Exploring the potential of phone call data to characterize the relationship between social network and travel behavior

Abstract

Social network contacts have significant influence on individual travel behavior. However, transport models rarely consider social interaction. One of the reasons is the difficulty to properly model social influence based on the limited data available. Nonconventional, passively collected data sources, such as Twitter, Facebook or mobile phones, provide large amounts of data containing both social interaction and spatiotemporal information. The analysis of such data opens an opportunity to better understand the influence of social networks on travel behavior. The main objective of this paper is to examine the relationship between travel behavior and social networks using mobile phone data. A huge dataset containing billions of registers has been used for this study. The paper analyzes the nature of co-location events and frequent locations shared by social network contacts, aiming not only to provide understanding on why users share certain locations, but also to quantify the degree in which the different types of locations are shared. Locations have been classified as frequent (home, work and other) and non-frequent. A novel approach to identify co-location events based on the intersection of users' mobility models has been proposed. Results show that other locations different from home and work are frequently associated to social interaction. Additionally, the importance of non-frequent locations in co-location events is shown. Finally, the potential application of the data analysis results to improve activity-based transport models and assess transport policies is discussed

Big Data y nuevas geografías: la huella digital de las actividades humanas

“…Incluso es posible identificar la convergencia espacio-temporal de individuos con datos de telefonía móvil: cuando dos personas que intercambian llamadas telefónicas se encuentran al mismo tiempo en el mismo lugar se puede asumir que se han encontrado (Picornell, 2015). Los resultados se pueden obtener de forma mucho más rápida y con menor coste que si se realizan encuestas, si bien la información obtenida es menos rica y la localización de los orígenes y destinos resulta no demasiado precisa (basada simplemente en polígonos de Voronoi en torno a las antenas de telefonía).…”

Analysis of travel activity determinants using robust statistics

“…These decisions are also influenced by level of comfort, attitudinal traits, daytime, household (family) arrangements or neighborhood properties. In addition, it is likely that with a growing amount of substantially more complex data sets collected by emerging techniques and technologies (Axhausen 2008;Hasan et al 2013;MacFarlane 2014;Wu et al 2014;Soora 2014;Picornell et al 2015;Huang and Wong 2016) and with demand for deeper insights from these novel data resources, the role of outliers becomes critical. With it the need for robust techniques becomes even greater.…”

Social Networks, Big Data and Transport Planning

“…On the other hand, they have some limitations: lack of accompanying context in the data; informal nature of textual content; scarce location related information; need of periodic monitoring and enhancement of the system. Characteristics of social network Big Data can also be inferred from wi-fi connections (Sapiezynski et al, 2015), and cell phones traces like Call Detail Records (CDR): Eagle et al (2009), Zhang andDantu (2010), Calabrese et al (2011), Cho et al (2011), Phithakkitnukoon et al (2012, Chen and Mei (2014), Toole et al (2015), Picornell et al (2015).…”

“…Additionally, Call Detail Records (CDR) are being used to extract information to infer characteristics of trips and activities and of social networks interactions (González et al, 2008;Picornell et al, 2015, Toole, 2015.…”