A Mixed-Methods Analysis of Western and Hong Kongbased Reporting on the 20192020 Protests

We apply statistical techniques from natural language processing to Western and Hong Kongbased English language newspaper articles that discuss the 20192020 Hong Kong protests of the Anti-Extradition Law Amendment Bill Movement. Topic modeling detects central themes of the reporting and shows the differing agendas toward \textitonecountrytwosystems. Embedding-based usage shift (at the word level) and sentiment analysis (at the document level) both support that Hong Kongbased reporting is more negative and more emotionally charged. A two-way test shows that while July 1, 2019 is a turning point for media portrayal, the differences between western- and Hong Kongbased reporting did not magnify when the protests began; rather, they already existed. Taken together, these findings clarify how the portrayal of activism in Hong Kong evolved throughout the Movement.