True lies in geospatial big data: detecting location spoofing in social media

Abstract

Location spoofing refers to the act of intentionally falsifying one’s actual locational information. The proliferation of location spoofing in recent years has stirred debate about the reliability and convenience of user-generated geospatial contents and the use of location spoofing as an effective countermeasure to protect individual geo-privacy and national security. However, these polarized views do not contribute to a holistic understanding of location spoofing. As of today, we still lack a robust method for detecting location spoofing and comprehending its multifaceted implications. The goal of this article is to develop a quantitative approach for detecting location spoofing and a qualitative approach for probing the possible motivations of this growing practice and its inherent uncertainties. We tested our Bayesian time geographic approach for detection using millions of geo-tagged tweets – a major source of big data for studying the spatial-temporal patterns of human activities. Our results indicate that the proposed approach can successfully detect certain types of location spoofing and more research is needed about the detection and implications of location spoofing in the age of wide-spread fake news. Rather than simply dismissing location spoofing as a technical nuisance, this article calls the GIScience community to confront this thorny issue head-on, especially when any arguments or policies are drawn from geospatial big data. Only then can we promote more effective and trustworthy uses of geospatial big data in society at large.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 66 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.