3rd Int'l AAAI Conference on Weblogs and Social Media
May 17 - 20, 2009, San Jose, California
ICWSM-09 Tutorial Program
Sunday, May 17
Tutorial 1 (T1): Predictive Modeling with Social Networks
Jennifer Neville (Purdue University) and Foster Provost (New York University)
Presented by Foster Provost
1:30 - 3:30 PM
Recently there has been a surge of interest in methods for analyzing complex social networks: from communication networks, to friendship networks, to professional and organizational networks. For predictive modeling, the dependencies among linked entities in the networks present an opportunity to improve inference about properties of individuals, as birds of a feather do indeed flock together. For example, when deciding whom to target with a product offer, it may be helpful to consider whether a person's MySpace or Facebook friends have expressed interest in the product.
This tutorial will explore the unique opportunities and challenges for predictive modeling with social network data. We will begin with a description of the problem setting, including examples of various applications of social network mining (e.g., targeted marketing, on-line advertising, fraud detection). We will then present a number of characteristics of social network data that differentiate it from the traditional settings for inference and learning, and outline the resulting opportunities for significantly improved inference and learning. We will discuss specific techniques for capitalizing on each of the opportunities in statistical models, and outline both methodological issues and potential modeling pathologies that are unique to network data.
The focus in this tutorial will be to cover the basics, discuss real applications and results where possible, and provide a framework for understanding the more advanced concepts. We also will provide supplemental material on more advanced concepts, including links to the recent literature. Prerequisites: The tutorial assumes a basic knowledge of AI-style inference and machine learning, equivalent to an introductory graduate or advanced undergraduate class.
Jennifer Neville is an assistant professor at Purdue University. She received her PhD from the University of Massachusetts Amherst in 2006. She received a DARPA IPTO Young Investigator Award in 2003 and was selected as a member of the DARPA Computer Science Study Group in 2007. Recently she was chosen by IEEE as one of "AI's 10 to watch" for 2008. Her research focuses on data mining techniques for relational and network domains.
Foster Provost is Professor, NEC Faculty Fellow, and Paduano Fellow in Business Ethics at New York University's Stern School. He is Editor-in-Chief of the journal Machine Learning, a founding board member of the International Machine Learning Society, and was program chair of the ACM SIGKDD Conference in 2001. He has received Faculty Awards from IBM and a President's Award from NYNEX Science and Technology. His recent research has focused on inference and learning with network data, utility-based data mining, and on-line advertising.
Tutorial 2 (T2): The Psychology of Social Media
Sam Gosling (University of Texas, Austin), Kate Niederhoffer (Dachis Corporation)
4:00 - 6:00 PM
Every action taken on a social media platform is performed by a psychological being trying to satisfy some kind of psychological need-that is, individuals use social media to meet their emotional, social, attitudinal, cognitive, behavioral, and identity needs. Media systems that adapt to these needs (which have evolved over many millions of years) will be more successful than those that do not. This tutorial will present a range of theories and recent empirical research in social, personality, and cognitive psychology to inform research and design on social media platforms. For example, self-verification theory predicts that much social interaction is motivated not by people's need to be seen in a favorable light by others but by their needs to be seen by others as people see themselves; this prediction is supported by research examining perceptions of others based on their websites and Facebook profiles. Person-environment theories can be used to understand the processes of selection, evocation, and manipulation by which people use social media platforms to improve the fit between themselves and their social, physical, and virtual environments. The presentation will be geared towards drawing design implications for social media systems and for providing psychological frameworks to guide data collection about the individuals and groups that use social media.
SAM GOSLING, Ph.D., is an associate professor of psychology at the University of Texas at Austin. He did his doctoral work at the University of California at Berkeley, where his dissertation focused on personality in spotted hyenas. In addition to his animal work he also does research on Internet-based methods of data collection and on how human personality is manifested in everyday contexts like bedrooms, offices, webpages, and music preferences. Gosling's environmental research, which is summarized in his book, "Snoop: What Your Stuff Says About You," is based on the idea that the spaces in which we live and work are rich with information about what we are like. His work has been widely covered in the media, including The New York Times, Psychology Today, NPR, Nightline, and Good Morning America. Gosling is the recipient of the American Psychological Association's Distinguished Scientific Award for Early Career Contribution. He lives in Austin, Texas.
|J.D. Power and Associates Web Intelligence Division|
Sponsored by the Association for the Advancement of Artificial Intelligence. For more info: firstname.lastname@example.org