs of Physical Activity Tracking Users

About the project

About the Project This PhD investigates how user interfaces for physical activity (PA) tracking can be generated automatically from a user's context, rather than designed once and applied to everyone. PA trackers offer a predetermined set of data views and actions, from setting goals to reviewing progress and reflecting on performance. What any individual needs from them, however, changes continually. Contemporary goal-setting theory identifies the factors behind this variation: the user's ability, the complexity of the task, the feedback they require, and their situational resources such as time, energy and competing demands. Personal informatics research adds a further dimension, since needs differ depending on whether someone is collecting, integrating, reflecting on or acting on their data. These factors fluctuate within a single person across days and weeks, and no fixed interface accommodates them. The resulting mismatches contribute to abandonment, misinterpretation of data and demotivation, and they are sharpest for non-normative users, whose abilities, routines and goals sit outside the assumptions built into mainstream products. Two developments make context-driven interface generation feasible. Context-aware interfaces can optimise layout and content online in response to a user's task and environment (Lindlbauer et al., 2019). Generative and malleable interfaces driven by Large Language Models can synthesise interfaces from evolving, task-driven data models (Cao et al., 2025). This project brings the two together in a domain where mature behavioural theory specifies what should adapt and why. You will work on three interlocking problems: Modelling. You will extend the task-driven data models underpinning generative interfaces so that they are conditioned on inferred context rather than a user prompt, and so that they represent the activity and the task the user is performing with the interface, not only the data shown. Inference and generation. You will establish how far contextual factors can be inferred from sensed activity and interaction data rather than asked about repeatedly, and how to constrain generation so that interfaces stay consistent and free of normative defaults such as universal step targets. Evaluation. Controlled studies in the Department's new HCI suite will isolate single adaptation mechanisms, measuring affect, perceived autonomy and goal commitment. A longitudinal deployment will then test whether context-driven generation improves engagement and sustained use relative to a static baseline, and where it undermines predictability and user agency. You will join an active group working at the intersection of HCI, PA tracking and behaviour change. The project suits candidates with interests in AI, HCI, personal informatics and behaviour change. We also value lived experience of physical activity tracking, and particularly welcome applicants whose own experience of tracking has been shaped by needs that mainstream tools serve poorly. This project is expected to start in September 2027. Before you apply: We strongly recommend that you contact the supervisors for this project before you apply. How to apply: To be considered for this project you must complete a formal application through our online application portal. If you already have an applicant account this link will directly open an application for PhD School of Engineering Scholarships . If you don’t already have an applicant account, please follow the instructions here. . When applying, please specify the full title and supervisor/s of the project, details of your previous study, and names and contact details of two referees. You must also upload a Supporting Statement describing the motivation to apply to the project, your CV and transcripts of awarded and in-progress university qualifications . Please note late or incomplete applications will not be considered. Equality, diversity and inclusion are fundamental to the success of The University of Manchester and central to all our activities. A diverse research community strengthens creativity, productivity and quality, while increasing the societal and economic impact of our work. We welcome applicants from all career paths, backgrounds and sections of the community, regardless of age, disability, ethnicity, gender, gender expression, sexual orientation or transgender status. We welcome applications from candidates returning to study after a career break or experience in other roles. Flexible study arrangements may be available, including part-time study at 50%, 60% or 80%, subject to the requirements of the project and funder. Eligibility : The standard academic entry requirement for this PhD is an upper second-class (2:1) honours degree in Computer Science, Engineering, Psychology, Cognitive Science, Health Sciences, or a related discipline (or international equivalent) OR any upper-second class (2:1) honours degree and a Master’s degree at merit in Computer Science, Engineering, Psychology, Cognitive Science, Health Sciences, or a related discipline (or international equivalent). Candidates from computing backgrounds should have an interest in behaviour change and human-centred research; candidates from behavioural or health backgrounds should have programming experience and some familiarity with applied machine learning. This project will remain open until filled. If your application is submitted by 1 st November 2026, you can expect a decision by 18 th December 2026. If your application is submitted by 15 th January 2027, you can expect a decision by 30 th March 2027. Self or externally funded students can also be considered for this project. FSESoE

Research areas