Graph-Structured Trajectory Extraction from Travelogues

TL;DR

This paper introduces a graph-based method for extracting human movement trajectories from travelogues, effectively capturing geographic hierarchy and temporal order, and provides a benchmark dataset for this task.

Contribution

It proposes a novel graph representation for trajectory extraction that preserves geographic hierarchy and temporal information, along with a benchmark dataset for evaluation.

Findings

Accurate prediction of visited locations and their order.

Difficulty in predicting hierarchical geographic relations.

Benchmark dataset enables standardized evaluation.

Abstract

Previous studies on sequence-based extraction of human movement trajectories have an issue of inadequate trajectory representation. Specifically, a pair of locations may not be lined up in a sequence especially when one location includes the other geographically. In this study, we propose a graph representation that retains information on the geographic hierarchy as well as the temporal order of visited locations, and have constructed a benchmark dataset for graph-structured trajectory extraction. The experiments with our baselines have demonstrated that it is possible to accurately predict visited locations and the order among them, but it remains a challenge to predict the hierarchical relations.