CausalMob: Causal Human Mobility Prediction with LLMs-derived Human Intentions toward Public Events

TL;DR

CausalMob leverages large language models to extract human intentions from news, integrating causal inference into mobility prediction to improve accuracy amid public events.

Contribution

The paper introduces a novel causality-augmented model that combines LLM-derived intentions with causal inference for human mobility prediction.

Findings

Outperforms state-of-the-art mobility prediction models

Effectively captures causal impact of public events on mobility

Utilizes large-scale real-world data for validation

Abstract

Large-scale human mobility exhibits spatial and temporal patterns that can assist policymakers in decision making. Although traditional prediction models attempt to capture these patterns, they often interfered by non-periodic public events, such as disasters and occasional celebrations. Since regular human mobility patterns are heavily affected by these events, estimating their causal effects is critical to accurate mobility predictions. Although news articles provide unique perspectives on these events in an unstructured format, processing is a challenge. In this study, we propose a causality-augmented prediction model, called CausalMob, to analyze the causal effects of public events. We first utilize large language models (LLMs) to extract human intentions from news articles and transform them into features that act as causal treatments. Next, the model learns representations of spatio-temporal regional covariates from multiple data sources to serve as confounders for causal inference. Finally, we present a causal effect estimation framework to ensure event features remain independent of confounders during prediction. Based on large-scale real-world data, the experimental results show that the proposed model excels in human mobility prediction, outperforming state-of-the-art models.