Social Networks and Digital Phenotyping

Abstract

[evdate 2015-09-08] IAS seminar series on big data. Title from opening screen.

Abstract: Research in the speaker's lab focuses on statistical network science and digital phenotyping. Applications of the former field to social networks have benefitted from the ubiquity of cell phones, whereas the latter field has been enabled by smartphones. The speaker will talk about some of their work that uses anonymized cell phone call records to investigate the structure of large-scale social networks and to study population dynamics at a massive gathering involving millions of people. The group has coined the term digital phenotyping to refer to the moment -by-moment quantification of the individual-level human phenotype, in situ, using data from digital devices. Using a dedicated smartphone application, the group collects active data (surveys, voice samples, etc.) and passive data (spatial location, social engagement, etc.) from consenting subjects and analyzes them using tools of statistical learning. The speaker will discuss some of their early results in this area, discuss the connection to social networks, and conjecture about the potential of digital phenotyping for the study of health in the near future.

Prof Jukka-Pekka Onnela obtained his MS and PhD in Network Science from Helsinki University of Technology (which has become Aalto University since 2010) in 2002 and 2006 respectively. He then completed two postdoctoral fellowships in Network Science at the University of Oxford and Harvard Medical School. In 2011, he started his faculty position at Harvard T.H. Chan School of Public Health and is currently an Assistant Professor of Biostatistics.

Prof Onnela’s research activities involve two categories: Network Science (the study of network representations of physical, biological, and social phenomena) and Digital Phenotyping (the moment-by-moment quantification of the individual-level human phenotype using data from digital devices). He has been an editorial board member of European Physical Journal (EPJ) Data Science since 2011. In 2013, he was awarded the US National Institutes of Health (NIH) Director's New Innovator Award for his Digital Phenotyping research.

Duration: 97 min.