SeMob: Semantic Synthesis for Dynamic Urban Mobility Prediction

ACL ARR 2025 May Submission2414 Authors

Abstract:

Human mobility prediction is vital for urban services, but often fails to account for abrupt changes from external events. Existing spatiotemporal models struggle to leverage textual descriptions detailing these events. We propose SeMob, an LLM-powered semantic synthesis pipeline for dynamic mobility prediction.
Specifically, SeMob employs a multi-agent framework where LLM-based agents automatically extract and reason about spatiotemporally related text from complex online texts. Fine-grained relevant contexts are then incorporated with spatiotemporal data through an innovative progressive fusion architecture proposed. The rich pre-trained event prior contributes enriched insights about event-driven prediction, and hence results in a more aligned forecasting model.
Evaluated on a dataset constructed through our pipeline, SeMob achieves maximal reductions of 13.92% in MAE and 11.12% in RMSE compared to the spatiotemporal model. Notably, the framework exhibits pronounced superiority especially within spatiotemporal regions close to an event's location and time of occurrence.

Paper Type: Long

Research Area: NLP Applications

Research Area Keywords: multimodal applications

Languages Studied: English

Submission Number: 2414