Finance Sentiment
Collection
A collections of models for detecting financial sentiment. • 8 items • Updated • 1
Finance Sentiment ES (base)
Finance Sentiment ES (base) is a model based on bert-base-spanish-wwm-cased for analyzing sentiment of Spanish financial news. It was trained on the translated version of Financial PhraseBank by Malo et al. (2014) for 10 epochs on single RTX3090 gpu.
The model will give you a three labels: positive, negative and neutral.
How to use
You can use this model directly with a pipeline for sentiment-analysis:
from transformers import pipeline
nlp = pipeline("sentiment-analysis", model="bardsai/finance-sentiment-es-base")
nlp("Las ventas netas aumentaron un 30%, hasta 36 millones de euros.")
[{'label': 'positive', 'score': 0.9987998807375955}]
Performance
| Metric | Value |
|---|---|
| f1 macro | 0.973 |
| precision macro | 0.974 |
| recall macro | 0.972 |
| accuracy | 0.978 |
| samples per second | 135.1 |
(The performance was evaluated on RTX 3090 gpu)
Changelog
- 2023-09-18: Initial release
License
This model is released under the Creative Commons Attribution 4.0 International (CC BY 4.0) license, inherited from the base model dccuchile/bert-base-spanish-wwm-cased (BETO, CC BY 4.0).
Commercial use caveat (from the BETO authors): "The license CC BY 4.0 best describes our intentions for our work. However we are not sure that all the datasets used to train BETO have licenses compatible with CC BY 4.0 (specially for commercial use). Please use at your own discretion and verify that the licenses of the original text resources match your needs." This caveat is passed through to this derivative model.
Attribution: BETO (bert-base-spanish-wwm-cased) — Cañete et al., Universidad de Chile; Finance Sentiment ES (base) — bards.ai.
About bards.ai
At bards.ai, we focus on providing machine learning expertise and skills to our partners, particularly in the areas of nlp, machine vision and time series analysis. Our team is located in Wroclaw, Poland. Please visit our website for more information: bards.ai
Let us know if you use our model :). Also, if you need any help, feel free to contact us at info@bards.ai
- Downloads last month
- 150
Model tree for bardsai/finance-sentiment-es-base
Base model
dccuchile/bert-base-spanish-wwm-casedDataset used to train bardsai/finance-sentiment-es-base
Collection including bardsai/finance-sentiment-es-base
Evaluation results
- F1 (macro) on Financial PhraseBank (translated to Spanish)self-reported0.973
- Precision (macro) on Financial PhraseBank (translated to Spanish)self-reported0.974
- Recall (macro) on Financial PhraseBank (translated to Spanish)self-reported0.972
- Accuracy on Financial PhraseBank (translated to Spanish)self-reported0.978