The invention relates to a city domain knowledge detection system and method based on an LDA topic model. The city domain knowledge detection system and method are used for generating a domain knowledge report of a certain domain of a smart city. The system adopts a C/S architecture, adopts a modular system design, and comprises an authentication and management module, a file uploading module, a data cleaning module, an emotion analysis module, a word segmentation and part-of-speech tagging module, a keyword extraction module, a clustering module and a data transmission module. According to the invention, large-scale domain knowledge data generated in the city informatization process is fully utilized, the city domain knowledge report can be automatically generated for the user, and the invention is further applied to the fields such as traffic early warning and public opinion monitoring; the design is good, operation is stable, the system can be used without deploying the environment,and the has high practical application value. The modules are updatable and replaceable, and can be suitable for maintenance, improvement and expansion which may be required in the future. Accordingto the personalized requirements of different users, each module provides customizable parameters or files, so that the system not only meets the general requirements of common users, but also meets the customization requirements of professional users.