A Comparative Study between Stock Price Prediction Models Using Sentiment Analysis and Machine Learning Based on SNS and News Articles

Abstract

Submitted：July 14, 2014 1 st Revision：September 12, 2014 Accepted：September 15, 2014 * 숭실대학교 SW특성화대학원 석사과정 ** 숭실대학교 SW특성화대학원 교수 *** 숭실대학교 SW특성화대학원 교수, 교신저자 Because people's interest of the stock market has been increased with the development of economy, a lot of studies have been going to predict fluctuation of stock prices. Latterly many studies have been made using scientific and technological method among the various forecasting method, and also data using for study are becoming diverse. So, in this paper we propose stock prices prediction models using sentiment analysis and machine learning based on news articles and SNS data to improve the accuracy of prediction of stock prices. Stock prices prediction models that we propose are generated through the four-step process that contain data collection, sentiment dictionary construction, sentiment analysis, and machine learning. The data have been collected to target newspapers related to economy in the case of news article and to target twitter in the case of SNS data. Sentiment dictionary was built using news articles among the collected data, and we utilize it to process sentiment analysis. In machine learning phase, we generate prediction models using various techniques of classification and the data that was made through sentiment analysis. After generating prediction models, we conducted 10-fold cross-validation to measure the performance of they. The experimental result showed that accuracy is over 80% in a number of ways and F1 score is closer to 0.8. The result can be seen as significantly enhanced result compared with conventional researches utilizing opinion mining or data mining techniques.

Keyword Analysis of Arboretums and Botanical Gardens Using Social Big Data

“…This is used as a tool to more quickly approach technological development and customer needs by analyzing user consciousness, tendencies and emotions based on collected data and obtaining objective information (Chang, 2015). Moreover, social big data is used actively in various fields such as verification of diplomatic tools (Choi and Kim, 2016), image assessment (Hong and Oh, 2016), public relations strategies (Lee et al, 2015;Oh et al, 2015), analysis of stock prices (Kim et al, 2014) (Kang et al, 2015), prediction of stock price fluctuations (Kim et al, 2014), fashion marketing with analysis on user opinions (Lee et al, 2014), etc.…”

Prediction of Stock Value using Pattern Matching Algorithm based on Deep Learning

“…Dong-Young Kim et al have used SNS and news articles through the Internet that include economic information and stock information in modern society in other to the research [14]. They searched for relevant keywords in articles and SNS, and judged positive or negative by using deep learning in articles and SNS, and predicted the rise and fall.…”

User Musical Taste Prediction Technique Using Music Metadata and Features

“…Bayesian Classifier is a classifier that predicts the probability that a given set of attributes belong to a certain class based on Bayesian theory, while the Bayesian Network can express a subordinate relationship where the subset of the set of properties combining the graphic theory with Bayesian classifier [16]. Random Forest algorithm was first proposed by Ho, et al [17]. It demonstrated operation of the algorithm by "Law of large numbers".…”