Downloads · 30 days
8
3% of all-time downloads
seantw/covid-19-vaccination-tweet-relevance
covid-19-vaccination-tweet-relevance is a text classification model from seantw. Use it when you need a label for a piece of text. It is set up for transformers. The card lists the license as mit.
This model is a text classifier trained to determine whether a tweet is related to COVID-19 vaccination or not.
Downloads · 30 days
8
3% of all-time downloads
All-time downloads
310
Public
Repo size
2.7 GB
Likes
0
Public
Click a slice to open those files.
.bin1.3 GB · 100%
From the Hugging Face model README
This model is a text classifier trained to determine whether a tweet is related to COVID-19 vaccination or not.
tokenizer = AutoTokenizer.from_pretrained("seantw/covid-19-vaccination-tweet-relevance")
model = AutoModel.from_pretrained("seantw/covid-19-vaccination-tweet-relevance")
The training corpus comprises 9373 tweets, a daily random sampled dated from December 2020 to June 2022. These tweets were labeled by domain experts.
We have seperated trained another model for classifying the stance of a tweet towards the COVID-19 vaccination. Please refer to covid-19-vaccination-tweet-stance for more information.
The model's performance metrics on the test set are as follows:
These metrics are based on a test set with a total size of 3699 samples.
The confusion matrix of predictions on the test set is as follows:
| Predicted: irrelevance | Predicted: relevance | |
|---|---|---|
| True: irrelevance | 1239 | 165 |
| True: relevance | 62 | 2233 |
The model is fine-tuned based on COVID-Twitter-BERT v2.
Sean Yun-Shiuan Chuang ([email protected])