Spatiotemporal Detection of Unusual Human Population Behavior Using Mobile Phone Data

Abstract

With the aim to contribute to humanitarian response to disasters and violent events, scientists have proposed the development of analytical tools that could identify emergency events in real-time, using mobile phone data. The assumption is that dramatic and discrete changes in behavior, measured with mobile phone data, will indicate extreme events. In this study, we propose an efficient system for spatiotemporal detection of behavioral anomalies from mobile phone data and compare sites with behavioral anomalies to an extensive database of emergency and non-emergency events in Rwanda. Our methodology successfully captures anomalous behavioral patterns associated with a broad range of events, from religious and official holidays to earthquakes, floods, violence against civilians and protests. Our results suggest that human behavioral responses to extreme events are complex and multi-dimensional, including extreme increases and decreases in both calling and movement behaviors. We also find significant temporal and spatial variance in responses to extreme events. Our behavioral anomaly detection system and extensive discussion of results are a significant contribution to the long-term project of creating an effective real-time event detection system with mobile phone data and we discuss the implications of our findings for future research to this end.

Detecting climate adaptation with mobile network data in Bangladesh: anomalies in communication, mobility and consumption patterns during cyclone Mahasen

“…Traditional methods for assessing cyclone impacts and human behavioral responses have well known limitations (Hallegatte and Przyluski 2010), and the anomaly detection technique applied to mobile network data presented here (building on work of Blumenstock et al 2011;Candia et al 2008;Dobra et al 2014;Kapoor et al 2010;Pawling et al 2007;Sundsøy et al 2012, andYoung et al 2014), may overcome some of these challenges, and demonstrates the potential value of mobile network data as a complement to current cyclone impact assessment tools. Specifically, the spatiotemporal distributions of anomalous usage activity could be used to improve the timeliness and cost-effectiveness of cyclone impact assessments.…”

“…Anomaly detection methods have previously been applied to mobile network data to identify unusual calling patterns after floods (Pastor-Escuredo et al 2014), and in the interest of improving the normal operation of mobile networks (Karatepe and Zeydan 2014). They have been used for anomaly detection for detecting and classifying social disturbances, like conflict and violence in datapoor circumstances (Dobra et al 2014;Young et al 2014). One study showed the diffusion of anomalous calling patterns through intimate social networks in the wake of a terrorist bombing in Oslo (Sundsøy et al 2012).…”

Assessing reliable human mobility patterns from higher order memory in mobile communications

“…Mobile data have been successfully used in a wide variety of applications, e.g. to estimate population densities and their evolution at national scales [13], to confirm social theories of behavioural adaptation [20] and to capture anomalous behavioural patterns associated with religious, catastrophic or massive social events [21]. Even more recently, the public availability of mobile phone datasets further revolutionized the field, e.g.…”

Temporal patterns of emergency calls of a metropolitan city in China

“…Yet our quantitative understanding of human calling activity under emergency circumstances [13][14][15][16][17][18][19][20], which indicates the requirements of accessing to police, fire and ambulance services, remain limited. Quantitative study of human calling dynamics under emergencies would provide helpful insights into many practical problems, such as emergency response, emergency resource allocation, urban planning and traffic management.…”

“…In order to uncover the quantitative features of human communication behavior under extreme situations, recent studies have begun to take advantage of mobile phone data to explore human behavioral patterns during anomalous events [13][14][15][16][17][18][19][20]. Previous studies have demonstrated that emergencies could trigger a dramatic increase in communication activity of the eyewitnesses [13][14][15].…”