This is a project that uses machine learning and sentiment analysis to predict stock trends based on social media articles, specifically tweets. The goal of this project is to achieve high accuracy in predicting the movement of stock prices based on sentiment analysis of tweets.

In this project, we developed a model that achieved 89.8% accuracy in classifying tweets and applying sentiment analysis. We used supervised learning models such as Naive Bayes, Random Forest, Decision Trees, AdaBoost and Logistic Regression to find the sentiment of the tweet. We also found the correlation between tweet sentiments and closing stock prices to be 0.6, which allowed us to predict the movement of stock prices.

Our model works by analyzing tweets related to a specific stock and assigning a sentiment score to each tweet. The sentiment score is then used to predict the movement of the stock price. We used a variety of supervised learning models to classify the sentiment of each tweet, and we trained our model on a large dataset of tweets and stock prices.

Our model achieved an accuracy of 89.8% in classifying tweets and predicting stock trends. We found a correlation of 0.6 between tweet sentiments and closing stock prices, which allowed us to predict the movement of stock prices with a high degree of accuracy.

To use our model, simply provide a list of tweets related to a specific stock, and our model will assign a sentiment score to each tweet and predict the movement of the stock price. You can use our model to make informed decisions about buying or selling stocks based on social media sentiment.