Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,21 @@
|
|
| 1 |
---
|
| 2 |
license: afl-3.0
|
| 3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
license: afl-3.0
|
| 3 |
---
|
| 4 |
+
|
| 5 |
+
This model is trained to classify US legislators' tweets about COVID-19 as skeptical of preventative measures or not. The model is fine-tuned on 10k hand coded tweets using vinai/bertweet-covid19-base-uncased (https://github.com/VinAIResearch/BERTweet).
|
| 6 |
+
|
| 7 |
+
The model is uncased.
|
| 8 |
+
|
| 9 |
+
|
| 10 |
+
|
| 11 |
+
sparse_categorical_accuracy: 0.9618
|
| 12 |
+
|
| 13 |
+
|
| 14 |
+
Sklearn validation metrics:
|
| 15 |
+
|
| 16 |
+
Precision: 0.927190139237617
|
| 17 |
+
Recall: 0.969193742478941
|
| 18 |
+
F1 score: 0.9465885064563841
|
| 19 |
+
|
| 20 |
+
|
| 21 |
+
|