A Novel End-To-End Event Geolocation Method Leveraging Hyperbolic Space and Toponym Hierarchies
Yaqiong Qiao, Guojun Huang

TL;DR
This paper introduces GTOP, an end-to-end event geolocation method that leverages hyperbolic space and toponym hierarchies to improve accuracy in social data-based event detection and localization.
Contribution
It proposes a novel hyperbolic space-based model and hierarchical toponym filtering algorithms for more accurate event geolocation.
Findings
GTOP outperforms state-of-the-art baselines in experiments.
The hierarchical toponym filtering reduces noise in geolocation.
Hyperbolic space modeling enhances node feature learning.
Abstract
Timely detection and geolocation of events based on social data can provide critical information for applications such as crisis response and resource allocation. However, most existing methods are greatly affected by event detection errors, leading to insufficient geolocation accuracy. To this end, this paper proposes a novel end-to-end event geolocation method (GTOP) leveraging Hyperbolic space and toponym hierarchies. Specifically, the proposed method contains one event detection module and one geolocation module. The event detection module constructs a heterogeneous information networks based on social data, and then constructs a homogeneous message graph and combines it with the text and time feature of the message to learning initial features of nodes. Node features are updated in Hyperbolic space and then fed into a classifier for event detection. To reduce the geolocation error,…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsWeb Data Mining and Analysis · Topic Modeling · Video Analysis and Summarization
