MEASURING THE SOCIAL MEDIA SENTIMENT INFLUENCE ON STOCK MARKET PRICE PREDICTION

—The machine learning is become more and more popular for understanding the patterns and information in various complex applications. In this work we are utilizing the machine learning techniques for understanding the patterns of stock market price. The stock market price prediction is one of the most fluctuating in nature. That incorporates the different influencing factors which make it much dynamic to understand. Therefore in this presented work for understanding the trends of the stock market data we have use the social media data analysis techniques for more accurate data prediction. The proposed model includes the natural language processing (NLP) techniques and machine learning algorithms for first computing the orientation of the sentiments of the social media. Then the common regression method has been employed over the yahoo financial data. The financial data prediction will be used with the social media sentiment orientation and the word sentiment scores for correcting the error in predictions. The implementation of the proposed model has been utilized the JAVA technology and API implementation for demonstrating the effectiveness of the prepared model. The comparative performance study among two other similar variants of stock market price prediction models demonstrates the superiority of the proposed model. The model will be evaluated and compared in terms of accuracy, error rate, and memory and time consumption. The model provides up to 5-8% improvement into the accurate prediction.