Question of prediction result

[minekirito]

Thank you your sharing!

I run your project with my data successfully. But how can I see the prediction results of "O" "C" "E" "A" "N" like TableⅡ in your paper. If it is convenient to you, please explain how to interpret the results generated by the codes in 'finetune_models'.

Thank you! Looking forward to your reply !!

[minekirito]

In addition, how to use models other than 'bert-base'！ Thank you!!

[Milad-Laly]

In addition, how to use models other than 'bert-base'！ Thank you!!

I believe they are using LaTeX for the table as the screenshot seems to be from the paper. You could create a dataframe with the data and save it to a CSV.

[elhamadjidi]

@minekirito did you predict any new text using their pre-trained data?

[minekirito]

@minekirito did you predict any new text using their pre-trained data?

No. I think the performance of the model trained by this project is not enough for practical application. So I'm still working on how to train a better model.

[yashsmehta]

Hi @Milad-Laly @minekirito,
@edersoncorbari just added functionality to the repository to use our language model to make personality predictions on new text input! Please use: unseen_predictor.py.