arXiv:2608.05841 · v3
SnapScope: A Platform for City-Scale Collection and Exploration of Public Snap Map Data
摘要
Snapchat's Snap Map is an ephemeral stream of geotagged public video and image stories. The platform documents no API for it, no prior work describes a reproducible way to collect it at city scale, and no tool exists for exploring what is collected. We present SnapScope, which pairs a collection back end with a web front end. The back end builds a geographic query grid, sweeps it on a schedule, and deduplicates at ingestion; the front end supports scraper management, interactive exploration, neighborhood comparison, and export. Deployed over Riyadh, Saudi Arabia, it collected 515,364 unique public snaps across 23 days (17 September-9 October 2024) on a 1 km grid of 2,740 query points. A saturation probe over 21 consecutive runs found 94.8% of returned observations already stored, indicating that successive passes mostly return already-captured content. We release a privacy-safe aggregate dataset of tile-level hourly counts under CC BY 4.0. The platform is city-agnostic: redeployment requires only new grid coordinates and boundary polygons.
作者备注：6 pages, 6 figures, 1 table. Accepted at the 6th International Multi-Conference on Artificial Intelligence Technology (MCAIT 2026)