A social sensing approach for everyday urban problem-handling with the 12345-complaint hotline data

The emergence of various types of everyday urban problems poses severe challenges to the conventional top-down designed urban problem-handling protocols. Social sensing data, such as the urban problem complaint hotline records, constitute good sources for collecting bottom-up information on urban problems. Nevertheless, a partially obsolete urban problem categorization standard, a manually operated and experience-dependent workflow for problem classification and pushing, and an unoptimized problem-handling responsibility designation among the municipal departments have been impairing the sufficient utilization of the collected complaint data toward more efficient urban problem-handling performance. In this paper, based on the 12345-hotline data collected in Sanya City, China, we 1) construct an urban problem tree that presents a new and expandable classification of everyday urban problems with 7 super-types, 34 types, and 105 sub-types of events, thus complementing that in the existing National Standard which merely contains 6 types and 66 sub-types; 2) design an auto-classification algorithm for the complaint records with Natural Language Processing and Supervised Machine Learning methods, which achieves an accuracy of up to 75% at the super-type level; and 3) optimize the urban problem-handling responsibility designation among the municipal departments for improved departmental function distinction and balanced workloads, which combined with the auto-classification algorithm yield a decrease of the problem pushing failure ratio from the current 73.8% to 14.6%. We integrate all the above functions in a web-based information system to establish a digital platform for practical urban problem-handling. We conclude the paper with discussions on the paper's implications of an overhaul of urban legislative and executive systems following a bottom-up paradigm and reflections on the paper's limitations and theoretical implications from a complex-system theory perspective. • An urban problem tree constructed from the “12345” Hotline is a complement to the National Standard. • Developing NLP and supervised ML algorithms for effective classification of crowd-sourced hotline complaints. • Optimizing the local government structure for urban problem-handling from a bottom-up approach. • Implementing a web-based system for hotline handling which decreases the failed pushes from 73.8% to 14.6%.