This research develops a Generative AI framework for evaluating transportation agency resolution of public complaints and comments, addressing the challenge of siloed datasets where public feedback and agency improvement records remain disconnected and difficult to analyze collectively. Building on previous work demonstrating Large Language Model efficiency in analyzing public feedback, the study creates automated systems to identify patterns and correlations between reported concerns and documented improvements. The methodology involves collecting complementary datasets including public complaint narratives with location details and timestamps, alongside agency activity records documenting improvement efforts and outcomes. Natural Language Processing techniques will clean and standardize unstructured text data, while machine learning algorithms generate text embeddings and cluster recurring themes in complaints and agency responses. Large Language Models will perform semantic matching to quantify correlations between complaints and improvements, classify complaint-response pairs by resolution status, and conduct gap analysis identifying unaddressed service issues. Evaluation metrics include response time quantification, resolution effectiveness assessment, sentiment analysis of follow-up feedback, and identification of systemic gaps in agency responsiveness. The research produces a visual dashboard displaying complaint trends, response patterns, and automated reports providing actionable insights for transportation agencies and policymakers.
Universities Involved
University of Pittsburgh
Principal Investigators
Lev Khazanovich,
Aleksandar Stevanovic
Expected Research Outcomes & Impacts
The application of this research will transform transportation agency complaint resolution processes by enabling systematic assessment and enhancement of service delivery effectiveness through automated data analysis. Transportation agencies will gain enhanced capabilities to evaluate how well public concerns are addressed, improving transparency and accountability in service delivery while identifying recurring infrastructure issues requiring proactive attention. Public satisfaction with transportation services will improve through more effective and timely complaint resolution enabled by data-driven decision-making processes that integrate community feedback into agency operations. Agency personnel will benefit from streamlined workflows replacing manual, labor-intensive analysis processes with automated systems that identify patterns and correlations across large datasets. Transportation planners and maintenance teams will receive targeted recommendations for improving service strategies based on quantitative assessment of complaint resolution effectiveness and identification of persistent service challenges. Communities will experience more responsive public services as agencies gain tools to prioritize maintenance and improvement projects aligned with public- informed feedback and evidence-based decision-making. Long-term impacts include enhanced resource allocation efficiency through improved understanding of complaint-response relationships, supporting cost-effective transportation system improvements. The prototype tool will enable broader technology transfer across transportation agencies, facilitating similar analyses using existing data streams and supporting digital transformation in public service delivery. Academic institutions will benefit from expanded research capacity in AI applications for transportation management, while PhD students will gain valuable experience in developing and implementing generative AI solutions for complex public administration challenges.
Subject Areas
Artificial Intelligence, Public Policy