This paper presents a new method to predicting the change of stock prices by utilizing text mining news of the stock market. Term Frequency Inverse Document Frequency (TF- IDF) is one of the most useful and widely used concepts in information retrieval. The method can handle without difficulty unstructured news of Saudi stock market (Tadawul) through reading and analysis of the news and build a relationship between the contents of the news, and keywords (core phrases). This technique must identified by analysts and financial specialists that affect the direction of the share price up or down. The aim of this paper is to explore the possibility of using text mining to automate the identification of financial news articles. The empirical results show that the proposed techniques can predict the up and down on a stock price after the news announce or released. The proposed method presented in the study is straightforward, simple and valuable for the short-term investors.
Stock market prediction, term frequency inverse document frequency (TF-IDF), text mining
M. Jarrah is with the King Abdulaziz University, Information Technology Department, Faculty of Computing and Information Technology, Jeddah, Saudi Arabia, and also with Universiti Teknologi Malaysia, Faculty of Computing, Johor Bahru, Malaysia (e-mail: firstname.lastname@example.org).
N. Salim is with the Universiti Teknologi Malaysia, Faculty of Computing, Johor Bahru, Malaysia (e-mail: email@example.com).
Mu’tasem Jarrah and Naomie Salim, "
Stock Market Prediction Based on Term Frequency-Inverse Document Frequency," Journal of Economics, Business and Management vol. 4, no. 3, pp.