AI-Powered Community Insights for Strategic Physical Transportation Infrastructure Management

Details

• Creators:
  Kennebeck, Kathryn A. ; Smetana, Mason ; Sukharev, Igor ; Khazanovich, Lev
• Corporate Creators:
  University of Pittsburgh ; Morgan State University. Safety and Mobility Advancements Regional Transportation and Economics Research Center
• Corporate Contributors:
  United States. Department of Transportation. University Transportation Centers (UTC) Program ; United States. Department of Transportation. Office of the Assistant Secretary for Research and Technology
• Subject/TRT Terms:
  Artificial Intelligence Asset Management Community Action Programs Decision Making Digital Infrastructure Pavement Condition Pedestrian Safety Strategic Planning Transportation Planning Transportation System Management
• Publication/ Report Number:
  SM09
• Resource Type:
  Tech Report
• Geographical Coverage:
  United States ; Pennsylvania
• Edition:
  Final Report
• Corporate Publisher:
  Morgan State University. Safety and Mobility Advancements Regional Transportation and Economics Research Center
• Abstract:
  This study examines how community feedback can inform transportation asset management, a field that has traditionally relied on physical condition metrics such as pavement age and roughness. Using 925 public comments collected by the Southwestern Pennsylvania Commission, the study applies a semi-automated workflow combining generative AI, natural language processing, and topic modeling to transform unstructured feedback into actionable themes. The comments were geolocated, linked to census tract income data, and analyzed with BERTopic to identify recurring concerns. Of the 925 comments, 864 were successfully geolocated and used in the tract-level analysis. The analysis produced 14 thematic clusters organized into three broad categories: Physical Infrastructure, Traffic Flow and Transit, and Non-Motorized User Safety. Approximately 30% of the comments focused directly on physical infrastructure concerns, including pavement condition, roadway design, and repair needs. A comparison with International Roughness Index data shows that community sentiment complements traditional performance measures by capturing concerns not visible in engineering metrics alone. The results also indicate differences in the type and urgency of concerns across census tracts. Overall, this study demonstrates that AI-assisted analysis can help transportation agencies process public input at scale and integrate community priorities more effectively into infrastructure decision-making.
• Format:
  PDF
• Funding:
  69A3552348303
• Collection(s):
  University Transportation Centers
• Main Document Checksum:
  urn:sha-512:f086b36a0a4e258134d748405e50897d9b37201edf147431cbb223f74b788a55b4fd1f2839084491f71d45627e2cacad4fb227d45f6603126225348a464175ea
• Download URL:
  https://rosap.ntl.bts.gov/view/dot/92774/dot_92774_DS1.pdf
• File Type:
  [PDF - 2.53 MB ]