About Ocsai
Ocsai (Organisciak et al., 2023) uses supervised learning: models are fine-tuned on thousands of human-judged divergent thinking responses so they learn what originality looks like.
Scores use a 1–5 scale, where 1 is very unoriginal, 5 is very original, and 3 is the median.
Ocsai works in multiple languages! Set the language and task type for your data in the dropdown menu above.
How do I use Ocsai?
To have your responses scored, upload a CSV that includes a column named 'item', containing the item text, and a column named 'response', which contains the participant's response. The algorithm is case sensitive for the 'item' and 'response' column names, but it does not matter if other columns are present in the CSV.
The algorithm will add two new columns to your CSV: one named 'originality' which reflects the model's score and a column named 'modelname', which is added to reflect the model providing the score.
For more scoring options and models, check out the full Ocsai site here!
