A United Tale of Three Regions: A Century of China on Screen

This chapter examines how the film industries of Chinese mainland, Hong Kong SAR, and Taiwan, Province of China have shaped the image of China under different political, historical, and cultural contexts since the mid-twentieth century. Using film summaries from the Internet Movie Database (IMDb), it applies unsupervised machine learning methods, including the LDA topic model, Word2Vec algorithm, and sentiment analysis, to identify recurring themes, semantic patterns, and emotional tendencies in cinematic narratives. The findings show that while the three regions share cultural origins, they express distinct identities shaped by their unique social experiences and global interactions. Positioned within quantitative cultural research in the social sciences, this study highlights how computational text analysis together with social interpretation can reveal the evolution and emotional depth of cross-regional cultural identities.