Information Retrieval from Internet Data Using Textual Mining and Statistical Models for Stock Market Price Movement Prediction

In this research, it is strictly based on the procedures of normal data analysis. They start from data (text) acquisition that is collected from various and objective sources, to data processing by utilizing unstructured data processing, TF-IDF, and Bag-of-words model methods, and finally to the data (text) analysis by setting up mathematical models like linear regression and neural network models, in the following, picking out the keywords with higher frequencies in the datasets. Eventually, after accurate calculations and impartial analysis in New Energy, Real Estate, and Steel industries, it concludes that the industries related to the selecting keywords have strong correlations to the stock prices.