Comparing global news sentiment using hesitant linguistic terms

Global policy makers need to maintain a pulse on the state of play of global governance. Advances in analytical tools, such as global news dashboards, can provide current information on changes to global sentiment. In particular, identifying unexpected shifts in sentiment following a major news event may better inform stakeholders' actions. This paper defines a methodology to evaluate global sentiment for periods before, during, and after a major event. Each period's sentiment can be derived from news articles generated by news outlets. The sentiment is expressed in terms of hesitant linguistic terms to capture the range of sentiments articulated in each article. This representation is advantageous as it permits the interpretation of sentiments without conversion to numerical values. Sentiment from each article considered is aggregated into three centralized sentiments representing periods before, during, and after a particular event. This leads to a second enhancement to existing methods where the concept of a central opinion is represented in hesitant linguistic terms. Each of these sentiments is associated with a measure of consensus indicating the degree of agreement among the articles within their corresponding periods. A real case is presented for a noteworthy event in recent history. Three thousand three hundred fifty-two articles that referenced both the World Health Organization and President Trump during the 2-week period surrounding the event are analyzed. The results show that the methodology presented can detect changes in aggregated sentiment and consensus. When compared with means of aggregation based on crisp approaches, our model is more sensitive to shifts in sentiment. This type of information can better inform policy makers about public opinion as it not only detects shifts in sentiment but also discourses among citizens.

Automated summary

Global policy makers need to monitor global governance and utilize analytical tools such as global news dashboards to provide current information on global sentiment changes, particularly by identifying unexpected shifts in sentiment following major events. This paper introduces a methodology to evaluate global sentiment before, during, and after significant events, utilizing hesitant linguistic terms to represent sentiment in news articles and aggregating them into centralized sentiments for each period. The approach is able to detect changes in aggregated sentiment and consensus, providing a more sensitive model compared to traditional crisp aggregation methods for informing policy makers about public opinion and discourse.