Karols's picture
Upload README.md with huggingface_hub
87f86cb
metadata
language: ja
tags:
  - text-classification
  - financial-sentiment-analysis
  - sentiment-analysis
datasets:
  - datasets/financial_phrasebank
metrics:
  - f1
  - accuracy
  - precision
  - recall
widget:
  - text: 売上高は30%増の3,600万ユーロとなった。
    example_title: Example 1
  - text: ブラックフライデー開幕。店頭プロモーション一覧。
    example_title: Example 2
  - text: CDPROJEKT株はWSE上場企業の中で最大の下落を記録した。
    example_title: Example 3

Finance Sentiment JA (base)

Finance Sentiment JA (base) is a model based on bert-base-japanese for analyzing sentiment of Japanese financial news. It was trained on the translated version of Financial PhraseBank by Malo et al. (20014) 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-ja-base")
nlp("売上高は30%増の3,600万ユーロとなった。")
[{'label': 'positive', 'score': 0.9987998807375955}]

Performance

Metric Value
f1 macro 0.959
precision macro 0.959
recall macro 0.959
accuracy 0.967
samples per second 134.9

(The performance was evaluated on RTX 3090 gpu)

Changelog

  • 2023-09-18: Initial release

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