叶光辉 毕崇武

摘 要：[目的/决义]基于标签语义挖掘的城市画像是表达公众认知视角下城市多维特征的结构视图，其计算与应用研究可为城市治理中的交互式服务提供有效的数据支撑和评测尺度。[方法/过程]随着城市所处技术环境的变迁，城市画像研究可划分为3个序贯相连的阶段：传统社会学阶段是萌芽期，此时城市画像研究逐步由实体层面的认知分析拓展到心理层面的认知分析;社会化标签的多维分析是过渡期，为后续以标签资源为基础的研究提供了多角度分析的路径;自媒体时代研究是拓展期，强调运用机器学习等智能方法从大规模标签资源中挖掘公众认知。[结果/结论]各阶段的研究成果将有效拓展标签利用场景及理论方法，系统构建城市画像计算与应用范式提供参考。

关键词：社会化标签;城市画像;语义挖掘;结构视图;位置数据

DOI：10.3969/j.issn.1008-0821.2021.02.017

〔中图分类号〕G203 〔文献标识码〕A 〔文章编号〕1008-0821（2021）02-0162-06

Abstract：[Purpose/Significance]The city profile based on tags semantic mining is a structural view of urban multidimensional features from the perspective of public cognition，the study of its calculation and application can provide effective data support and evaluation criteria for interactive services in urban governance.[Method/Process]According to the change of the technical environment in which the city is located，the study of urban portraits can be divided into three sequential stages as follows：the traditional sociological analysis is the germination stage.At this time，the urban portrait study was gradually extended from the cognitive analysis at the substantive level to the cognitive analysis at the psychological level;The multidimensional analysis of socialized tags was a transitional period that provides a multi-angle analysis path for subsequent research based on tag resources;Research in the media era was an extended period，emphasizing the use of intelligent methods such as machine learning to mine public perception from large-scale tag resources.[Pesult/Conclusion]The research results at each stage would effectively expand the label utilization scenarios and theoretical methods，and provide a reference for systematically constructing urban image calculation and application paradigms.

Key words：social tags;city profile;semantic mining;structural view;location data

當前许多智慧城市建设项目主要关注城市基础设施布局，着力通过新一代信息技术来提升城市硬件的智能化程度，但随着智慧城市建设热度的不断上升，城市间基础设施的差距正在逐步缩小，“如何培育城市形象，改善公众印象”已成为新时期城市智慧化管理和服务的焦点议题。

随着移动网络和政务社交媒体的融合发展，面向公众的交互式服务平台越来越多，它们正逐步发展成为公众“连接政务”的重要窗口。据中国互联网络信息……