Publication announced

Published · Updated · Thomas Wood
Publication announced

Our NLP research has been published in BMC Psychiatry!

Fast Data Science has been working on the Harmony project in collaboration with UCL, Ulster University, and Universidade Federal de Santa Maria. Harmony is an open-source natural language processing tool designed to revolutionise mental health research as well as an AI research project.

We are pleased to announce the publication of a paper coming out from this collaboration, Using natural language processing to facilitate the harmonisation of mental health questionnaires: a validation study using real-world data, authored by Eoin McElroy, Thomas Wood, Raymond Bond, Maurice Mulvenna, Mark Shevlin, George B. Ploubidis, Mauricio Scopel Hofmann and Bettina Moltrecht, and published in BMC Psychiatry, which is part of Springer Nature. Our paper demonstrates Harmony’s ability to predict correlations in mental health questionnaires - how the cosine scores coming out of Harmony relate to real-world data correlations.

Open access natural language processing paper

Read BMC paper

Our publication is open access. Click to read online or download as PDF.

You can try Harmony at https://harmonydata.ac.uk

🤷 What does Harmony do?

👉 Psychologists and social scientists often have to match items in different questionnaires, such as ““I often feel anxious”” and ““Feeling nervous, anxious or afraid””.

👉 This is called harmonisation.

👉 Harmonisation is a time consuming and subjective process.

👉 Going through long PDFs of questionnaires and putting the questions into Excel is no fun.

✅ Enter Harmony, a tool that uses natural language processing and generative AI models to help researchers harmonise questionnaire items, even in different languages.

Harmony addresses a critical challenge in psychology and social sciences: harmonising text data from diverse questionnaires often found in PDF format. By leveraging AI and natural language processing, Harmony efficiently compares and aligns questionnaire items, enabling researchers to conduct longitudinal studies using datasets from multiple studies. This groundbreaking tool is helping to unlock the potential of existing data and accelerate mental health research.

Funded by Wellcome and UKRI Economic and Social Research Council, Harmony is freely available for researchers to download and customize. Join the open-source community and help shape the future of mental health research.

Your NLP Career Awaits!

Ready to take the next step in your NLP journey? Connect with top employers seeking talent in natural language processing. Discover your dream job!

Find Your Dream Job

Can I put sensitive data into an AI model at work?
Generative ai

Can I put sensitive data into an AI model at work?

No part of this blog post constitutes legal advice. A common question that came up at the two expert witness conferences which I attended in 2026, was

Can AI be used in court documents in 2026?
Generative aiLegal ai

Can AI be used in court documents in 2026?

There are a number of unresolved questions around when and how AI can be used in court documents. A variety of cases have been reported where litigants in person, advocates, or expert witnesses have been admonished or penalised by the courts for undeclared or inappropriate use of AI. In this post, I will focus on AI use in England and Wales, although I have covered some other jurisdictions in an earlier blog post on the topic.

Bond Solon Expert Witness Conference 2026
Legal aiEvents

Bond Solon Expert Witness Conference 2026

Thomas Wood, director of Fast Data Science, appeared today as a panelist at the Bond Solon Expert Witness Conference on 6 November 2026 at Church House, Westminster in London. This follows Thomas’s appearance at the Ireland’s Expert Witness Conference on 20 May 2026.

What we can do for you

Transform Unstructured Data into Actionable Insights

Contact us