Update README.md

README.md

@@ -3,7 +3,7 @@ tags:
 - generated_from_trainer
 model-index:
 - name: drug-stance-bert
-  results: []
+  results: [1, 0, -1]
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -11,33 +11,42 @@ should probably proofread and complete it, then remove this comment. -->
 
 # drug-stance-bert
 
-This model was trained from scratch on an unknown dataset.
+This model is a fine-tuned version of [cardiffnlp/twitter-roberta-base-sentiment](https://huggingface.co/cardiffnlp/twitter-roberta-base-sentiment) on [COVID-CQ](https://github.com/eceveco/COVID-CQ), a dataset that contains 3-label annotated opinions (negative, neutral, and positive) of the tweet initiators regarding the use of Chloroquine or Hydroxychloroquine for the treatment or prevention of the coronavirus.
 
 ## Model description
 
-More information needed
+"We developed two COVID-drug-stance RoBERTa-base models by fine-tuning a pre-trained Twitter-specific stance detection model on a stance data set called COVID-CQ. The data were divided into training-dev-test validation datasets with a 70:10:20 ratio. Model I (COVID-drug-stance-BERT) was trained on the original tweet data, and Model II (COVID-drug-stance-BERT-masked) was trained on tweets with drug names masked as “[mask]” for model generalizability on different drugs. The two models had similar performance on the COVID-19 validation set: COVID-drug-stance-BERT had an accuracy of 86.88%, and the masked model had an accuracy of 86.67%. The two models were then evaluated by predicting tweet initiators’ attitudes towards the drug mentioned in each tweet using randomly selected test sets (100 tweets) of each drug (Hydroxychloquine, Ivermectin, Molnupiravir, Remdesivir). As suggested by the evaluation in Table 2, Model I had better performance and was therefore used in this study". 
 
-## Intended uses & limitations
 
-More information needed
+| **Drug**               | **Model I: Original Tweet** |             |              | **Model II: Drug Names Masked** |             |              |
+|------------------------|:---------------------------:|:-----------:|:------------:|:-------------------------------:|:-----------:|:------------:|
+|                        |        **Precision**        |  **Recall** | **F1-Score** |          **Precision**          |  **Recall** | **F1-Score** |
+| **Hydroxychloroquine** |             0.93            |     0.92    |   **0.92**   |               0.84              |     0.83    |      0.83    |
+| **Ivermectin**         |             0.92            |     0.91    |   **0.91**   |               0.72              |     0.68    |      0.68    |
+| **Molnupiravir**       |             0.89            |     0.89    |   **0.89**   |               0.78              |     0.77    |      0.77    |
+| **Remdesivir**         |             0.82            |     0.79    |   **0.79**   |               0.70              |     0.66    |      0.66    |
 
-## Training and evaluation data
+The model uploaded here is Model I.
+
+## Intended uses & limitations
+Predict opinions (negative, neutral, and positive) of tweet initiators regarding the use of a drug for the treatment or prevention of the coronavirus.
 
-More information needed
+The model works better when there's only one drug name in a single tweet.
+## Training and evaluation data
+COVID-CQ
 
 ## Training procedure
-
+See our Github repo for training scripts. [https://github.com/ningkko/COVID-drug](https://github.com/ningkko/COVID-drug)
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
 - learning_rate: 5e-05
-- train_batch_size: 96
-- eval_batch_size: 96
+- train_batch_size: 24
+- eval_batch_size: 24
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- lr_scheduler_warmup_steps: 500
-- num_epochs: 4
+- num_epochs: 3.0
 
 ### Framework versions