For Japan-a country that has always been described with virtually no major natural resources such as oil, gas, and coal-the Middle Eastern region has a special place in its economic and foreign policy. In 2017, 39% of Japan's energy came from oil, and 87% of Japan's imported oil came from the Middle East, predominantly Saudi Arabia and the UAE. The above facts are enough to discern the critical significance of the Middle Eastern region for Japan. For Japan to have an unhindered supply of oil and other natural resources, it is pertinent that this region remains peaceful. In this scenario, the Middle East-related articles in Japan's newspapers can help understand Japan's perspective towards the Middle East. This paper would first apply the topic modelling approach non-negative matrix factorization (NMF) on Middle East-related articles from three newspapers of Japan. After discovering crucial topics, we would utilize traditional supervised machine learning algorithms to determine the overall and topic-specific sentiments from the collected headlines. Our topic modelling results discovered that the Japanese media widely reported issues like Islamic State, the refugee crisis, the Syrian civil war, Qasem Soleimani killing, and Iran nuclear deal. Further, the news related to Saudi Arabia, Syria, and Trump garnered high negative sentiment.
All Science Journal Classification (ASJC) codes
- Information Systems
- Language and Linguistics
- Linguistics and Language
- Computer Science Applications