Projects

An LLM-based auditing tool that reads a whole corpus of academic papers and audits how each one handles response-validity threats in self-report data — tested at a scale of nearly 50,000 articles.

A self-assessment dashboard for the Professional Quality of Life Scale (ProQOL) — helping professionals track compassion satisfaction, burnout, and secondary traumatic stress over time.

An R pipeline that compares the latent structure of LLM text embeddings with human psychometric data using Exploratory Graph Analysis (EGA) — using language models as a new lens on construct validity, factor structure, and scale design.

A reusable Shiny platform for online surveys that give participants immediate, personalised feedback on their own results — its flagship deployment, the Machiavellianism self-test (TDMS), has been completed by more than 40,000 participants who chose to share their data.

An R + Quarto pipeline that turns a study's raw questionnaire data into a bespoke, plain-language HTML (or PDF) feedback report for every participant — scoring the HEXACO-100, PVQ-21, and NISE against population norms so respondents get something meaningful back for taking part.

A long-running program on how personality pathology is diagnosed — comparing categorical and dimensional (DSM-5 AMPD, ICD-11, HiTOP) approaches and their downstream effects on stigma, clinical utility, and treatment, especially for borderline personality disorder.

A government-funded study of the relationship between personality and online behaviour, using consent-gated digital data donation rather than self-report alone.

Person-specific measurement using ecological momentary assessment and intensive longitudinal designs — studying how distress and personality states fluctuate within individuals over time, and whether measures built on group averages hold at the individual level.

Developing open-source tools to detect careless, inconsistent, and distorted responding in psychological research and assessment — including informant-report validity scales and brief, appendable inconsistency and under-reporting measures.

Building and validating open-source psychological measures — from item generation through factor analysis (EFA/CFA), reliability, and construct validation — so researchers and clinicians have rigorous, freely available instruments.

An emerging project applying large language models and embedding-based methods to study the structure of personality — how AI represents traits, and what that reveals about long-standing questions in personality science.

Using large language models to assist translating and culturally adapting psychometric scales across languages — making validated instruments more accessible to non-English-speaking researchers and clinicians.

A government-funded project developing AI chatbots to support professional training.