Sentiment analysis library for russian language
Please note that Dostoevsky supports only Python 3.7+ on both Linux and Windows
$ pip install dostoevskyThis model was trained on RuSentiment dataset and achieves up to ~0.71 F1 score.
First of all, you'll need to download binary model:
$ python -m dostoevsky download fasttext-social-network-modelThen you can use sentiment analyzer:
from dostoevsky.tokenization import RegexTokenizer
from dostoevsky.models import FastTextSocialNetworkModel
tokenizer = RegexTokenizer()
tokens = tokenizer.split('всё очень плохо') # [('всё', None), ('очень', None), ('плохо', None)]
model = FastTextSocialNetworkModel(tokenizer=tokenizer)
messages = [
'привет',
'я люблю тебя!!',
'малолетние дебилы'
]
results = model.predict(messages, k=2)
for message, sentiment in zip(messages, results):
# привет -> {'speech': 1.0000100135803223, 'skip': 0.0020607432816177607}
# люблю тебя!! -> {'positive': 0.9886782765388489, 'skip': 0.005394937004894018}
# малолетние дебилы -> {'negative': 0.9525841474533081, 'neutral': 0.13661839067935944}]
print(message, '->', sentiment)- 🇷🇺 Dostoevsky — анализ тональности в Python за 5 минут
- 🇷🇺 Семантический анализ мнений о поправках к Конституции на основе данных ВКонтакте
- 🇷🇺 Как писать посты в стиле Артемия Лебедева? Подробный анализ телеграм-канала и кое-что еще
Feel free to extend this list with your article! ✨
- David Dale BERT-based models for emotion detection and classification of toxicity
If you use the library in a research project, please include the following citation for the RuSentiment data:
@inproceedings{rogers-etal-2018-rusentiment,
title = "{R}u{S}entiment: An Enriched Sentiment Analysis Dataset for Social Media in {R}ussian",
author = "Rogers, Anna and
Romanov, Alexey and
Rumshisky, Anna and
Volkova, Svitlana and
Gronas, Mikhail and
Gribov, Alex",
booktitle = "Proceedings of the 27th International Conference on Computational Linguistics",
month = aug,
year = "2018",
address = "Santa Fe, New Mexico, USA",
publisher = "Association for Computational Linguistics",
url = "https://www.aclweb.org/anthology/C18-1064",
pages = "755--763",
}