In just a few years, mobile phones have emerged as the ultimate multimedia device. Smartphones allow us to take pictures, listen to music, watch videos, interact with the physical world through GPS, communicate via calls, SMS, or MMS, and browse the web. Given their ubiquity, mobile phones have become the most natural device for multimedia consumption, production, and interaction, but there is much more to it. Smartphones can constantly sense people’s location via GPS or cell tower connectivity, motion through accelerometers, proximity via Bluetooth, and communication through call and SMS logs, and thus represent the most accurate and non-intrusive current means of tracing real-life human activities. Furthermore, all this information, as never before, is being generated at massive scales. It is therefore not surprising that the understanding of personal and social behavior from mobile sensor data at large-scale, where population of cell phone users are analyzed both as individuals or groups over possibly long periods of time, has emerged as a frontier domain in computing. This research domain has been recognized as having high potential impact in real life, whether it is our personal life, business, or government. With appropriate privacy-protection mechanisms in place, the use of mobile phones as part of computational methods to analyze people’s routines and relations opens the possibility to new forms of information access, healthcare, and creative expression. Beyond applications, many of the fundamental scientific questions have profound value on their own, as part of an emerging body of work dubbed by some as computational social science.
The research in this domain is currently scattered over several communities, including ubiquitous and wearable computing, human-computer interaction, multimedia, machine learning, and network science. Each of these communities has begun to analyze specific aspects of this rich domain with different emphasis, and often with disparate methodological tools. Beyond the diversity of communities, there is a divide regarding the definition of the fundamental research questions and how to approach them. The tutorial aims at presenting and discussing the state-of-the-art in this domain to the ACM MM community, traditionally open to new ideas.
Outline
The tutorial has two main objectives: to present the scientific and technological state-of-the-art in mobile phone-based modeling of large-scale human behavior from a coherent perspective; and to motivate further work in this domain by the multimedia community by discussing both the most important lessons learned so far and the variety of problems that remain open. The tutorial is organized around several topics including: sensor data on mobile phones; interacting with mobile phones; mobile sensing in real life; privacy issues, models to characterize individual and community behavior from single and multiple data sources; large-scale research resources; and open problems and opportunities. The tutorial will consist of lectures accompanied by a variety of examples and demos to illustrate the discussed concepts, models, and systems. The lectures will also contain pointers to the appropriate literature for further study.
Audience
The tutorial is intended for graduate students and researchers in areas related to ACM MM who are interested in learning about the state-of-the-art in smartphone-based modeling of human behavior from a coherent perspective. Given the current fragmentation of the research in this domain, both young and seasoned researchers might benefit from the exposure of fairly recent concepts under a consistent framework. The tutorial aims at introducing concepts and open perspectives that motivate further work in this domain, ranging from fundamentals to applications and systems.
Organizers/Presenters
Daniel Gatica-Perez is a Senior Researcher at Idiap Research Institute, Switzerland, where he directs the Social Computing Group, developing computational models to analyze human behavior from sensor data. His research integrates methods from multimedia signal processing and information systems, machine learning, ubiquitous computing, and elements from social sciences to address questions related to the discovery, recognition, and prediction of behavior of individuals, groups, and communities in real life. His recent work has studied several social interaction scenarios, including populations of cell phone users in urban environments, small groups at work in multisensor spaces, and on-line communities in web social media. His research has been supported by the Swiss and the US governments, the European Commission, and industry. He currently serves on the Editorial Board of the IEEE Transactions on Multimedia, the Journal of Ambient Intelligence and Smart Environments, Image and Vision Computing, and Machine Vision and Applications, and was Guest Co-Editor of the IEEE Computer Magazine Special Issue on Human-Centered Computing. He got a PhD in Electrical Engineering from the University of Washington in 2001, receiving the Yang Research Award for his doctoral research. He is an active member of the multimedia community, recently serving as Vice Chair of the IEEE Int. Conf. on Multimedia (ICME), Program Co-Chair of the ACM. Int. Conf. on Image and Video Retrieval (CIVR), Program Co-Chair of the Int. Conf. on Multimodal Interfaces (ICMI), and Short-Paper Chair of the Human-Centered Track at ACM MM.
T09 – Modeling Human Behavior with Mobile Phones
In just a few years, mobile phones have emerged as the ultimate multimedia device. Smartphones allow us to take pictures, listen to music, watch videos, interact with the physical world through GPS, communicate via calls, SMS, or MMS, and browse the web. Given their ubiquity, mobile phones have become the most natural device for multimedia consumption, production, and interaction, but there is much more to it. Smartphones can constantly sense people’s location via GPS or cell tower connectivity, motion through accelerometers, proximity via Bluetooth, and communication through call and SMS logs, and thus represent the most accurate and non-intrusive current means of tracing real-life human activities. Furthermore, all this information, as never before, is being generated at massive scales. It is therefore not surprising that the understanding of personal and social behavior from mobile sensor data at large-scale, where population of cell phone users are analyzed both as individuals or groups over possibly long periods of time, has emerged as a frontier domain in computing. This research domain has been recognized as having high potential impact in real life, whether it is our personal life, business, or government. With appropriate privacy-protection mechanisms in place, the use of mobile phones as part of computational methods to analyze people’s routines and relations opens the possibility to new forms of information access, healthcare, and creative expression. Beyond applications, many of the fundamental scientific questions have profound value on their own, as part of an emerging body of work dubbed by some as computational social science.
The research in this domain is currently scattered over several communities, including ubiquitous and wearable computing, human-computer interaction, multimedia, machine learning, and network science. Each of these communities has begun to analyze specific aspects of this rich domain with different emphasis, and often with disparate methodological tools. Beyond the diversity of communities, there is a divide regarding the definition of the fundamental research questions and how to approach them. The tutorial aims at presenting and discussing the state-of-the-art in this domain to the ACM MM community, traditionally open to new ideas.
Outline
The tutorial has two main objectives: to present the scientific and technological state-of-the-art in mobile phone-based modeling of large-scale human behavior from a coherent perspective; and to motivate further work in this domain by the multimedia community by discussing both the most important lessons learned so far and the variety of problems that remain open. The tutorial is organized around several topics including: sensor data on mobile phones; interacting with mobile phones; mobile sensing in real life; privacy issues, models to characterize individual and community behavior from single and multiple data sources; large-scale research resources; and open problems and opportunities. The tutorial will consist of lectures accompanied by a variety of examples and demos to illustrate the discussed concepts, models, and systems. The lectures will also contain pointers to the appropriate literature for further study.
Audience
The tutorial is intended for graduate students and researchers in areas related to ACM MM who are interested in learning about the state-of-the-art in smartphone-based modeling of human behavior from a coherent perspective. Given the current fragmentation of the research in this domain, both young and seasoned researchers might benefit from the exposure of fairly recent concepts under a consistent framework. The tutorial aims at introducing concepts and open perspectives that motivate further work in this domain, ranging from fundamentals to applications and systems.
Organizers/Presenters