This package is a natural language processing (NLP) library that allows users to access large language models and use them to compare datasets where variable names are in unstructured text form. The target users are often academic researchers in the social sciences, such as psychology/mental health. We are actively recruiting contributors. We have an existing Python library also.
The source code is at: https://github.com/harmonydata/harmony_r
The web front-end of the tool is 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.
Tracker
Mailing Lists (0 public mailing lists)
SCM Repository (Subversion: 0 updates, 2 adds)
Project Home Page
