Sentiment analysis of tweet content on Hurricane Dorian: Sensemaking in digital journalistic inquiry ecology

Abstract

Twitter is a powerful digital journalistic instrument and evidence shows journalists were transferring authority to Twitter. With journalistic information ecology becoming imbalanced, it is valuable to research how journalists may use Twitter to discover accurate and reliable information and maintain a vast overview of news events without shifting the power as the fourth estate. The purpose of this study is to provide a possible digital journalistic inquiry model to identify trending topics, distinguish reliable journalistic information while maintaining the balance of journalistic information ecology. Utilizing a large-scale dataset – 1.2 million tweets collected from Twitter API – this study executed cutting-edge network analysis and sentiment analysis to fill in the knowledge gap through a case study on Hurricane Dorian. The study found that the impact of traditional opinion leaders on information diffusion is declining. On the contrary, top in-degree centrality users play more important roles in information diffusion on Twitter. Moreover, tweets with negative polarity opinions were retweeted more. In addition, non-opinion leaders’ negatively polarized tweets were retweeted more than positively polarized ones, although it is not the same case with opinion leaders. With the change of journalistic ecology, identifying top in-degree centrality users and examining their tweets will provide useful resources for journalists to identify keywords, trending themes and predict how likely a topic may interest audience based on degree of polarity and number of retweets on Twitter. The results provide useful patterns for journalists to follow in sensemaking tasks in digital journalistic inquiry.