This project focuses on analyzing the sentiment of news articles to predict stock trends. It features a Flask-based web application designed to provide real-time financial data analysis and sentiment tracking.
- Input: Users can enter a company name or ticker symbol to retrieve relevant news articles.
- Process: Each news article is analyzed for sentiment, with scores generated to gauge the article's impact on stock trends.
- Output: The application delivers actionable insights and confidence indices based on the sentiment analysis, helping investors make informed decisions about their investments.
Before you begin, make sure you have the following installed:
- Python (version 3.11 or higher)
- Poetry (recommended)
- or pip
- Clone the repository:
git clone https://github.com/LifeAdventurer/sentify.git cd sentify - Install dependencies:
poetry install
- Activate the virtual environment:
poetry env activate poetry shell
- Clone the repository:
git clone https://github.com/LifeAdventurer/sentify.git cd sentify - Create and activate a virtual environment:
python -m venv venv source venv/bin/activate # On Windows use `venv\Scripts\activate`
- Install dependencies:
pip install -r requirements.txt
To serve the Flask app locally, run:
python src/main.py
To configure the application, update the config.py file in the src/config directory. Key parameters include:
TOP_COMPANIES_COUNT = 10000
TIMESTAMP_FORMAT = "%Y-%m-%dT%H:%M:%SZ"
UTC_DIFFERENCE = 8
MAX_NEWS_LOOKBACK_DAYS = 60
CPU_COUNT = 2
TOP_COMPANIES_COUNT: The number of top companies ranked by market cap to search.TIMESTAMP_FORMAT: The format for timestamps used in the application, especially for the news API.UTC_DIFFERENCE: The difference in hours between local time and UTC.MAX_NEWS_LOOKBACK_DAYS: The max number of days to look back when fetching news articles.CPU_COUNT: The number of CPUs to be used for multiprocessing.
This project is licensed under the GNU General Public License v3.0 - see the LICENSE file for details.