Harmony tends to perform better if you upload a file with item numbers.
If there are are no question numbers in the instrument, it’s very hard for Harmony to distinguish question text from other content such as the copyright information. Click here to see an example PDF with question numbers included.
Also, if your PDF is a scanned document, please see if you can find a fully digitised (OCR’ed) version of the document.
We suggest either finding a file with question numbers or better quality content. Or try a different file format such as Word, Excel or CSV. We have guidance on formatting your files for Harmony.
Harmony supports:
Finally, feel free to raise an issue to let us know that your PDF isn’t being parsed. Please also share the PDF in question.
How are research funders reacting to the AI governance vacuum? A recent article by Sense about Science, a leading independent charity that promotes the public interest in sound science and evidence, highlights the growing need for responsible AI governance in research. The article, titled Research funders tackle AI governance vacuum with pragmatic guidance, discusses the alarming gap between the rapid development and adoption of AI tools, and the lack of clear frameworks for their safe and ethical use.
Tech Talk at the AI|DL AI Meetup (London) Artificial Intelligence and Deep Learning for Enterprise Thomas Wood will present the Harmony project at the 19th AI and Deep Learning for Enterprise meetup on 8 October 2024. Topic: Harmony: a free online tool using LLMs for research in psychology and social sciences Speaker: Thomas Wood (Fast Data Science) Description: 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 researchers compare items in questionnaires such as GAD-7 (used to measure anxiety), even when they are written in different languages.
