Geographically Masking Addresses to Study COVID-19 Clusters

Abstract The spatial analysis of health data usually raises geoprivacy issues. But with the virulence of COVID-19, scientists and crisis managers do need to analyse the spatio-temporal distribution and spreading of the disease with spatially precise data. In particular, it is useful to locate each case on a map to identify clusters of cases in space and time. To allow such analyses with breach of geoprivacy, geomasking techniques are necessary. This paper experiments the geomasking techniques from the literature to solve this problem: masking the real address of positive cases while preserving the local cluster patterns. In particular, two different approaches based on aggregation and perturbation are adapted to the geomasking of addresses in areas with different densities of population. A new simulated crowding method is also proposed to preserve clusters as much as possible. The results show that geomasking techniques can spatially anonymize addresses while preserving clusters, and the best geomasking method depends on the use of the anonymized data.