Detection Model for Correlation between SNS Spikes and Stock Price Movement

Abstract

Stock price prediction has become an important research theme in text mining application fields. Many models of sentiment analyses for the prediction have been published. If they found SNS volume spikes on companies or products, many stock investors might quickly sell the stocks even if they cannot predict whether the stock price direction is an increase or a decrease. In the paper, we shall propose a detection model for the clear-cut correlation between a SNS spike and stock price movement. If we find a SNS spike, firstly, topic extraction is conducted on the SNS text data to remove the noise data to extract a purely breaking topic. Then, from the breaking topic distribution, we make the differential equation. Finally, we determine whether the solution data matches the actual stock price data.