Community-in-The-loop: Creating Artificial Process Intelligence for Co-production of City Service

Abstract

Communities have first-hand knowledge about community issues. This study aims to improve the efficiency of social-Technical problem-solving by proposing the concept of "artificial process intelligence,"based on the theories of socio-Technical decision-making. The technical challenges addressed were channeling the communication between the internal-facing and external-facing 311 categorizations. Accordingly, deep learning models were trained on data from Kansas City's 311 system: (1) Bidirectional Encoder Representations from Transformers (BERT) based classification models that can predict the internal-facing 311 service categories and the city departments that handle the issue; (2) the Balanced Latent Dirichlet Allocation (LDA) and BERT clustering (BLBC) model that inductively summarizes residents' complaints and maps the main themes to the internal-facing 311 service categories; (3) a regression time series model that can predict response and completion time. Our case study demonstrated that these models could provide the information needed for reciprocal communication, city service planning, and community envisioning. Future studies should explore interface design like a chatbot and conduct more research on the acceptance and diffusion of AI-Assisted 311 systems.