Stock Market Prediction using Sentiment Analysis of Tweets
date
Mar 16th 2018
category
machine-learning
short description
SVM, Logistic Regression and Multi-layer Perceptron are used on the classified sentiment data along with stock price to predict the trends of stock price.
Info
- Implemented web crawlers to extract Tweet data and Stock Market Price.
- NLP techniques like Tokenization, Stop-word-removal, Stemming are used to perform language modeling and Sentiment Analysis on Twitter data.
- Machine learning techniques like Support Vector Machines, Logistic Regression and Multi-layer Perceptron are used on the classified sentiment data along with stock market price to predict the trends of stock market price.
- The ML models predicted the prices most accurately when Topic Modeling was used. Considering past 5 days of tweet sentiments, we were able to predict change in stock prices with close to 70% accuracy.