Chen, Yixin (Tongji University), Yang, Chao (Tongji University)

Semantic-Enhanced Micro-Chain Modeling for Identifying Commuting Behavior Complexity

Scheduled for presentation during the Regular Session "S36a-Behavior Modeling and Decision-Making in Traffic Systems" (FR-LM-T36), Friday, November 21, 2025, 10:50−11:10, Surfers Paradise 3

2025 IEEE 28th International Conference on Intelligent Transportation Systems (ITSC), November 18-21, 2025, Gold Coast, Australia

This information is tentative and subject to change. Compiled on October 18, 2025

Abstract

Understanding commuting complexity is essential for effective urban mobility management, yet traditional studies often overlook the sequential and temporal dynamics embedded within daily commuting behaviors. This paper proposes a semantic-enhanced framework for modeling commuting micro-chains by integrating structured activity sequences and key temporal anchors. Each commuting chain is represented through Word2Vec-based activity embeddings, normalized commuting times, and Smooth Inverse Frequency (SIF)-based chain-level vectors. Clustering analysis identifies four distinct commuting patterns among Shanghai residents: standard, dual-escort, post-work extension, and front-loaded. Further analysis reveals that household structure—specifically the presence of children, elderly members, and the number of employed individuals—significantly shapes commuting complexity by influencing the embedding and timing of additional activities. By capturing behavioral nuances and linking commuting structures to social and family contexts, this paper provides behavioral insights that inform transportation demand management, peak-hour congestion mitigation, and the design of commuter support strategies in complex urban environments.