Evaluating Online Public Sentiments towards China: A Case Study of English and Chinese Twitter Discourse during the 2019 Chinese National Day

Abstract: As the Internet gradually penetrates into people's daily lives and empowers everyone to demonstrate and exchange opinions and sentiments online, individual citizens are increasingly participating in the agenda-setting of public affairs and the design and implementation of official policies. The current study describes an approach to analyze online public sentiments using social media data and provides an example of Twitter discourse during the 2019 Chinese National Day. Over 300,000 tweets were collected between Sept 30 and Oct 3, and a hybrid method of SVM and dictionary was applied to evaluate the sentiments of the collected tweets. This method avoids complex structures while yielding an average accuracy of over 96% in most classifiers used in the study. The results indicate alignment between the time of National Day celebration activities and the expressed sentiments revealed in both English and Chinese tweets, although the sentiments of the two languages tend to be in different directions. The sentiment of tweets also diverges from nation to nation, but is generally consistent with the country's official relations with China to varying degrees. The linguistic features of the tweets suggest different concerns for Twitter users who have different sentiments towards China. At last, possible directions for further studies are indicated.