Measuring Tie Strength in Implicit Social Networks

Given a set of people and a set of events attended by them, we address the problem of measuring connectedness or tie strength between each pair of persons. The underlying assumption is that attendance at mutual events gives an implicit social network between people. We take an axiomatic approach to this problem. Starting from a list of axioms, which a measure of tie strength must satisfy, we characterize functions that satisfy all the axioms. We then show that there is a range of tie-strength measures that satisfy this characterization.

A measure of tie strength induces a ranking on the edges of the social network (and on the set of neighbors for every person). We show that for applications where the ranking, and not the absolute value of the tie strength, is the important thing about the measure, the axioms are equivalent to a natural partial order. To settle on a particular measure, we must make a non-obvious decision about extending this partial order to a total order. This decision is best left to particular applications. We also classify existing tie-strength measures according to the axioms that they satisfy; and observe that none of the “self-referential” tie-strength measures satisfy the axioms. In our experiments, we demonstrate the efficacy of our approach; show the completeness and soundness of our axioms, and present Kendall Tau Rank Correlation between various tie-strength measures. Time-permitting, I will discuss the big data issues of measuring tie-strength and applications of our work in the wild (e.g., the WaPo Social Reader).

Full paper is available at http://eliassi.org/papers/gupte-websci12.pdf

About Tina Eliassi-Rad

Tina Eliassi-Rad is an Associate Professor of Computer Science at Rutgers University. Before joining academia, she was a Member of Technical Staff and Principal Investigator at Lawrence Livermore National Laboratory. Tina earned her Ph.D. in Computer Sciences (with a minor in Mathematical Statistics) at the University of Wisconsin-Madison. Within data mining and machine learning, Tina’s research has been applied to the World-Wide Web, text corpora, large-scale scientific simulation data, complex networks, and cyber situational awareness. She has published over 50 peer-reviewed papers (including a best paper runner-up award at ICDM’09 and a best interdisciplanary paper award at CIKM’12); and has given over 70 invited presentations. Tina is an action editor for the Data Mining and Knowledge Discovery Journal. In 2010, she received an Outstanding Mentor Award from the US DOE Office of Science and a Directorate Gold Award from Lawrence Livermore National Laboratory for work on cyber situational awareness. Visit http://www.eliassi.org for more details.

Digital Intensity and Variation in Design Routines: A Comparative Sociotechnical Sequence Analysis of Four Organizations

Organizations continue to embed increasingly richer repertoires of digital capabilities into their activities, and the impact of this digitalization on those routines is, as yet, not well‐understood. Will increased digital intensity reduce, increase, or have no effect on the variation of organizational routines? Furthermore, how is this routine variation affected by internal and external factors, such as centrality of the decision structure and volatility of the market environment? In this study, we leverage a novel sociotechnical sequence analysis technique to explore these questions in four theoretically‐sampled, design organizations (software development, semiconductor design, hydraulic valve design, and architecture). We study the context of design because of the fluidity, interactive complexity, knowledge‐intensiveness, heavy digitalization, and variation found in design activity.

Through this research, we advance a theory of “configural” routine variation – that of variation between components of routines – by examining the effects of (1) environmental variation; (2) structural variation; and (3) variation in digital intensity on routine variation. We propose that design routines are subject to greater variation between (rather than within) organizations; between (rather than within) similar environments; within more volatile environments; and within more de‐centralized organizations. Our analysis largely supports these theoretical arguments. Further, we find that increased digital intensity reduces process variation in design contexts. Overall, our analysis sheds new light on the interactions between organizational context, environment, and digitalization, and their impact on design routine variation. Our sequence‐analytic approach is founded on well‐established sequence analysis techniques widely used in the study of organizational routines, but extends these techniques with insights gained by sociotechnical scholarship for discovering the intricacies of the process context. The technique accounts for how digital artifacts and human activities become entangled in practice by detailing the activities, actors, artifacts, and affordances that comprise a sociotechnical routine. This study illustrates the valuable insights one might draw from the application of the approach in the study
of the digitalization of organizational routines.

About Nicholas Berente

Nicholas Berente is an assistant professor in Management Information Systems at the University of Georgia’s Terry College of Business. He received his PhD from Case Western Reserve University and conducted his postdoctoral studies at the University of Michigan. Dr. Berente is the principal investigator for three projects funded by the National Science Foundation investigating the management of next generation scientific research centers(NSF OCI‐1059153, RCN‐1148996, CI‐TEAM‐1240160). He has contributed to a variety of NSF‐funded projects associated with distributed, collaborative innovation in multiple contexts (NSF OCI‐0943157; SES‐0621262; CCF‐0613606; IIS‐0208963) and has focused much
of his research on information technology‐enabled innovation at NASA. He has authored more than seventy peer‐reviewed articles, and his work has been published in top journals, including MIS Quarterly, Information Systems Research, and Organization Science.

Download the flyer for this talk 

About The Talk: Applying Network Science: An Evolving Perspective

While opinion leader and other peer­based interventions are firmly established in public health research contexts where we seek to impact individuals’ behaviors, developments in network analytic methods have led to changes in the way we understand peer influence and selection processes and in the way we can apply network studies for intervention development. I will present my framework for understanding network­based interventions and describe how that framework has evolved in light of new network statistical approaches. I will illustrate this evolutionary process with examples of cross­sectional and longitudinal studies that link individual behaviors and attitudes to network structure and composition. I conclude with some discussions of future directions in research and in application.

About Hank Green

Harold D. Green, Jr. (Hank) is a Senior Behavioral Scientist at the RAND Corporation in Santa Monica, where he is the coordinator of the RAND Applied Network Analysis Research Group. Hank uses network analyses to understand the social and cultural determinants of health. In addition to his applied work, Hank is active in designing and implementing specialized software for the collection of longitudinal personal network data via the Internet. He holds a Ph.D. in Anthropology from the University of Florida and is an Alumnus of the University of Illinois Training Grant in Quantitative Psychology, of the National Center for Supercomputing Applications Center for the Humanities, Arts and Social Sciences, and of the Science of Networks in Communities Research Group.

Download the flyer for this talk 

About The Talk: From Words to Networks: Relevance of methodological choices for real-world applications

Coding texts as socio-technical networks – a process also known as relation extraction – can be used to collect network data on hard-to-access groups and organizations. This process requires people to choose appropriate methods and parameter settings. The impact of these choices on the resulting data and findings can be strong, but is hardly understood. I discuss our findings from addressing this problem:

We applied four common relation extraction methods – from fairly qualitative to fully automated (including probabilistic, machine-learning based techniques) – to large-scale, open-source corpora from the business, science and geopolitical domain, and compared the retrieved networks. I will report on common agreements and disagreements about network structure and behavior depending on the considered methods, and show how these methods can be combined to gain a more robust and comprehensive understanding of a network.

Another factor limiting the reliability of relation extraction methods is the propagation of errors throughout multi-step analysis procedures and pipelines. I will present our findings from a series of empirical experiments that we conducted to find answers to the following question: How much variation in network structure and properties is due to the error rates of the involved sub-routines? Does increasing the accuracy of these techniques actually matter for network analysis results?

About Jana Diesner

Jana Diesner is an Assistant Professor at the iSchool (a.k.a. Graduate School of Library and Information Science) at the University of Illinois at Urbana-Champaign. She earned her PhD from Carnegie Mellon University, School of Computer Science. Jana conducts research at the nexus of network science, natural language processing and machine learning. With her work, she aims to advance the understanding and computational analysis of the interplay and co-evolution of information and socio-technical networks. She develops, analyzes and applies methods and technologies for extracting information about networks from text data and considering the substance of information for network analysis. In her empirical work, she studies networks from the business, science and geopolitical domain. She is particularly interested in covert information and covert networks. For more information see http://people.lis.illinois.edu/~jdiesner/.

Download the flyer for this talk 

SONIC lab is proud to welcome Elena Pavan, who will present a talk on Thursday, Jan 24, 2013 (12:00-01:15pm) in Frances Searle Building Room 1.459 on Northwestern’s Evanston Campus. All are welcome to attend.

About Elena Pavan
Post-Doctoral Research Fellow
Department of Sociology and Social Research
via Verdi 26, int. 26
38123 Trento (Italy)

e-mail: elena.pavan@unitn.it
telephone: +39 (0)461 28 1378

About The Talk

Studies on social networks have proved that both structure and social attributes influence dynamics. Two streams of modeling exist to explain the dynamics of social networks: 1) models predicting links through network properties, and 2) models considering the effects of social attributes. In our current work we take an approach to work to overcome a number of computational limitations within these current models.We employ a mean-field model which allows for the construction of a population-specific model informed from empirical research for predicting links from both network and social properties in large social networks. The model is tested on a population of conference coauthorship behaviors of Dutch Computer Scientists, considering a number of parameters from available Web data. We prove that the mean-field model, using a data-aware approach, allows us to overcome computational burdens and thus scalability issues in modeling large social networks. A link to our current work can be found here – http://arxiv.org/abs/1209.6615.

About Julie Birkholz

Julie’s research works to comment on institutional influences on patterns of collaboration in producing research of interdisciplinary character. She specifically works to investigate the effects of institutional organizational processes on scientists’ knowledge production processes. For example, how does collaboration evolve in field of scientific practice? Using a combination of social network analysis, bibliomterics and computational social models (e.g. longitudinal actor-based network models such as ERGM),  Additionally, she is working within the Semantically Mapping Science Project (http://www.sms-project.org/) which implements the use of Web data to assess science.

Research interests include: knowledge innovation in academic networks, dynamic cooperation techniques in arising collaboration networks, and ephemeral network structures

Download the flyer for this talk 

Mean-field approach for large social networks

About the talk

Barend will talk about the role of semantic technologies, (under)standards and the nanopublication ecosystem in particular. He will challenge several established views in the field of the semantic web, scholarly communication, intellectual networking, science metrics, peer review and ‘data publishing’ with an emphasis on the barriers to break down in order to allow effective data exposure, sharing and integration in the Big Data era. The context of his talk will be the need for eScience approaches to ‘in silico’ knowledge discovery.

About Barend Mons

Barend Mons (born The Hague, The Netherlands in 1957, PhD in 1986 at Leiden University, in The Netherlands) is a molecular biologist who turned to bioinformatics in 2000 after a decade of research on the genetic differentiation of malaria parasites, and five years of science management at the Research Directorate of the European Commission and the Netherlands Organisation of Scientific Research. He is the initiator of WikiProfessional and an inventor of the Knowlet technology. In 2008 he was one of the driving forces behind the Concept Web Alliance, in close collaboration with (a.o.) Jan Velterop, Mark Musen, Amos Bairoch. In 2000 he founded Collexis and in 2005, he co-founded Knewco, Inc.

Since 2002 he has been Associate Professor in Biosemantics at the Department of Medical Informatics, Erasmus Medical Centre, University of Rotterdam and (since 2005) at the Department of Human Genetics at the Leiden University Medical Centre, both in The Netherlands. Mons published over 70 peer reviewed articles, holds three patents in semantic technology and is a regular keynote speaker at international conferences.

As of 2010 he is a Scientific Director of the Netherlands Bioinformatics Centre (NBIC), whilst retaining his academic affiliations with Leiden University Medical Centre and Erasmus Medical Centre. In 2012 Barend has been appointed as professor in Biosemantics at the Leiden University Medical Center. The chair is established by the Netherlands Bioinformatics Centre (NBIC).

Download the flyer for this talk

View a PDF flyer about Peter’s talk

About the talk
Systems that present people with information inescapably make editorial judgments in determining what information to show and how to show it. However the editorial values used to make these judgments are generally invisible to users and in many cases even to the engineers who design them. Our work is aimed at developing news and media information technologies that provide explicit and visible editorial control, at scale. Some of our most exciting work in this area is aimed at automatically generating stories from data. A system based on this technology is already generating more than 10 thousand stories weekly in areas ranging from sports, to business, to politics. This system is the nation’s most prolific and published author of, among other things, women’s collegiate softball stories. The stories compare favorably to those written by human beings.

About Larry Birnbaum
Larry Birnbaum received his PhD in computer science from Yale University in 1986, and joined the Northwestern faculty in 1989. His research in artificial intelligence and computer science has encompassed natural language processing, case-based reasoning, machine learning, human-computer interaction, educational software, and computer vision. Birnbaum has authored or coauthored more than eighty articles. He was the program co-chair of the 1991 International Machine Learning Workshop and has been a member of the program committee for numerous other conferences and workshops.

From Contextual Search to Automatic Content Generation: Scaling Human Editorial Judgement

Goals as Antecedent to Social Network Structure