Stock Price Forecasting with Support Vector Regression Based on Social Network Sentiment Analysis and Technicl Analysis

For many years the following question has been a source of continuing controversy in both academic and business circles: To what extent can the past history of a common stock s price be used to make meaningful predictions concerning the future price of the stock (Fama, 1965). The rise of social networks and their role in daily life is significant due to the presence of these networks. Investors and their views on the stock market have affected financial markets. The purpose of this study is to predict the daily stock price using sentiment analysis and technical indicators. Therefore, support vector regression (SVR) is used in this study. The tests involving feature combination with numeric and textual data and the proposed technical indicator features with the sentiment score series from tweets yield the best results of all, with classification accuracy for next day stock price prediction using the support vector regression model . The innovation of this study in comparison with other researches is stock price forecasting in short-term by combining the analysis of users opinions and technical indicators, which uses the support vector regression. The next section gives an overview of related work in the fields of text mining and stock price trend forecasting from unstructured data, methods and algorithms used in the research. In Section 3, the research methodology is stated and in the 4 and 5 sections, the results of modeling and discussion and conclusion will be stated.