Multi-perspective perception of city image in Shanghai via massive short videos

Abstract

The concept of city image plays a pivotal role in urban branding, serving as a strategic tool for promoting sustainable urban development. A city’s image not only shapes its identity but also enhances its global competitiveness, attracting tourism, investment, and new residents. Traditional media such as newspapers and television offer limited perspectives on city image, whereas emerging platforms like short video apps provide richer and more diverse insights. Nevertheless, existing studies remain dominated by traditional media analysis, with insufficient examination of how short video platforms represent the spatial, landscape, social, and emotional dimensions of a city’s image. This study proposed a novel approach by leveraging the diverse and extensive short video data from Douyin to thoroughly deconstruct Shanghai’s comprehensive city image. We constructed a geotagged short video database, categorizing landscape and social images based on visual features and assessing emotional tones through audio-text analysis. The findings revealed distinct spatial patterns, with core areas highly concentrated and peripheral areas more dispersed. The analysis further identified nine core image areas, three major development axes, and ten prominent zones that defined Shanghai’s unique geographic and cultural identity. This approach could provide a quantitative characterization of city image, highlighting the potential for improved public space design and enhanced citizen engagement through short videos. Moreover, these results underscored the significant role of social media platforms, especially short video apps, in shaping public perception of cities. Such insights could also offer new perspectives for city image research and valuable guidance for urban planning and branding strategies.