AI-Based Predictive Civic Grievance Intelligence System
This research paper presents CivicWeave, an AI-based predictive civic grievance intelligence system designed to improve the identification, analysis, and prioritization of civic complaints. The proposed system analyzes civic complaints using their textual content, geographical locations, and submission timestamps to identify potentially related reports. It aims to help municipal authorities recognize recurring civic issues, understand complaint patterns, and identify incidents that may require greater attention. CivicWeave considers factors such as semantic similarity, geographical proximity, temporal information, complaint frequency, distinct citizen participation, citizen support, unresolved duration, and safety-related keywords to support incident analysis and priority assessment. It also incorporates a human-review mechanism through which municipal officers can review, approve, or reject suggested complaint relationships. The system is developed using React for the frontend, FastAPI for backend services, and MongoDB for data storage. It also supports optional Gemini-based text embeddings with a deterministic local fallback mechanism. The research focuses on improving civic grievance management through AI-assisted complaint analysis, incident identification, explainable prioritization, and human-centered decision-making. Keywords: CivicWeave, Civic Grievance Management, Artificial Intelligence, Complaint Analysis, Semantic Similarity, Incident Detection, Priority Assessment, Smart Cities.
Authors
- Ankita Jadhav
- Nandini Kumari
- Nupur Ramtirthkar
- Anushka Harpale
- Shashank Bholane
Publication Details
- Journal
- Zenodo (CERN European Organization for Nuclear Research)
- Published
- 2026-11-19
- DOI
- https://doi.org/10.5281/zenodo.24372881
- Primary Topic
- E-Government and Public Services
- Type
- article
- Field-Weighted Citation Impact
- 0.00