Exploring the Use of Sentiment Data in machine learning stock Market Predictions

This research paper investigates the utilization of sentiment data from social media (specifically Twitter) and financial news articles in machine learning models for predicting stock market movements. Various machine learning algorithms, including Neural Networks (NN), Support Vector Machines (SVM), Naïve Bayes (NB), Long Short-Time Memory (LSTM), and Random Forest(RF), are examined for their effectiveness in sentiment analysis and stock market prediction. The study finds that sentiment analysis of social media and news articles provides valuable insights into stock market sentiment, with LSTM and SVM showing high accuracy in predicting stock movements. The results highlight the potential benefits of incorporating sentiment data alongside historical price data for stock price predictions, but also show that variations exist in effectiveness of sentiment data for predictions of different stocks. This research contributes to the existing literature, guiding researchers in developing more robust stock market forecasting models, ultimately improving investment strategies.