PhD Studentship in Simulating Person-Specific Cognitive Processes from Expressive Behaviours for Mental Health Assessment University of Exeter in United Kingdom

[Funded PhD studentship covering Home or International tuition fees plus an annual tax-free stipend of at least £21,805 (UKRI minimum) for 3.5 years full-time, or pro rata for part-time study.]

The University of Exeter’s Department of Computer Science is offering a funded PhD studentship focused on simulating person-specific cognitive processes from expressive behaviours for mental health assessment. The project is based at the Streatham Campus within the Faculty of Environment, Science and Economy and is supported by the University Startup Package, the University, and the Department of Computer Science.

This PhD sits at the intersection of computer science, artificial intelligence, affective computing, multimodal learning, and computational mental health. The research aims to develop personalised AI models that infer latent cognitive-response mechanisms from expressive behaviours such as facial expressions, speech, gaze, head movement, affective dynamics, and interaction patterns. Rather than using these signals only as direct classifiers of mental health labels, the project will build an individualised “cognitive simulator” that models how a person responds in emotional, social, or conversational contexts, and then use that simulator for downstream inference of mental health states, symptom severity, and change over time.

The project is motivated by the limitations of traditional assessment methods for conditions such as depression, anxiety, and bipolar disorder, which can be subjective, time-consuming, and hard to scale. By learning personalised neural architectures or model weights, the research seeks to capture individual expressive mechanisms more robustly than surface-level behavioural features alone. Planned methods include deep learning, graph neural networks, transformers, hypernetworks, temporal modelling, multimodal signal processing, and responsible AI. The work also emphasizes fairness, privacy, uncertainty estimation, and explainability so that the models can support decision-making rather than automate diagnosis.

Expected outputs include personalised cognition simulation algorithms, benchmark comparisons with direct behaviour-to-label baselines, interpretable markers of cognitive-affective dysfunction, and prototypes for non-invasive mental health monitoring. The studentship is full-time for 3.5 years (or part-time pro rata) and, for eligible students, provides Home or International tuition fees plus an annual tax-free stipend of at least £21,805.

Applicants should have a background in computer science, AI, machine learning, affective computing, computational psychology, or a closely related area, and must have strong programming skills. This is a research-intensive opportunity for candidates interested in developing personalised, multimodal AI methods for clinically relevant mental health assessment.

The application deadline is 23 October 2026. The studentship is expected to commence on 21 September 2026, or as soon as possible thereafter.