Towards rich mobile phone datasets: Lausanne data collection campaign

Abstract

Abstract—Mobile phones have recently been used to collect large-scale continuous data about human behavior. In a paradigm known as people centric sensing, users are not only the carriers of sensing devices, but also the sources and consumers of sensed events. This paper describes a data collection campaign wherein Nokia N95 phones are allocated to a heterogeneous sample of nearly 170 participants from Lausanne, a mid-tier city in Switzerland, to be used over a period of one year. The data collection software runs on the background of the phones in a non-intrusive manner, yielding data on modalities such as social interaction and spatial behavior. The main motivations for organizing a new campaign on top of the ones that have been successfully conducted in the past are the following: First, in comparison to the Reality Mining data, generated in 2004-2005, the present data set is expected to provide a richer means to study location attributes, in particular, because today’s mobile phones are more powerful and equipped with more sensors. Second, we aim to recruit a heterogeneous set of participants, comprising family and leisure related social networks in addition to organizationally driven ones. This paper provides a methodological description of the project and shows the potential of the resulting data set in terms of illuminating multiple aspects of human behavior. I.