Unveiling Global Chinese Businesses Early 20th Century

Unveiling Global Chinese Businesses Early 20th Century

Presentation at the 2025 CALA Canada Annual Conference

Tang, Helen

Chinese American Librarians Association

2025-05-05

https://creativecommons.org/licenses/by/4.0/

application/pdf

eng

Text; Presentation

This presentation details a novel approach to historical data extraction and analysis. I utilized the Google Gemini API within a Python script to process a digitized directory of early 20th-century global Chinese businesses. The API performed Optical Character Recognition (OCR) on the traditional Chinese text within the PDF, extracting key business information. This extracted data was then analyzed and visualized to unveil findings revealing: (1) the geographical distribution of these businesses, displayed on an interactive world map; (2) the predominant business categories engaged in by overseas Chinese; (3) common naming conventions employed by these enterprises; and (4) linguistic patterns evident in the transliteration of foreign place names into Chinese, offering insight into early immigrant experiences and language adaptation. This methodology demonstrates the power of combining modern AI tools with historical sources to uncover hidden historical patterns.