Proliferation of GPS-enabled mobile devices has brought a plurality of location-Aware applications leveraging the location characteristics in the shared content, like photos and checkins. While these applications provide contextual and relevant information, they also assume geo-Tagged contents to be representative of the geo-bounded characteristics of location. In this paper, however, we show that the characteristics geo-Tagged contents capture about a location can vary based on the familiarity of user (sharing the content) with the location. Using a large dataset of geo-Tagged photos, we learn descriptive spatial photo characteristics and user temporal-location-familiarity to highlight unique characteristics photos capture of location, which vary significantly if taken by locals versus tourists. We then propose a ranking-Approach to find most representative photos for a given city. A user-based evaluation shows photos are more diverse and characteristic of location compared to other popular baselines while being representative of how locals and tourists would describe the city.

Image content, Locals, Location-familiarity, Retrieval, Tourists
Facebook Inc., Menlo Park, CA, USA, Futurewei Technologies Inc., Santa Clara, CA, USA
Conference on User Modeling, Adaptation and Personalization
Centrum Wiskunde & Informatica, Amsterdam, The Netherlands

Kumar, V, Bakhshi, S, Kennedy, L, & Shamma, D.A. (2017). Adaptive city characteristics: How location familiarity changes what is regionally descriptive. In UMAP 2017 - Proceedings of the 25th Conference on User Modeling, Adaptation and Personalization (pp. 131–139). doi:10.1145/3079628.3079665