Welcome to DYAD 2014, the First Workshop on Interaction and Exchange in Social Media. The workshop will held in Barcelona, Spain in conjunction with the 6th International Conference on Social Informatics (SocInfo 2014) on November 10th 2014.

Scientists are now on the cusp of gaining a computational understanding of social interaction by means of online data. Online interactions can be conceptualized as a social exchange, and also as a process through which meaning emerges through dialogue between the two partners. We believe that our understanding of social structure will undoubtedly be enriched through a computational focus on the mechanics of the dyad. Join us at the DYAD workshop for plentiful dialogue and exchange.

Call for Papers

A great deal of work has used computational methods to investigate the intensity, structure, topic and sentiment of social interactions. But neither information alone nor structure in isolation can be considered fully responsible for the complexity of social life, whether on- or offline. We aim for the DYAD workshop to examine online interactions from a number of extremely rich perspectives. Scientists are now on the cusp of gaining a computational understanding of social interaction by means of online data. Online interactions can be conceptualized as a social exchange, and also as a process through which meaning emerges through dialogue between the two partners. Our understanding of social structure will undoubtedly be enriched through a computational focus on the mechanics of the dyad. We hope you will join us for plentiful dialogue and exchange.

The workshop will welcome submissions on topics related to computational approaches to the study of dyadic interaction, relevant to fields as diverse as social psychology, behavioral economics, sociolinguistics as well as computational linguistics, web science, and network science. Examples of relevant submissions include, but are not limited to, the following topics:

  • Detection of social expectations and norms
  • Status relations and power imbalances
  • Detection and measurement of social support, such as in critical situations related to illness, bullying or grieving
  • Self-disclosure, turn-taking, deference in interpersonal communication
  • Identity
  • Topic development and change in online conversations
  • Emotion dynamics in conversation thread
  • Social dynamics in comment thread (politics, news, interest-based communities)
  • Development of language and the self through social interaction
  • Language variation across communities and social relationships (e.g. distinguishing friends from colleagues, etc.)
  • Persuasive language
  • Pragmatics of language


Submitted works have to present original research contributions not concurrently submitted elsewhere and they can come as either full 10-page or short 4-page papersb .

All submitted papers must:

  • be written in English;
  • contain author names, affiliations, and email addresses;
  • be formatted according to the Springer LNCS paper formatting guidelines;
  • be in PDF (make sure that the PDF can be viewed on any platform).

It is the authors’ responsibility to ensure that their submissions adhere strictly to the required format. Submissions that do not comply with the above guidelines may be rejected without review.

Paper submission will be handled via EasyChair and it will be available at this link. For any question about the call for papers please contact dyad2014@easychair.org.

The authors can choose to publish their papers along with the main conference proceedings, or withhold such publication for future work considerations.


Full papers will be given 30 minutes and short 20 minutes for presentations including questions.


Submission deadline:September 8, 2014  September 15, 2014 (extended)
Notification of acceptance:September 22, 2014  September 29, 2014 (extended)
Camera-ready due:October 5, 2014
Workshop date:November 10, 2014
SocInfo Conference dates:November 10-13, 2014


Accepted Papers

Triad-based Role Discovery for Large Social SystemsDerek Doran
Detecting Presence of Personal Events in Twitter StreamsSmitashree Choudhury and Harith Alani
A Tool-based Methodology to Analyze Social Network Interactions in Cultural Fields: the Use Case MuseumWeekAntoine Courtin, Juanals Brigitte, Jean-Luc Minel, Mathilde de Saint Léger
Digital Addiction Ontology for Social Networking SystemsAmen Alrobai and Huseyin Dogan


9:10invited talkCarlos Diuk-Wasser
10:00invited talkBruno Gonçalves
11:20paperTriad-based Role Discovery for Large Social Systems
11:45paperDetecting Presence of Personal Events in Twitter Streams
12:10paperA Tool-based Methodology to Analyze Social Network Interactions in Cultural Fields: the Use Case MuseumWeek
14:00round table The Study of Social Ties in the Computational Age
16:25paperDigital Addiction Ontology for Social Networking Systems
16:50invited talkCristian Danescu-Niculescu-Mizil
17:40 Closing remarks


Cristian Danescu-Niculescu-Mizil

Cristian Danescu-Niculescu-Mizil

MPI-SWS / Cornell University

Language and Social Dynamics in Online Communities

More and more of life is now manifested online, and many of the digital traces that are left by human activity are in natural-language format. In this talk I will show how exploiting these resources under a computational framework can bring a new understanding of online social dynamics; I will be discussing two of my efforts in this direction.

The first project explores the relation between users and their community, as revealed by patterns of linguistic change. I will show that users follow a determined life-cycle with respect to their susceptibility to adopt new community norms, and how this insight can be harnessed to predict how long a user will stay active in the community.

The second project proposes a computational framework for identifying and characterizing politeness, a central force shaping our communication behavior. I will show how this framework can be used to study the social aspects of politeness, revealing new interactions with social status and community membership.

This talk includes joint work with Dan Jurafsky, Jure Leskovec, Christopher Potts, Moritz Sudhof and Robert West.


Cristian Danescu-Niculescu-Mizil is a faculty member of the Max Planck Institute SWS; in January he will join Cornell as an assistant professor in the information science department. His research aims at developing computational frameworks that can lead to a better understanding of human social behavior, by unlocking the unprecedented potential of the large amounts of natural language data generated online. His work tackles problems related to conversational behavior, opinion mining, computational semantics and computational advertising. He is the recipient of several awards, including the WWW 2013 Best Paper Award and a Yahoo! Key Scientific Challenges award, and his work has been featured in popular-media outlets such as the New Scientist, NBC's The Today Show, NPR and the New York Times.

Bruno Gonçalves

Bruno Gonçalves

Aix-Marseille Université

Data driven models of human interaction

With the advent of modern communication tools, more and more of human interactions occur online. The massive quantities of data that ae automatically generated by these systems provides us with a unique view on how we socialize, communicate and travel. Until recently, studies have focused primarily on just one of these different layers, however, it has become clear that a global view on human behavior can only be achieved by considering how the different layers mutually influence one another.

In this talk I will review some recent results on the study of human behavior using data sets from online social networks. In particular we will analyze how information diffusion impacts the social network structure and how our mobility shapes our social connections.


Bruno Gonçalves is a faculty member at Aix-Marseille Université with a strong expertise in using large scale datasets for the analysis of human behaviour. After completing his joint PhD in Physics, MSc in C.S. at Emory University in Atlanta, GA in 2008 he joined the Center for Complex Networks and Systems Research at Indiana University as a Research Associate. From September 2011 until August 2012 he was an Associate Research Scientist at the Laboratory for the Modeling of Biological and Technical Systems at Northeastern University. Since 2009 he has been pursuing the use of Data Science and Machine Learning to study human behavior. By processing and analyzing large datasets from Twitter, Wikipedia, web access logs, and Yahoo! Meme he studied how we can observe both large scale and individual human behavior in an obtrusive and widespread manner. The main applications have been to the study of Information Diffusion, Behavioral Change and Epidemic Spreading. He is the author of over 40 publications and the editor of the forthcoming book Social Phenomena: From Data To Models (Springer, 2014).

Carlos Diuk-Wasser

Carlos Diuk-Wasser

Facebook, Inc.

Passions in the time of Facebook

The Facebook graph connects people to their friends and family, their lovers and exes, to celebrities and media outlets, their favorite sports teams and politicians. The past 5-10 years have seen the birth of a unique tool for social research: a global, real-time snapshot of our connected online personas. In this talk I will illustrate how these tools enable us to study the individual, dyads and whole societies, all in one place and simultaneously. Through examples from relationships to soccer to politics, I hope to raise some questions about new methodologies, new biases, and an evergreen concern: how our persona online relates to the real world.


Carlos Diuk is a data scientist on the Data Science team at Facebook. He works on improving our understanding of people’s identities online, as well as figuring out what we can learn about society from our online personas. He received a PhD in Computer Science from Rutgers University and worked for four years as a Postdoctoral Researcher scanning human brains at the Princeton Neuroscience Institute.


Program Committee

Saiph SavageUC Santa Barbara
Nicholas DiakopoulosColumbia University
Emre KicimanMicrosoft
Haewoon KwakQatar Computing Research Institute
Michael MäsETH Zürich
Salvatore ScellatoUniversity of Cambridge
Mirco MusolesiUniversity of Birmingham
Giovanni Luca CiampagliaIndiana University
Emilio FerraraIndiana University
Emma SpiroUniversity of Washington
Vincent BuskensUtrecht University
Brandy AvenCarnegie Mellon
Damon CentolaUniversity of Pennsylvania
Giancarlo RuffoUniversity of Torino
Farshad KootiUniversity of Southern California
Eytan AdarUniversity of Michigan
Frank SchweitzerETH Zürich
Brian KeeganNortheastern University
Aek Palakorn AchananuparpSingapore Management University (LARC)
Fabio CelliUniversity of Trento
Chenhao TanCornell University
Airi LampinenHelsinki Institute for Information Technology
Emilio ZagheniQueens College
Ka-Yuet LiuUCLA
Andrea TagarelliUniversity of Calabria


John Doe

Rossano Schifanella

Assistant Professor, University of Torino

Jane Helf

Bogdan State

Scientist, Facebook

Yelena Mejova

Scientist, Qatar Research Institute