4th Int'l AAAI Conference on Weblogs and Social Media
May 23-26, 2010, George Washington University, Washington, DC
Sponsored by the Association for the Advancement of Artificial Intelligence.
Tutorials - May 23, 2010
Detailed schedule for the conference including the tutorials is here
9:00am - 12:00pm
1:00pm - 4:00pm
SA1: The Social Semantic Web: How Web 2.0 and the Semantic Web Can Strengthen Each Other
John Breslin and Alexandre Passant (NUI Galway, Ireland)
Web 2.0, a platform where people are connecting through their shared objects of interest, is encountering some boundaries in the areas of information integration, portability, search, and demanding tasks like querying. The Semantic Web is an ideal platform for interlinking and performing operations on the diverse data available from Web 2.0 “data silos”, and has produced a variety of approaches to overcome some of the limitations with Web 2.0. In this tutorial, Breslin and Passant aim to educate attendees on the applications of Semantic Web technologies to Web 2.0. They will also describe how Web 2.0 can serve as a very vaulable source of semantically-rich data for Semantic Web applications, solving the oft-quoted “chicken and egg” problem with the Semantic Web. The tutorial is intended for professionals, researchers, graduates, practitioners and developers who wish to learn how Semantic Web technologies can be applied to and leveraged by social software and social media systems.
John Breslin is a lecturer in Engineering and Informatics at NUI Galway. He leads the Social Software Unit at DERI, NUI Galway, and is creator of the SIOC project which aims to interlink online communities with semantic technologies. He is co-founder of boards.ie Ltd. and an advisor to CrowdGather LLC.
Alexandre Passant is a postdoctoral researcher and adjunct lecturer at DERI, NUI Galway. His research focuses on the Semantic Web and social software. He is the author of MOAT, a framework that allows people to tag their content using semantic technologies, and he is also co-editor of the SIOC specification.
SA2: Introduction to Social Media Network Analysis
Marc Smith (Connected Action) and Derek Hansen (University of Maryland)
Social networks are the defining data structure of social media, created as people reply, link, click, favorite, friend, re-tweet, co-edit, mention, or tag one another. In this tutorial, we review the core concepts and methods of social network analysis and apply it to the collection, analysis, and visualization of social media networks. Using the free and open NodeXL application, learn how to extract a social media network and generate metrics and visualizations that highlight key people and positions within streams of tweets, videos, photos, or emails.
Marc Smith is a sociologist specializing in the social organization of online communities and computer mediated interaction. Smith leads the Connected Action consulting group (http://www.connectedaction.net) which applies social science methods in general and social network analysis techniques in particular to gain insights into enterprise and internet social media usage. Smith is the co-editor with Peter Kollock of Communities in Cyberspace (Routledge), a collection of essays exploring the ways identity; interaction and social order develop in online groups. Along with Derek Hansen and Ben Shneiderman, he is the co-author and editor of the forthcoming Analyzing Social Media Networks with NodeXL, a guide to mapping connections created through computer-mediated interactions. He contributes to the open and free NodeXL project (http://www.codeplex.com/nodexl) that adds social network analysis features to the familiar Excel spreadsheet.
Derek L. Hansen is an Assistant Professor at Maryland’s iSchool and Director for the Center for the Advanced Study of Communities and Information (http://casci.umd.edu), a multi-disciplinary research center focused on harnessing the power of social technologies to support the needs of real and virtual communities. He is also an active member of the Human Computer Interaction Lab (http://www.cs.umd.edu/hcil/). His research focuses on mass collaboration, consumer health informatics, alternate reality games (ARGs), and social network analysis and visualization of online interactions. Dr. Hansen completed his PhD from the University of Michigan’s School of Information where he was an NSF-funded interdisciplinary STIET Fellow (http://stiet.si.umich.edu/) focused on understanding and designing effective online socio-technical systems.
SP1: Large-Scale Social Media Analytics with Hadoop
Jake Hofman (Yahoo!)
Over the last several years there has been a rapid increase in the
number, variety, and size of readily available social media data. As
such, there is a growing demand for software solutions that enable one
to extract relevant information from these data. For sufficiently
large data sets (e.g., networks with hundreds of millions of nodes)
distributed solutions are often necessary, as the storage and memory
constraints of single machines are prohibitive. Hadoop, an open source
implementation of the map/reduce paradigm, is an increasingly popular
framework for processing such data sets at the terabyte and petabyte
scale using commodity hardware.
In this tutorial we will discuss the use of Hadoop for processing
large-scale social data sets. We will first cover the map/reduce
paradigm in general and subsequently discuss the particulars of
Hadoop's implementation. We will then present several use cases for
Hadoop in analyzing example data sets, examining the design and
implementation of various algorithms with an emphasis on social
network analysis. Accompanying data sets and code will be made
Jake Hofman is a member of the Human Social Dynamics group at Yahoo!
Research. His work involves data-driven modeling of complex systems,
focusing on applications of machine learning and statistical inference
to large-scale data. He holds a B.S. in Electrical Engineering from
Boston University and a Ph.D. in Physics from Columbia University.
SP2: The Social Psychology of Social Media through the Lens of Text Analysis
Cindy Chung and James W. Pennebaker (University of Texas - Austin)
How do the words we use reflect our personality, psychological states, and social groups? In this tutorial, we discuss computerized text analysis tools widely used in the social sciences. Particular attention will be devoted to word counting programs such as the one we have developed that references a dictionary of grammatical, psychological, and content word categories. Word counting programs such as Linguistic Inquiry and Word Count (LIWC; Pennebaker, Booth, & Francis, 2007) have been used to efficiently classify texts along psychological dimensions and to predict behavioral outcomes. By analyzing commonly used words such as pronouns, prepositions, and other function or junk words, it is possible to identify the language patterns and personalities of speakers and writers. We describe the rationale of our word counting approach, and highlight several applications – such as a lie detector, status decoder, or as remote sensor of group dynamics. Finally, we present novel ways in which the LIWC program is being applied for computer-mediated conversations and for thematic analyses for online social media. Participants will have the opportunity to test the LIWC software for the day on their own data and laptops, and to discuss issues specific to their research questions.
Cindy K. Chung is a Post Doctoral Fellow at the University of Texas, Austin. Her research focuses on the development and application of text analysis tools and methods for research questions in psychology. She examines how personality, psychological states, and social dynamics are reflected in word use.
James W. Pennebaker is Professor and Chair at the University of Texas, Austin. He studies the links between natural language and physical and mental health. More recent research focuses on the nature of language and range of psychological dynamics in the real world, including emotion, deception and social status.