Data analysis & Social Mining for the Interconnected Society

Motivation of the Track:

One of the most pressing, and fascinating, challenges of our time is in understanding the complexity of the global interconnected society we inhabit. The rapid growth of the Internet and the Web, the speed with which global communication and trade now takes place, and the fast spreading around the world of news and information as well as epidemics, trends, financial crises and social: these are all signals that mankind has entered a new era, a new techno-social ecosystem whose inner mechanisms are different from before, and largely unveiled. Ours is also a time of opportunity to observe and measure how our society intimately works: the big data originating from the digital breadcrumbs of human activities, sensed as a by-product of the ICT systems that we use, promise to let us scrutinize the ground truth of individual and collective behavior at an unprecedented detail. Multiple dimensions of our social life have now big data “proxies”:

• our desires, opinions and sentiments leave their traces in the social media we participate in, in the query logs of the search engines we use, in the tweets we send and receive;
• our relationships and social ties leave their traces in the network of our phone or email contacts, in the friendship links of our favorite social networking site;
• our shopping patterns and lifestyles leave their traces in the transaction records of our purchases;
• our movements leave their traces in the records of our mobile phone calls, in the GPS tracks of our onboard navigation system.

Sensing big data at a societal scale, and the interlinking of digital and physical reality, is providing us with a powerful social microscope, which can help us understand many complex socio-economic phenomena. It is clear that such challenge requires high-level analytics, modeling and reasoning across all the social dimensions above. In practice, however, there is a big gap from the opportunities offered by the big data to the challenges posed by the social phenomena. The reasons behind the gap are at least the following. First, Analytics and data mining offer limited tools to study the models and patterns of human activities. Although
data mining from traditional databases is a mature technology, we do not have yet adequate data mining tools to deal with the networked, multi-dimensional nature of human activities and their semantic richness. The role of social semantics is confined to the preparation of data and to the interpretation of the obtained patterns and models, without truly high-level modeling tools. Second, people are unaware of the power of their personal data, which are predated by service providers and secluded in disparate public and private databases. Lack of trust and transparency makes people reluctant to share high-quality personal data. What is missing here? Social mining techniques and tools able to deal with semantic-rich data, complex data for extracting patterns and models, which incorporate the multi-dimensional aspects of real life taking into consideration possible ethical and legal aspects like privacy,
data protection, transparency and user control on own personal data.

The purpose of this track is to encourage principled research that will lead to the advancement of the data analysis, social mining and privacy-aware (big) data analytics.

Topics of the track:

The track will seek top-quality submissions addressing important topics that include, but are not limited to, the following:

• Social Network analysis
• Community Discovery
• Social Dynamics
• Diffusion of Innovations
• Epidemic Models
• Mobility Data analysis
• Social Media analysis
• Modeling and mining of human behaviors
• Data-driven individual/collective well-being indicators
• Privacy in Online Social network
• Privacy-preserving mining and sharing
• Personal data protection and law enforcement
• Balancing privacy and quality of the service/analysis
• Ethics in data mining and analysis
• Transparency and accountability in data mining

Organizers:

Anna Monreale, Department of Computer Science, University of Pisa, Italy
Giulio Rossetti, Department of Computer Science, University of Pisa, Italy

Technical Program Committee:

• Remy Cazabet, LIP6 Universite Pierre et Marie Curie/CNRS, Paris, France
• Michele Coscia, Harvard Kennedy School, US
• Riccardo Guidotti, ISTI-CNR, Italy
• Sophia Karagiorgou,  Greece
• Anna Leontjeva, University of Tartu, Estonia
• Matteo Magnani, Uppsala University, Sweden
• Stan Matwin, Dalhousie University, Canada
• Letizia Milli, University of Pisa, Italy
• Luca Pappalardo, University of Pisa, Italy
• Nikos Pelekis, University of Pireus, Greece
• Francesca Pratesi, ISTI-CNR, Italy
• Manolis Terrovitis, Institute for the Management of Information Systems (IMIS), Greece
• Olivia Woolley, ETH Zurich, Switzerland