This project aims to establish Hong Kong as a leading global centre for Cross-Cultural Analytics, an emerging field at the intersection of data science and cultural studies. Focusing on the influence of Chinese culture on Europe and the Americas between 1550 and 1900, the project will apply large-scale data analysis to historical texts and translations using advanced Natural Language Processing techniques, including Large Language Models and Knowledge Graphs. Leveraging CUHK’s exceptional rare book collections alongside major public-domain resources, the team will develop a high-quality textual corpus for intertextual analysis. In the long term, the project envisions the establishment of a permanent Cross-Cultural Analytics research centre at CUHK to advance international collaboration and postgraduate training.
