metadata

language:
  - ja
library_name: transformers
license: apache-2.0
metrics:
  - accuracy
  - f1
pipeline_tag: text-classification

BERT for Sentiment Analysis of Japanese Twitter

This model was finetuned from BERT for Japanese Twitter.

This model was finetuned on the Japanese Twitter Sentiment 1k, which includes 1000 examples with four sentiment labels: negative, neutral, positive, and mixed.

BERT for Japanese SNS Sentiment is reccomended over this model.