BERTForDetectingDepression-Twitter2020

This model is a fine-tuned version of AIMH/mental-bert-base-cased on data taken from Safa, R., Bayat, P. & Moghtader, L. Automatic detection of depression symptoms in twitter using multimodal analysis. J Supercomput (2021).. It achieves the following results on the evaluation set:

• Loss: 0.8966
• Accuracy: 0.6445

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

Eval Accuracy: 0.6445

Eval Precision: 0.627281460134486

Eval Recall: 0.6690573770491803

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 3.083803249747333e-05
• train_batch_size: 4
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 2

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.6484	1.0	4500	0.6851	0.637
0.5904	2.0	9000	0.8966	0.6445

Framework versions

• Transformers 4.42.4
• Pytorch 2.3.1+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1