Towards Predicting Stock Price Moves with Aid of Sentiment Analysis of Twitter Social Network Data and Big Data Processing Environment

摘要

This chapter illustrates design and evaluation of a sentiment analysis based system that may be used to predict future stock prices. Social media information is processed in order to extract opinions that are associated with Apple Inc. company. The authors took advantage of large datasets available from Twitter micro blog-ging platform and widely available stock market records. Data was collected during 3 months and processed for further analysis. Machine learning was employed to conduct sentiment classification of data in order to estimate future stock prices. Calculations were performed in distributed environment according to Map Reduce programming model. Evaluation and discussion of predictions results for different time intervals and input datasets is discussed in terms of efficiency and feasibility of the chosen approach.