Fast Data Science presents Harmony at Pydata on 2 July

Above: video of Thomas Wood presenting Harmony at the Pydata on 27 March 2024

Harmony at PyData London - 86th Meetup

NLP and generative models for psychology research - Thomas Wood

Update: you can download the slides from the presentation here

Link to the meet up: Meetup.com.

I will present our work on Harmony, harmonydata.ac.uk, which is a free online AI research 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://harmonydata.ac.uk
• https://pypi.org/project/harmonydata/
• https://github.com/harmonydata/harmony

About Fast Data Science

Fast Data Science is a leading data science consultancy firm providing bespoke machine learning solutions for businesses of all sizes across the globe. With a focus on innovation and collaboration, Fast Data Science empowers businesses to leverage the transformative power of data.