Social media platforms have become an important source for the public to obtain information about smart city construction. In order to explore the current situation of the public's perception of smart city construction, text data related to smart city construction in microblogging platforms is studied. The LDA(linear Discriminant analysis） topic model is used to get the six topics of public concern, the sentiment analysis method based on sentiment dictionary is used to get the distribution of public sentiment tendency towards smart city construction, and the negative text is visualized. The results show that the topics of public concern can be categorized into digital economy, technology application, stock market, artificial intelligence, social livelihood, and policy development, and that the public generally has a positive attitude towards smart city construction.