Bartosz Hawelka


































This email address is being protected from spambots. You need JavaScript enabled to view it.
Phone: +43 - (0)662 - 8044 - 7568
Fax: +43 - (0)662 - 8044 - 7588


Scientific profile:

Bartosz obtained a master’s degree in human geography, with aspecialization in GIS, at the Jagiellonian University in Krakow, Poland in 2009. His thesis focuses on the spatio-temporal patterns of mobile phone activities, using the example of Amsterdam city. Since 2009 he has been working in the CurrentCity Research Foundation as a data specialist. During that period Bartosz participated in different projects exploring the potential of telecom data for the real-time monitoring of population dynamics in a city.

Bartosz's research within the Doctoral College GIScience deals with the geo-spatial modeling for collective sensing. He focuses on understanding and modeling human behaviour based on diverse data sources such as telecom data or social media.

Due to Bartosz’s education and professional experience his scientific background includes: GIS&T, data mining, pattern recognition and the handling of huge databases.

For more information about Bartosz's current projects please visit the website

Research Cluster: Time and Process


PhD Thesis Topic: Collective Sensing and Human Mobility Analysis



Collective Sensing seeks to understand the collective time-space behaviour of complex systems by analysing the vast amount of anonymous digital traces that are continuously left behind while using digital networks, such as telecom and wireless networks, digital transactions, location and sensor capabilities, wired and wireless connectivity and social networks. These systems, while designed to perform a certain primary goal, capture also time-space activity of their users. Data are collected constantly and on entire communities. Since they act as probes of collective behaviour of those communities, in the thesis they are called Collective Sensing Probes (CSPs).CSPs gain increasing attention in research. The thesis focuses on human mobility, a broad field dedicated to extracting and understanding patterns that govern human movements. It considers three CSPs that relate to human mobility, specifically to the time-space dimension of mobility, in particular telecom data, social media data and bank card transactions. A significant portion of the work refers directly or indirectly to tourism and international travel.The thesis is built around two broad objectives and four research questions. Objective 1 asks for the insights and foresights on human mobility based on the CSP data. In particular, the study explores the content and representativeness of the selected probes,as well as spatial (local, global) and temporal patterns (short-, long-term) that can be derived from the CSPs, also in combination with traditional data (RQ1, 2, 3). Objective 2 focuses on methods that can be applied to, or developed for, CSP data to analyse human mobility. Existing approaches (e.g. gravity model, network analysis) are tested with the new data types and spatial scales. The thesis also proposes a new algorithm to predict individual mobility traces based on the travel history of other users of the system (RQ4).The results are presented in five research papers. P1 explores several examples of collective human behaviour based on telecom and social media data. It shows that even simple spatio-temporal analysis of CSPs and geo-visualisation methods contribute to a better understanding of urban systems and their dynamics. P2 studies international travels reflected in geo-located Twitter and compares detected patterns with traditional datasets and mobility models. It argues on the validity of this CSP as an objective, freely accessible data proxy for global mobility studies. P3 exploits bank data in the context of mobility at multiple spatial scales and validates that it has a significant potential for regional delineation. P4 studies individual mobility traces of tourists based on their telecom footprint. It proposes a new sequential learning algorithm that improves the predictability of individuals based on a large number of sequences of motion generated by many agents simultaneously. P5 combines social media data and migration statistics to study short- and long-term mobility in a global scale. It proves that a multi-layer mobility network reveals important new patterns, invisible with the analysis based on single sources.The final part of the thesis includes an outlook on an open issues and further research directions in the field of collective sensing and human mobility.

First Supervisor: Dr. Euro Beinat   Second Supervisor: Dr. Pavlos Kazakopoulos    Third Supervisor: Dr. Stanislav Sobolevsky 



Please find the list of my publications in my google scholar profile


Research Areas: Big Data, Collective Sensing, Location Based Services, Pervasive Computing, Social Media.


Presentation Hawelka Bartosz