metadata

language:
  - hu
tags:
  - text-classification
license: gpl
metrics:
  - accuracy
widget:
  - text: Jó reggelt! majd küldöm az élményhozókat :).

Hungarian Sentence-level Sentiment Analysis model with huBERT

For further models, scripts and details, see our repository or our demo site.

Pretrained model used: huBERT
Finetuned on Hungarian Twitter Sentiment (HTS) Corpus
Labels: 1, 2

Limitations

max_seq_length = 128

Results

Model	HTS2	HTS5
huBERT	85.55	68.99
XLM-RoBERTa	85.56	85.56

Citation

If you use this model, please cite the following paper:

@inproceedings {yang-bart,
    title = {Improving Performance of Sentence-level Sentiment Analysis with Data Augmentation Methods},
    booktitle = {Proceedings of 12th IEEE International Conference on Cognitive Infocommunications (CogInfoCom 2021)},
    year = {2021},
    publisher = {IEEE},
    address = {Online},
    author = {{Laki, László and Yang, Zijian Győző}}
    pages = {417--422}
}