Abstract
A set of 125 tweets about North Korea’s Supreme Leader Kim Jong-Un by President Trump from 2013 to 2018 are analysed by means of the data mining technique, sentiment analysis. The intention is to explore the contents and sentiments of the messages contained, the degree to which they differ, and their implications about President Trump’s understanding and approach to international diplomacy. The results suggest a predominantly positive emotion in relation to tweets about North Korea, despite the use of questionable nicknames such as “Little Rocket Man”. A comparison is made between the tweets on North Korea and climate change, madefrom 2011–2015, as Trump has tweeted many times on both issues. It is interesting to find that Trump’s tweets on North Korea have significantly higher positive polarity scores than his tweets on climate change.
Highlights
A series of 125 tweets by President Trump on the topic of North Korea’s Supreme Leader Kim Jong-Un are analysed by means of textual analysis using data mining techniques
We decided to apply the R package ’sentiment’, which distinguishes between five different emotions, namely joy, sadness, anger, fear and surprise
Ignoring the ’unknown’ category, the predominant emotion recognised in Figure 1 is ’joy’, which accounts for 14.4 per cent of the total, followed by ’sadness’ at 3.2 percent. ’Anger’ and ’fear’ both account for 1.6 percent, Sustainability 2018, 10, 2310 and ’surprise’ accounts for 0.8 per cent. 78.4 per cent of the tweets are not classified, but 14.4 per cent is classified as being ’joy’, which is a positive emotion
Summary
A series of 125 tweets by President Trump on the topic of North Korea’s Supreme Leader Kim Jong-Un are analysed by means of textual analysis using data mining techniques. There are two broad approaches to text mining and document analysis for extracting sentiment: the lexicon based approach and the text classification approach The former involves using the semantic orientation of words or phrases in the document to calculate the orientation of the document. There are many different forms of sentiment analysis, but many use the same basic approach They begin by constructing a list of words or dictionary associated with different emotions, count the number of positive and negative words in a given text, and analyse the mix of positive and negative words to assess the general emotional tenor of the text. In our analysis we have used the inbuilt lexicon in the ’sentiment’ package This means we can compare our results with previous analyses we have undertaken using the same method. We preferred to have consistency in the series of analyses we are undertaking using this method
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
