Public Perception of China’s Low-Altitude Economy: A Text Mining and LDA Topic Modeling Approach

• 발행기관: 한국무역연구원
• 저자명: Chen Hong
• 간행물 정보: 『무역연구』제21권 제5호, 107~129쪽, 전체 23쪽
• 주제분류: 경제경영 > 무역학
• 파일형태: PDF
• 발행일자: 2025.10.30

국문 초록

Purpose – This study examines China’s low-altitude economy through the lens of social perception, addressing a key research gap by analyzing how this emerging strategic industry is understood and discussed publicly. Design/Methodology/Approach – Using text mining, we collected data from Baidu, CNKI, and Weibo (2023-2025) and applied both TF-IDF and LDA topic modeling to identify key themes and cognitive patterns. Findings – The LDA topic modeling identifies three core themes shaping public discourse: (1) Industrial Ecosystem and Policy System, emphasizing top-level design and institutional support; (2) Technological Innovation and Key Breakthroughs, focusing on critical technologies such as batteries and artificial intelligence; and (3) Regional Practices and Application Scenarios, reflecting diverse commercialization efforts across different locales. Together, these themes form a coherent cognitive framework that spans macro-level strategy to micro-level implementation. Research Implications – From a managerial and policy perspective, this study offers empirical support for designing region-specific strategies and helps businesses better navigate market dynamics. For the international community—particularly countries actively developing their own low-altitude economies—this research presents a compelling “Chinese case” of nurturing an emerging industrial ecosystem under strong policy guidance. It highlights the dynamic interplay between policy intervention, technological advancement, and social perception, offering valuable comparative insights for global practitioners and policymakers.

목차

Ⅰ. Introduction

Ⅱ. Theoretical Background and Conceptual Framework

Ⅲ. Methodology

Ⅳ. Results and Discusion

Ⅴ. Conclusion

References

키워드

Low-Altitude Economy Text Mining TF-IDF Analysis LDA Topic Modeling