Large Language Models for Spatial Trajectory Patterns Mining

TL;DR

This paper evaluates the effectiveness of large language models like GPT-4 and Claude-2 in detecting anomalies in human spatial trajectories, highlighting their potential and limitations in mobility behavior analysis.

Contribution

It empirically assesses LLMs for anomaly detection in mobility data, demonstrating their capabilities and the benefits of contextual clues for improved performance.

Findings

LLMs can reasonably detect anomalies without specific cues.

Providing contextual clues enhances detection accuracy.

LLMs can generate explanations, improving transparency.

Abstract

Identifying anomalous human spatial trajectory patterns can indicate dynamic changes in mobility behavior with applications in domains like infectious disease monitoring and elderly care. Recent advancements in large language models (LLMs) have demonstrated their ability to reason in a manner akin to humans. This presents significant potential for analyzing temporal patterns in human mobility. In this paper, we conduct empirical studies to assess the capabilities of leading LLMs like GPT-4 and Claude-2 in detecting anomalous behaviors from mobility data, by comparing to specialized methods. Our key findings demonstrate that LLMs can attain reasonable anomaly detection performance even without any specific cues. In addition, providing contextual clues about potential irregularities could further enhances their prediction efficacy. Moreover, LLMs can provide reasonable explanations for their judgments, thereby improving transparency. Our work provides insights on the strengths and limitations of LLMs for human spatial trajectory analysis.