Evaluating Online Public Sentiments towards China: A Case Study of English and Chinese Twitter Discourse during the 2019 Chinese National Day
share
This project describes an approach to analyze public sentiments with social media data and provides an example of the Twitter discourse during the 2019 Chinese National Day. The objective is to study the online discourse towards China with NLP algorithms, as well as observe the temporal, spatial and lingual characteristics of the expressed sentiments. Firstly, the Twitter data sets were collected between Sept 30 and Oct 3 through API and part of them were manually labeled to train the SVM. Then, a hybrid method of SVM and dictionary was applied to evaluate the sentiments of the collected tweets. After that, the tweets sentiments' time fluctuation, spatial distribution and frequently used words were given. Finally, we conclude by highlighting the possible consequences of the overall negative image of China in the English-speaking discourses and indicating future directions.
READ FULL TEXT
