We introduce a method to examine the effects of the U.S. news sentiments on Korean firms listed on the New York Stock Exchange (NYSE) when North Korea causes geopolitical risks to the South Korean economy. Stock prices are evaluated by market factors and return to their fundamental values in the long term. Nevertheless, external shocks such as geo-political and international risks often cause stock volatility. Using a semi-supervised machine learning approach, we classify negative and positive news from five major newspapers in the U.S. to scrutinize the degree of North Korean risk and its influence on the stock prices of Korean firms listed on the NYSE. We find that news related to North Korea have an impact on the stock volatility in the U.S. and Korea. We could detect the direct impact of political risk posed by North Korea on the NYSE, but it was weaker than their indirect effects through the Korean stock Market.
All Science Journal Classification (ASJC) codes
- Social Sciences(all)