We believe that the best way to learn about the right research questions is to actually design and build a working system that can be deployed at real-life social gatherings. We partnered with the TAGora project, and specifically with the team of the University of Southampton (Harith Alani, Martin Szomszor and Gianluca Correndo) and designed the Live Social Semantics (LSS) experiment. The basic idea is to focus on a conference gathering and establish a contact between: A) the real-world identities and physical-space relations of conference attendees, B) their identities and relations in web-based systems for social networking and collaborative tagging, and C) their identities in semantic representation of knowledge that describe their interests and collaborations (paper co-authorship, for example). The SocioPatterns project provides the social sensing platform needed for A), while the TAGora project provided the profile-mining and semantic integration techniques required to collect, filter and represent B) and C). The movie below illustrates the experiment concept and the user-facing aspects of the system.

Attendees enroll in Live Social Semantics (LSS) by volunteering to wear a RFID-equipped badge that can detect face-fo-face proximity. This is the real-world part of the experiment. The real-world identity of an attendee is then associated with multiple on-line identities of her choice by creating a user profile in the LSS web interface. LSS currentlty supports Facebook, Flickr, Delicious, and Last.FM. Once a profile has been created, the system will gather data from these systems in the background, record on-line friendships and infer interests and shared interests. The system will also mine for co-membership in communities of practice (COP) using semantic web sources such as the RKBExplorer.

The data collected and integrated by LSS are stored as RDF relations in a triple store, and fed back to the conference attendees in a number of ways. There are public real-time visualizations of the ongoing face-to-face contacts (as in previous SocioPatterns experiments), but now annotated using information and profile pictures from on-line social networks and semantic data. Participants can also visit their account page on the LSS web interface and browse the list of persons they have been in contact with during the event, ranked by the measured strengths of the interactions. On top of that, the system provides an interactive web-based visualization that allows users to browse their ego networks across all supported systems, exploring the interplay of face-to-face time, on-line friendships and shared interest. The system also provides simple forms of recommendation, by suggesting the closure of social triangles that span the supported networks: for example, if attendee A has spent face-to-face time with attendee B, the system can point her to the profile of a third attendee C who is a Facebook friend of both A and B, and hasn’t met A yet at the event.

The architecture of the system and some basic usage statistics are reported in a paper that will be presented in the “Semantic Web in Use” track of the International Semantic Web Conference 2009 (ISWC2009). From a research perspective, the collected data enable to relate, quantitatively, how much an on-line friendship between individuals is predictive of their face-to-face time, and how the structure of the on-line and real-world social networks relate to one another. Results about this will be posted here in the coming weeks.

Basic libraries for tapping into the live data stream for each of these platforms will be provided. During the workshop, participants will be able to tap into the live data stream from the SocioPatterns deployment at the Science Gallery. Given that the participants will only have access to the live stream during the workshop, the idea is to have finished pieces by the end of the workshop. It is necessary that all participants think about what they want to do beforehand, and even pre-develop basic artwork to be used during the workshop.

This workshop is free, but you need to reserve here (hurry, because we’ve heard that there are only a few places left…)

The second will be deployed at the 20ème Congrès de la Société Française d’Hygiène Hospitalière on June 4th and 5th in Nice, France. This deployment aims to demonstrate the SocioPatterns platform and its ability to collect highly detailed data on the social interactions in a large-scale setting.

The third experiment will be deployed at the ACM Hypertext 2009 conference from June 29th to July 1sr, at Villa Gualino in Torino, Italy.

Setup

All visitors of the exhibition get to wear SocioPatterns/OpenBeacon tags during their visit. For this exhibition, the firmware has been enhanced to support a “virtual contagion” process. When visitors enter the exhibition their tags are initially “uninfected”. A tag can get “infected” if the person wearing it spends time in the vicinity of an “infected” person. Infected tags have a different blinking pattern and show up as red marks in the real-time visualization available to the visitors, as opposed to green for uninfected ones.

This deployment also features a reactive part that involves audio-visual effects  triggered by the proximity of individuals. Various visualizations of either the whole interaction network or contextual subsets, are located throughout the exhibition.

The following is an extract from the April 16 journal on the national Irish TV (RTE) that should give you an idea of the exhibition in general and the theatrical framing of the tag distribution process, as well as (the current state of) the alarm effects in the tunnel.

The following video offers a nice overview of the complete exhibition, starting with the SocioPatterns deployment.

Also have a look at the exhibition guide superbly designed to look like a government emergency procedure leaflet.

Science

This particular SocioPatterns deployment clearly has a high “drama” component to it. It is, however, also scientifically relevant. In particular the fact that it involves a continuous stream of visitors entering and leaving the exhibition is of interest. Such ”high-flow” setting is akin e.g. train stations or airports. A better understanding of the structural and temporal nature of social interaction patterns in such high-flow settings is relevant in a number of domains, including epidemiology. Clearly, collecting detailed data on these patterns in an actual train station or airport is very difficult. The relatively controlled and approximating settings of this exhibition does however provides us a promising opportunity to indeed collect such data.

While our earlier experiments were deployed at conferences with a relatively homogeneous and stable population, here we have a more heterogenous and dynamic population. We can thus now compare the social interaction patterns in these different settings. We are interested in deploying SocioPatterns experiments in yet other kinds of social settings (proposals are welcome!)

The SocioPatterns deployment at the Infectious exhibition includes a “live” simulation of contagious spreading. By framing this functionality as a “game” and controlling the nature of the information that is provided to the visitors in different runs on different days, we hope to collect data on and compare different kinds of behavioral effects.

Acknowledgements

This project has been deployed by Ciro Cattuto and Wouter Van den Broeck in collaboration with the Science Gallery. We would like to thank Michael John Gorman, Don Pohlman and Derek Williams from this great venue for making this possible. We would also like to thank Milosch and Brita Meriac from OpenBeacon.org for once again providing excellent RFID hardware, and the ISI Foundation for their continued support.

Pictures

To wrap up this post, we would like to share some pictures taken at the exhibition.

A bunch of RFID tags ready to be distributed at the entrance.

Handing out the RFID tags.

Handing out the RFID tags.

The tunnel contains alarm effects triggered by nearby infected tags.

Nearing the end of the tunnel with the disinfection stations.

Queuing to get healed at the disinfection stations.

The visualization at the end of the tunnel during the crowded opening event.

On December 26-30th we deployed a new SocioPatterns experiment at the 25th Chaos Communication Congress in Berlin (25C3). This is the first large-scale deployment of our platform for sensing social interactions. We added to the visualization interface several ways of focusing on particular subsets of the real-time and cumulative contact networks. In line with the conference’s action line “nothing to hide”, we made the live contact network available on the web.

We thank the following persons for their work and support: Milosch Meriac, Brita Meriac, and aestetix, Janette Lehmann, Aurora Mazzone, Marco Perosa, Eric Preston, Tomasz Rybak. Our work at 25C3 was carried out in the context of a broader tracking event by the OpenBeacon project and the OpenAMD project, with hardware and infrastructure provided by Bitmanufaktur. We also thank the organizers of 25C3 for hosting our work at such a stimulating event!

Visualizations, movies and results from the data collected at 25C3 will be posted to this blog in the next few weeks.