Social Pattern Discovery for GPS Datasets

Abstract

This work introduces a method to analyze human mobility and social interactions, highlighting the use of geohash codes for spatial clustering and the identification of social encounters with and without time constraints. Our approach uncovers ”followers” by tracking how people move to subsequent geohashes within a specific time interval, revealing patterns of coordinated mobility. Our analysis includes the construction of a social graph visualizing individual connections. Additionally, we discover significant data duplication within the applied dataset (Geolife by Microsoft Research Asia), leading to a reassessment of the frequency of social interactions. This result underscores the importance of data integrity in geospatial analysis, contributing to the broader field of human mobility research by demonstrating a novel method for extracting meaningful insights from complex mobility data.

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 — 2 citations exist upstream.

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