A library for scoring Alternate Uses Tests with word embedding models.

See it implemented on https://openscoring.du.edu/. There is also an API available https://openscoring.du.edu/docs.

As of Jan 2024, the functionality for using GPT-based fine-tuned large language models, or prompted ChatGPT or GPT-4 models is being/has been moved to Ocsai.

Organisciak, P., Acar, S., Dumas, D., Berthiaume, K., (2022). Beyond Semantic Distance: Automated Scoring of Divergent Thinking Greatly Improves with Large Language Models. Submitted for publication.

Dumas, D., Organisciak, P., & Doherty, M. D. (2020). Measuring divergent thinking originality with human raters and text-mining models: A psychometric comparison of methods. Psychology of Aesthetics, Creativity, and the Arts. https://doi.org/10/ghcsqq