In recent decades, the rapid development of information technology in the big data field has introduced new opportunities to explore a large amount of data available online. The Global Database of Events, Location (Language), and Tone (GDELT) is the largest, most comprehensive, and highest resolution open source database of human society that includes more than 440 million entries capturing information about events that have been covered by local, national, and international news sources since 1979 in over 100 languages. GDELT constructs a catalog of human societal-scale behavior and beliefs across all countries of the world, connecting every person, organization, location, count, theme, news source, and event across the planet into a single massive network that captures what is happening around the world, what its context is and who is involved, and how the world is feeling about it, every single day. On the other hand, the stock market prediction has also been a long-time attractive topic and is extensively studied by researchers in different fields with numerous studies of the correlation between stock market fluctuations and different data sources derived from the historical data of world major stock indices or external information from social media and news. Support Vector Machine (SVM) and Logistic Regression are two of the most widely used machine learning techniques in recent studies. The main objective of this research project is to investigate the worthiness of information derived from GDELT project in improving the accuracy of stock market trend prediction specifically for the next days' price changes. This research is based on data sets of events from GDELT database and daily prices of Bitcoin and some other stock market companies and indices from Yahoo Finance, all from March 2015 to May 2017. Then multiple different machine learning and specifically classification algorithms are applied to data sets generated, first using only features derived from historical market prices and then including more features derived from external sources, in this case, GDELT. Then the performance is evaluated for each model over a range of parameters. Finally, experimental results show that using information gained from GDELT has a direct positive impact on improving the prediction accuracy. Keywords: Machine Learning, Stock Market, GDELT, Big Data, Data Mining

学位プログラム名: 京都大学大学院思修館 / 京都大学 / 新制・課程博士 / 博士(総合学術) / 甲第24949号 / 総総博第31号 / 新制||総総||5(附属図書館) / 京都大学大学院総合生存学館総合生存学専攻 / (主査)教授 池田 裕一, 教授 IALNAZOV Dimiter Savov, 准教授 関山 健, 安橋 正人 (奈良女子大学) / 学位規則第4条第1項該当 / Doctor of Philosophy / Kyoto University / DFAM

ABSTRACT MAJID MEMARI, for the Masters of Science degree in Computer Science, presented on November 3rd, 2017 at Southern Illinois University, Carbondale, IL. Title: PREDICTING THE STOCK MARKET USING NEWS SENTIMENT ANALYSIS Major Professor: Dr. Norman Carver Big data is a term for data sets that are so large or complex that traditional data processing application software is inadequate to deal with them. GDELT is the largest, most comprehensive, and highest resolution open database ever created. It is a platform that monitors the world's news media from nearly every corner of every country in print, broadcast, and web formats, in over 100 languages, every moment of every day that stretches all the way back to January 1st, 1979, and updates daily [1]. Stock market prediction is the act of trying to determine the future value of a company stock or other financial instrument traded on an exchange. The successful prediction of a stock's future price could yield significant profit. The efficient-market hypothesis suggests that stock prices reflect all currently available information and any price changes that are not based on newly revealed information thus are inherently unpredictable [2]. On the other hand, other studies show that it is predictable. The stock market prediction has been a long-time attractive topic and is extensively studied by researchers in different fields with numerous studies of the correlation between stock market fluctuations and different data sources derived from the historical data of world major stock indices or external information from social media and news [6]. The main objective of this research is to investigate the accuracy of predicting the unseen prices of the Dow Jones Industrial Average using information derived from GDELT database. Dow Jones Industrial Average (DJIA) is a stock market index, and one of several indices created by Wall Street Journal editor and Dow Jones & Company co-founder Charles Dow. This research is based on data sets of events from GDELT database and daily prices of the DJI from Yahoo Finance, all from March 2015 to October 2017. First, multiple different classification machine learning models are applied to the generated datasets and then also applied to multiple different Ensemble methods. In statistics and machine learning, Ensemble methods use multiple learning algorithms to obtain better predictive performance than could be obtained from any of the constituent learning algorithms alone. Afterwards, performances are evaluated for each model using the optimized parameters. Finally, experimental results show that using Ensemble methods has a significant (positive) impact on improving the prediction accuracy. Keywords: Big Data, GDELT, Stock Market, Prediction, Dow Jones Index, Machine Learning, Ensemble Methods

無 / Discussions of the South China Sea maritime territorial disputes are rife with assertions that certain state actors escalate regional tensions and that it is only a matter of time before provocations trigger armed conflict. However, these claims are based primarily on incomplete evidence, inaccurate comparisons with historical conflicts, and country or individual biases. This dissertation questions these common assertions and uses empirical evidence to assess their validity. Using time-series event data from the Global Database of Events, Language, and Tone (GDELT), it analyzes (1) the relationship between state involvement and South China Sea tensions and (2) which forecast models can most accurately predict South China Sea tensions based on data from earlier time periods. For RQ1, the analyses reveal that the involvement of certain countries corresponds with significantly higher tensions in the South China Sea, that state involvement and tensions are correlated at various positive and negative lags of interest, and that these correlations go in both directions. These findings have important implications for policymakers and researchers in that they offer empirical evidence that confirms or refutes assertions suggesting that certain countries’ actions lead to escalation or deescalation. They also provide a solid foundation for future research, which could take specific countries as individual case studies to further investigate the relationships between state involvement and South China Sea tensions. Moreover, the results indicate that there may be even more interesting phenomena at play that merit attention in future research: evidence suggesting that certain countries may either contribute to lower tensions or avoid becoming involved when there are heightened tensions, and evidence that some countries may not be contributing to but instead reacting to tensions and volatility in the South China Sea. For RQ2, two of the four forecast models perform better than the four benchmark models using both datasets. These findings also have important implications for policy and research. As governments become increasingly interested in using continuously updated global databases to facilitate policy-making, the results suggest that empirical data can help to inform conclusions about trends of escalation and deescalation in the South China Sea and be used to make relevant predictions. As a first cut at the data and a pioneering approach to analyzing South China Sea tensions, the analyses and findings of this dissertation represent a significant contribution to knowledge and a foundation for future research using time-series event data to understand the relationship between state involvement and tensions and the extent to which tensions can be forecasted in the South China Sea and around the world.