|
--- |
|
tags: |
|
- ernie |
|
- health |
|
- tweet |
|
datasets: |
|
- custom-phm-tweets |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: ernie-phmtweets-sutd |
|
results: |
|
- task: |
|
name: Text Classification |
|
type: text-classification |
|
dataset: |
|
name: custom-phm-tweets |
|
type: labelled |
|
metrics: |
|
- name: Accuracy |
|
type: accuracy |
|
value: 0.885 |
|
--- |
|
|
|
# ernie-phmtweets-sutd |
|
|
|
This model is a fine-tuned version of [ernie-2.0-en](https://huggingface.co/nghuyong/ernie-2.0-en) for text classification to identify public health events through tweets. The dataset was used in an [Emory University Study on Detection of Personal Health Mentions in Social Media](https://arxiv.org/pdf/1802.09130v2.pdf), with this [custom dataset](https://github.com/emory-irlab/PHM2017). |
|
|
|
It achieves the following results on the evaluation set: |
|
- Accuracy: 0.885 |
|
|
|
## Usage |
|
```Python |
|
from transformers import AutoTokenizer, AutoModelForSequenceClassification |
|
tokenizer = AutoTokenizer.from_pretrained("dibsondivya/ernie-phmtweets-sutd") |
|
model = AutoModelForSequenceClassification.from_pretrained("dibsondivya/ernie-phmtweets-sutd") |
|
``` |
|
|
|
### Model Evaluation Results |
|
With Validation Set |
|
- Accuracy: 0.889763779527559 |
|
|
|
With Test Set |
|
- Accuracy: 0.884643644379133 |
