FinnSentiment -- A Finnish Social Media Corpus for Sentiment Polarity Annotation
Paper โข 2012.02613 โข Published
How to use fergusq/finbert-finnsentiment with Transformers:
# Use a pipeline as a high-level helper
from transformers import pipeline
pipe = pipeline("text-classification", model="fergusq/finbert-finnsentiment") # Load model directly
from transformers import AutoTokenizer, AutoModelForSequenceClassification
tokenizer = AutoTokenizer.from_pretrained("fergusq/finbert-finnsentiment")
model = AutoModelForSequenceClassification.from_pretrained("fergusq/finbert-finnsentiment")This is a FinBERT model fine-tuned with the FinnSentiment dataset. 90% of sentences were used for training and 10% for evaluation.
| Metric | Score |
|---|---|
| Accuracy | 0.8639028475711893 |
| F1-score | 0.8643024701696561 |
| Precision | 0.8653866541244811 |
| Recall | 0.8639028475711893 |
| Matthews | 0.6764924917164834 |
FinBERT-FinnSentiment is licensed under the CC BY 4.0 License (same as FinBERT and the FinnSentiment dataset).