Finance-Sentiment-Classification Open-Source Financial Sentiment Classification Model - Accurately Analyze the Sentiment Tendency of Financial Data

Finance Sentiment Classification

Developed by RashidNLP

Financial sentiment classification model based on Deberta-v2 architecture, fine-tuned on multiple financial sentiment datasets

Text Classification

Transformers

EnglishOpen Source License:MIT #Financial Sentiment Analysis #Deberta-v2 Fine-tuning #Multi-source Financial Data

Downloads 418

Release Time : 5/14/2023

Model Overview

This model is specifically designed for sentiment analysis of financial texts, capable of identifying positive, neutral, and negative emotions in the text.

Model Features

Specialized for Financial Domain

Optimized specifically for financial texts, accurately identifying sentiment tendencies in financial news and reports

Multi-dataset Fine-tuning

Fine-tuned on 4 different financial sentiment datasets, improving the model's generalization capability

Three-class Sentiment Analysis

Capable of identifying positive, neutral, and negative sentiments

Model Capabilities

Financial text sentiment analysis

News sentiment classification

Market sentiment monitoring

Use Cases

Financial Market Analysis

Stock Market News Sentiment Analysis

Analyzing sentiment tendencies in stock market-related news

Helps predict market sentiment changes

Corporate Earnings Report Sentiment Analysis

Evaluating language sentiment in corporate earnings reports

Assists in investment decision-making

Social Media Monitoring

Financial Tweet Sentiment Analysis

Analyzing sentiment on financial topics from social media platforms like Twitter

Real-time public sentiment monitoring

🚀 Deberta for Financial Sentiment Classification

This project uses a Deberta model for financial sentiment classification. It fine - tunes a pre - trained model on four finance datasets with sentiment labels, enabling accurate sentiment analysis of financial texts.

🚀 Quick Start

This project utilizes a Deberta model initially trained on over 1 million reviews from Amazon's multi - reviews dataset. Subsequently, it is fine - tuned on four finance datasets labeled with sentiment categories. The datasets used are as follows:

financial_phrasebank
chiapudding/kaggle - financial - sentiment
zeroshot/twitter - financial - news - sentiment
FinanceInc/auditor_sentiment

✨ Features

Dataset Diversity: Employs four different finance - related datasets for fine - tuning, enhancing the model's generalization ability in financial sentiment classification.
Pre - trained Base: Leverages a Deberta model pre - trained on a large - scale Amazon review dataset, providing a solid foundation for transfer learning.

📦 Installation

The project uses the transformers library. You can install it using the following command:

pip install transformers torch

💻 Usage Examples

Basic Usage

import torch
from transformers import AutoModelForSequenceClassification, AutoTokenizer

def get_sentiment(sentences):
    bert_dict = {}
    vectors = tokenizer(sentences, padding = True, max_length = 65, return_tensors='pt').to(device)
    outputs = bert_model(**vectors).logits
    probs = torch.nn.functional.softmax(outputs, dim = 1)
    for prob in probs:
        bert_dict['neg'] = round(prob[0].item(), 3)
        bert_dict['neu'] = round(prob[1].item(), 3)
        bert_dict['pos'] = round(prob[2].item(), 3)
        print (bert_dict)

MODEL_NAME = 'RashidNLP/Finance-Sentiment-Classification'
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')

bert_model = AutoModelForSequenceClassification.from_pretrained(MODEL_NAME, num_labels = 3).to(device)
tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME)

get_sentiment(["The stock market will struggle until debt ceiling is increased", "ChatGPT is boosting Microsoft's search engine market share"])

📄 License

This project is licensed under the MIT license.

Featured Recommended AI Models

Empowering the Future, Your AI Solution Knowledge Base

English 简体中文繁體中文にほんご