Pydata on 2 July

Harmony at PyData London - 86th Meetup

Update: you can download the slides from the presentation here

Topic: NLP and generative models for psychology research

Thomas Wood will present our work on Harmony, harmonydata.ac.uk, which is a free online tool that uses generative AI and LLMs to help psychologists analyse datasets. It uses Python, Pandas and HuggingFace Sentence Transformers to find similarities between questionnaires.

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.
We’ve been working on an open source Python library and free web tool called Harmony which uses natural language processing and generative AI models to help researchers harmonise questionnaire items, even in different languages.
https://pypi.org/project/harmonydata/
https://github.com/harmonydata/harmony

Register for Pydata event

📅 Date: 2 July 2024

🕘 Time: 7pm

🏢 Where: EC4R 3AD

See other Harmony events

8 October 2024: Harmony: a free online tool using LLMs for research in psychology and social sciences at AI|DL London
11 and 12 September 2024: Harmony at MethodsCon Futures in Manchester
3 June 2024: Harmony Hackathon at UCL
5 May 2024: Harmony: A global platform for harmonisation, translation and cooperation in mental health at Melbourne Children’s LifeCourse Initiative seminar series.
27 March 2024: Harmony at AI Camp
17 August 2023: Harmony and TIDAL workshop

Improving Harmony's PDF extraction with user testing

Since we built Harmony, a common complaint has been that it frequently identifies the wrong questions in PDFs. The original algorithm for finding questions in PDFs was a mixture of rule based heuristics and some hand coded logic to look for e.g. lines in the document which begin with numbers. This was very fragile and worked fine on short questionnaires such as the GAD-7, but failed on larger documents. We decided to run a competition with our partner DOXA AI where members of the public could train their own model to extract questions from PDFs.

Harmony at MQ and DataMind Data Science Workshop

Harmony at MQ and Datamind Data Science workshop On 2 May 2025, Dr Eoin McElroy demonstrated Harmony at the MQ and Datamind Data Science workshop in Deutsche Bank. Eoin’s presentation focused on “Maximising the use of existing survey data: facilitating cross-study research using retrospective harmonization.” The workshop brought together researchers interested in applying novel harmonisation techniques to existing datasets. Eoin explained traditional harmonisation processes and presented a user-friendly guide to the Harmony tool, demonstrating how natural language processing can streamline the harmonisation process.