Stock Sentiment Analysis using News Headlines

Using News Paper Headlines to predict weather the Next day's news would increase the stock price of a news channel or not.

Dataset

• The data set in consideration is a combination of the world news and stock price shifts.
• There are 25 columns of top news headlines for each day in the data frame.
• Class 1- the stock price increased.
• Class 0- the stock price stayed the same or decreased.

Approach

• Used TF-IDF and Bag of Words for extracting featues from the headlines.
• Used Random Forest Classifier and Multinational Naive Bayes for analysis.