Category Archives: special_talk

Talk by Zhong-Yuan Zhang

Speaker: Zhong-Yuan Zhang
Title: Semi-Supervised Community Structure Detection in Social Networks Based on Matrix De-noising
Date: 10/15/2012
Time: 1pm
Room: Informatics East 122
Abstract: Constrained clustering has been well-studied in the unsupervised learning society. However, how to encode constraints into community detection process of the complex social networks remains a challenging problem. We propose a semi-supervised learning framework for community structure detection. This framework implicitly encodes the must-link and cannot-link constraints by modifying the adjacency matrix of the network, which can also be regarded as the de-noising process of the consensus matrix of the community structures. Our proposed method gives consideration to both the topology and the functions (background information) of the complex network, which improves the interpretability of the results. The comparisons performed on the synthetic benchmarks and the real-world networks show that the framework can significantly improve the detection performance with few constraints, which makes it an attractive methodology in the analysis of complex social networks.


Talk by Cosma Shalizi

Speaker: Cosma Shalizi, Carnegie Mellon University
Title: Homophily, Contagion, Confounding: Pick Any Three
Date: 11/27/2012
Time: 1pm
Room: Informatics East 130
Abstract: A person’s behavior can often be predicted from that of their neighbors in a social network. This is sometimes explained by homophily, the tendency to form social ties with others because we resemble them.  It is also sometimes explained by social contagion or social influence, the tendency to act like someone because they are our neighbor.  We show that, generically, these two mechanisms are confounded with each other, and with the causal effect of an individual’s attributes on their behavior. Distinguishing them requires strong assumptions on the parametrization of the social process or on the adequacy of the covariates used (or both). In particular, simple examples show that asymmetries in regression coefficients cannot identify causal effects, and that imitation (a form of social contagion) can produce substantial correlations between an individual’s enduring traits and their choices, even when there is no intrinsic affinity between them. We also suggest some possible constructive responses to these non-identifiability results.  (Joint work with Andrew Thomas)

Talk by Robert J. Glushko

Speaker: Robert J. Glushko, School of Information, University of California-Berkeley
Title: The Discipline of Organizing
Date: 04/09/2012
Time: 4pm
Room: Psychology 101
Abstract: We organize things, we organize information, we organize information about things, and we organize information about information. But even though “organizing” is a fundamental and ubiquitous challenge, when we compare these activities their contrasts are more apparent than their commonalities.  As a result different concepts and methods have evolved that are embodied in the disciplines of library science, publishing and content management, business process analysis, data science, information systems design, and other fields that are studied and taught in the ISchools.  These fields don’t always agree in how they approach problems of organizing, the words they use to describe what they do, and in what they seek as solutions.

We propose to unify many perspectives about organizing with the concept of an Organizing System, defined as an intentionally arranged collection of resources and the interactions they support.  Every Organizing System involves a collection of resources, and we can treat things, information, and information about things or information as resources.  Every Organizing System involves a choice of properties or principles used to describe and arrange the resources, and ways of supporting interactions with the resources.  By comparing and contrasting how these activities take place in different contexts and domains, we can identify patterns of organizing and see that Organizing Systems often follow a common life cycle.  We can create a discipline of organizing in a disciplined way.

This new approach cuts across traditional categories of resource collections; we can describe familiar categories like libraries, museums, and business information systems as design patterns that we can then use to apply knowledge about familiar domains to unfamiliar ones; someone with a business or informatics background can better understand libraries and museums and have intelligent conversations with librarians and museum curators… and vice versa.  We now have a generative, forward-looking framework for organizing any collection of resources, especially those that that don’t cleanly fit into the familiar categories, and we can more easily invent new kinds of interactions for them.

This work to develop the Discipline of Organizing is the collective effort of a score of ISchool professors and graduate students from several institutions, and will result in a textbook targeted for the “core” or “gateway” courses at ISchools. This book will be published in early 2013 simultaneously as a printed book, as an ebook, and as an open content repository to support collaborative use and maintenance of the content by all of the ISchools using it.


Robert J. Glushko is an Adjunct Full Professor in the School of Information at the University of California, Berkeley.   After receiving his PhD in Cognitive Psychology at UC San Diego in 1979, he spent about ten years working in corporate R&D, about ten years as a Silicon Valley entrepreneur, and now has worked ten years as an academic.  His interests and expertise include information systems and service design, content management, electronic publishing, Internet commerce, and human factors in computing systems.  He founded or co-founded four companies, including Veo Systems in 1997, which pioneered the use of XML for electronic business before its acquisition by Commerce One in 1999.

Talk by Qiaozhu Mei

Speaker: Qiaozhu Mei, School of Information, University of Michigan
Title: The Foreseer: Integrative Retrieval and Mining of information in Online Communities
Date: 03/02/2012
Time: 12:00pm
Room: Informatics West 105
Abstract: With the growth of online communities, the Web has evolved from networks of shared documents to networks of knowledge-sharing groups and individuals. A vast amount of heterogeneous yet interrelated information is being generated for which existing information analysis techniques are inadequate. Current tools often neglect the actual creators and consumers of information, and as a result, the findings are only useful to data analysts. The user-centric Foreseer is the next generation of information analysis for online communities. It represents a new paradigm of study through the four “C’s”: content, context, crowd, and cloud. Information analysis of content is put into the context of the users’ daily lives to benefit the communities (crowd) that generate information residing in the cloud.

In this talk, we will introduce our recent effort of integrative information analysis of online communities. We will highlight the real world problems in online communities to which the Foreseer techniques have been successfully applied. These topics include tracking event evolution and diffusion, detecting misinformation, predicting the adoption of hashtags in microblogging communities, and the prediction of user behaviors in microfinance communities.

Bio: Qiaozhu Mei is an Assistant Professor at the School of Information, the University of Michigan. He received his PhD from the University of Illinois at Urbana-Champaign. He is widely interested in information retrieval, text mining, natural language processing and their applications in web search, social computing, and health informatics. He has served in the program committee of almost all major conferences in these areas. He is also a recipient of the NSF CAREER Award.

Talk by Daniel Romero

Speaker: Daniel Romero, Center for Applied Mathematics, Cornell University
Title: The Mechanics of Network Formation and Information Diffusion on Social Media Sites
Date: 12/02/11
Time: 10:30 a.m.
Room: Informatics West 105
Abstract: Today’s online social networks and social media sites contain a combination of social and informational ties that serve as bridges for different types of information to flow. An example of such social network is Twitter, where many users follow their friends and others that they are interested in but do not know in real life such as celebrities, news media accounts, and politicians. In this talk, I will discuss different aspects of how these networks form and how information flows through them. I will also show how studying different aspects of network formation and information diffusion on social media sites can be useful for gaining sociological insights as well as improving the sites.

Talk by Pan-Jun Kim

Speaker: Pan-Jun Kim, University of Illinois
Title: Sociology in the genetic world: What we can learn from microbial genetic co-occurrence
Date: 11/21/2011
Time: 11am
Room: Informatics East 122
Abstract: The phenotype of any organism on earth is, in large part, the consequence of interplay between numerous gene products encoded in the genome, and such interplay between gene products may affect the evolutionary fate of the genome itself through the resulting phenotype. In this regard, contemporary genomes can be used as molecular fossils that record successful associations of various genes working in their natural lifestyles. By analyzing thousands of orthologs across ~600 bacterial species, we constructed the map of gene-gene associations conserved across much of the sequenced biome. In addition to the biochemical and phylogenetic properties, we elucidate the global organization of this gene association map, in which various modules of genes are strikingly interconnected by antagonistic crosstalk between the modules. Our approach infers functional coupling of genes regardless of mechanistic detail, and may guide exogenous gene import in synthetic biology to engineer a cell for desired bioproduct production.