Making data harmonisation simple! Harmony is an open source tool which helps psychologists analyse datasets using AI and natural language processing.
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.
Try Harmony at harmonydata.ac.uk
Join our Discord server at https://discord.com/invite/harmonydata
Clone us from Github at https://github.com/harmonydata/harmony
How you can get involved in Harmony:
1. Use the tool, and share and promote us on LinkedIn and Twitter.
If you're a developer,
2. clone the repository (ideally both front and back ends) and get the tool running locally
3. Pick your issues to work on. We have lots of ideas: https://harmonydata.ac.uk/ideas and a guide to contributing here: https://harmonydata.ac.uk/contributing-to-harmony/
4. The highest priority issue is the PDF file handling, which is on the competitions website Kaggle: https://harmonydata.ac.uk/harmony-on-kaggle/. We really appreciate you having a go at this challenge!
If you're a researcher,
5. Please use us in your research, let us know of your ideas on how to improve the tool, and don't forget to cite the tool (https://harmonydata.ac.uk/frequently-asked-questions/) and link to Harmony!