News sentiment and actual price of stock data: using news classification technique / Anupong Sukprasert, Weerasak Sawangloke and Benchamaphorn Sombatthira

The objective of this study is to examine the relationship between news sentiment and actual price of stock data by using news classification technique. The effects of online news towards stock market turning points. This investigation studies the methods of news sentiment analysis. There were seventeen companies’ data used to analyze the data. News classification techniques was used to sort out key features for further classification. News classification into factors affecting stock market price was done using Naïve Bayes, Deep Learning, Generalized Linear Model (GLM) and Support Vector Machine (SVM). The news classification and news sentiment were used to predict the stock market turning points. Results show that best news classification approach is based on Deep Learning techniques that provide the most accurate classification. The study suggests that the accurate and time saving decision for stock investors.