Traffic Urgency Model: A Novel Approach to Prioritize Complaint Texts Using Enhanced Named Entity Recognition for Bahasa Indonesia Cases

Addressing traffic complaints effectively requires a priority system capable of accommodating urgency levels based on critical factors. This study introduces the Traffic Urgency Model (TUM), which quantitatively assesses the urgency of traffic complaints by identifying and measuring key variables. The research analyzes 23,361 traffic complaint records using a redesigned Named Entity Recognition (NER) approach with specialized tags tailored to Indonesian-language complaint texts. The NER development process enhances information extraction, capturing relevant elements such as time, location, reported conditions, involved parties, and traffic-related objects, which serve as potential variables. Furthermore, the study employs a Causal Loop Diagram (CLD) to map causal relationships among variables and construct a comprehensive model structure. Variable evaluation integrates normalization techniques and weighting based on historical data and expert assessments, resulting in a data-driven model framework that supports objective prioritization in handling complaints. The findings include a new entity design for NER development to identify entities in traffic complaint texts and a novel method for managing complaint texts based on urgency levels that encompass various traffic criteria. The results demonstrate that TUM provides a more comprehensive approach by considering quantitative data and inter-variable relationships to prioritize traffic complaints with greater specificity according to urgency values.