Using semantic signatures for social sensing in Urban environments

The term social sensing describes crowd-sourcing techniques and applications that make use of sensors that are closely attached to humans (e.g., as parts of smartphones) and are either directly or indirectly used to provide sensor observations at a high spatial and temporal resolution. In contrast to typical volunteered geographic information applications which rely on the conscious and active contribution of information, most social sensing happens on-the-go, that is, as by-product of human behavior and interaction with technology. Social Sensing has great potential for many applications in urban planning, transportation, crime prevention, health, and so on. In this paper, we focus on a technique called semantic signatures to extract and share high-dimensional data about places. Such semantic signatures reveal how people interact with their environment such as the times they visit places of a certain type (e.g., Winery), how they communicate about such places, and how these places are distributed throughout space. We will provide an overview of signatures, methods to extract them, and highlight examples for their usage from previous work ranging from location privacy and the extraction of regions to reverse geocoding.