Mapping the spatial-temporal evolution of imagery in Tang poetry: a computer vision and GIS-based approach

Abstract

This study uses computer analysis and mapping technology to examine the changes in the locations and times mentioned in poetry images from the Tang Dynasty (618–907 CE). Tang poetry from this era of Chinese history contains a wealth of cultural and geographic details that are suitable for computer analysis. Using tools for location mapping and automatic image sorting, we examined 2,800 poems written by 485 poets. With an accuracy of 89% for natural images, 85% for cultural images, and 82% for emotional images, the computer vision system produced good results. Three distinct regional groups — centered on northwest political areas, central cultural corridors, and southern literary regions — were identified through the successful mapping of 1,247 location mentions across Tang Dynasty China using geographic analysis. Time analysis revealed the distinct shift in poetic activity from northwestern centers to southern regions, centered by the An Lushan Rebellion (755-763 CE). In the Late Tang analysis, the lines of separation show, with some degree of real evidence, matching the recorded population changes affecting large populations. This method gives digital humanities researchers a tool for constructing number-based frameworks that are founded in accepted literary history views. These findings furnish practical needs in matters of cultural heritage protection and in educational programs linking literature with historical geography.