poltextlab/illframes-climate-binary

Model description

An xlm-roberta-large model fine-tuned on parliamentary speeches (in English) labeled as:

1: contains climate-related illiberal frame

0: does not contain climate-related illiberal frame

Fine-tuning procedure

This model was fine-tuned with the following key hyperparameters:

Number of Training Epochs: 5

Batch Size: 8

Learning Rate: 5e-06

Maxlen = 256

Model performance

The model was evaluated on an independent test set of 969 samples.

Weighted F1 score is 0.76.