This project explores the potential of sentiment analysis in stock market prediction. It utilizes a Random Forest Classifier to analyze the sentiment expressed in news articles related to specific stocks. By understanding the overall sentiment surrounding a company, we can potentially gain insights into future stock price movements.
- Sentiment Classification: Leverages a Random Forest Classifier, a powerful machine learning algorithm for sentiment analysis tasks.
- Stock-Specific Analysis: Focuses on news articles pertaining to specific stocks, allowing for targeted sentiment analysis.
- Actionable Insights: Aims to uncover sentiment-based trends that may be useful in predicting stock market movements (Note: This is for informational purposes only, and should not be used for sole investment decisions).
-
Stock Sentiment Analysis.ipynb: Contains the source code for the sentiment analysis and classification model. -
Data.csv: Holds the dataset with news articles and their sentiment labels (positive or negative). -
Performance Metrics: Includes a confusion matrix, accuracy score, and a classification report providing precision, recall, and F1-score for each sentiment class (positive and negative).
-
LICENSE: Outlines the terms under which this project is distributed according to the Apache License.
Sentiment analysis can be a complex task, and the results obtained from this project may not be a perfect reflection of actual market trends. It's crucial to consider this project for informational purposes only, and to incorporate other financial analysis methods when making investment decisions.