News

**New** Workshop Program is online.

**New** Confirmed Keynote Speakers. 

**New** Poster format: Please take the SIGIR poster format. 

**New** Camera ready instruction: please submit your CRC before June 21st. A few papers will be recommended to JCST. A following up email will be sent to those papers. 

**New** Call for papers announced. 

Workshop Program

Keynotes 

• James Allan, UMass Amherst

Title:  Search and Mining Challenges for Crowds in a Crisis

Abstract: We have all heard stories of the importance of social media in the context of a human crisis: from understanding what is happening during political upheaval, to locating survivors of a natural disaster, to collecting donations to support aid workers responding to the situation.  This talk discusses the uses of information retrieval approaches in this context, actual, possible, and desirable.  How can IR methods be used to sift through rapidly arriving and accumulating data to find changes and surprises?  How can the useful information be separated from the useless?  What is important, what is interesting, and who should be alerted?  Are these questions any different from traditional IR research problems?  If so, how?

Bio: James Allan is a Professor in the Department of Computer Science at the University of Massachusetts Amherst (UMass). He co-directs the Center for Intelligent Information Retrieval (CIIR), the well-known research organization in Information Retrieval and related fields. Allan’s research focuses on interactive information retrieval and organization, including retrieval models, browsing and other human-computer interactions, topic detection and tracking, automatic information organization, and evaluation of information systems. Allan has served on the editorial board of two major journals in the field and was recently elected Chair of the ACM SIGIR organization. He is the author of more than 100 refereed conference and journal publications in the field of IR and has chaired the PhD committees of 14 graduated students in the area.

• Tat-Seng Chua, National University of Singapore

Title: Extracting Structured Knowledge from User-Generated Information Sources

Abstract: The emergence of social networking sites has given rise to a huge amount of user-generated contents (UGCs). Through these social sites, users share (multimedia) contents, pose comments, ask questions, provide answers, and tweet about their recent pursuits. The contents accumulated have evolved into a huge unstructured source of timely knowledge. The ability to organize this knowledge will help to unlock the rich user-generated contents to better understand the current information needs of users as well as to support trend and sentiment analysis, retrieval and question answering. To accomplish this, our research aims to automatically mine an initial prototype hierarchy of the question topic by leveraging on the domain knowledge encoded in the Web, Wikipedia or product manuals. We then develop a prototype-hierarchy based clustering framework that utilizes the category structure information of initial prototype hierarchy as well as the distribution of relevant UGCs around the topic to perform information organization based on a multi-criterion optimization function. We apply this framework to organize and fuse the UGCs in question-answering, forums, photos sharing and check-in sites. This talk discusses our research to transform the unstructured and evolving UGCs into knowledge structures. The talk also outlines a large-scale 5-year collaborative effort between Tsinghua and NUS to mine and structure UGCs in Singapore and Beijing.

Bio: Chua Tat-Seng the KITHC Chair Professor at the School of Computing, National University of Singapore (NUS). He was the Acting and Founding Dean of the School of Computing during 1998-2000. He joined NUS in 1983, and spent three years as a research staff member at the Institute of Systems Science (now I2R) in the late 1980s. Dr Chua's main research interest is in multimedia information retrieval, in particular, on the analysis, retrieval and question-answering (QA) of text and image/video information. He is currently working on several multi-million-dollar projects: interactive media search, local contextual search, and real-time extreme search. He is the co-Director of the NUS-Tsinghua Center for Extreme Search.
    Dr Chua has organized and served as program committee member, area chair and technical co-chair of numerous international conferences in the areas of computer graphics, multimedia and text processing. He is the conference co-chair of ACM Multimedia 2005, CIVR (Conference on Image and Video Retrieval) 2005, and ACM SIGIR 2008. He is the Technical Program co-Chair of ACM SIGIR 2011. He serves in the editorial boards of: ACM Transactions of Information Systems (ACM), Foundation and Trends in Information Retrieval (NOW), The Visual Computer (Springer Verlag), and Multimedia Tools and Applications (Kluwer). He sits in the steering committee of ICMR (International Conference on Multimedia Retrieval), Computer Graphics International, and Multimedia Modeling conference series; serves as member of International Review Panels of two large-scale research projects in Europe; and as independent director of 2 public listed companies in Singapore.

Objectives

SWSM 2011 will take place in Beijing, China on July 28, 2011 during the 34th Annual International ACM SIGIR conference. The aim of the workshop is to provide a forum for researchers and practitioners to discuss ideas related to searching and mining the social Web, with a special focus on the analysis of user generated content during human crises (e.g., earthquakes, terrorist attacks, etc.).

The ubiquitous nature of Web-enabled devices, including desktops, laptops, tablets, and mobile phones, enables people to participate and interact with each other in various Web communities. Examples of such communities include forums, newsgroups, blogs, microblogs, bookmarking services, photo sharing platforms, and location-based services. Hence, the rapidly evolving social Web provides a platform for communication, information sharing, and collaboration. A vast amount of heterogeneous data (composed of e.g., text, photos, video, links) has been generated by the users of various social communities, which offers an unprecedented opportunity for studying novel theories and technologies for social Web search and mining.

The goal of the workshop is to provide a forum for discussing and exploring social media topics related to Web search and information retrieval, Web mining, social network analysis, semantic Web, natural language processing, and computational advertising. In addition to paper presentations, we will solicit invited talks and a panel that will stress the interdisciplinary challenges of social search and mining. 

Special Theme: Social Web Search and Mining Under Crisis

Natural and man-made disasters are particularly important classes of events that are of interest to affected populations, governments, disaster response teams, and aid organizations. Information about such events can be gathered from various sources. While traditional news sources provide authoritative disaster information, self-publishing media such as blogs, Facebook, and Twitter can contribute immediate, personalized eye-witness information. However, there are many challenges involved when dealing with such data sources, especially when time is of the essence, as is often the case with human crises. Information is often incomplete, contradictory, fictitious, and changing. As a result, information is the least organized when users need it most.

To highlight the importance of this emerging area, "Social Web Search and Mining Under Crisis" will serve as the workshop's special theme. Along these lines, the workshop seeks submissions that leverage news, social media, and user generated content to predict, analyze, understand, and help cope with events related to human crises, such as earthquakes, campus shootings, hurricanes, influenza pandemics, terrorist attacks, and oil spills. Novel applications, methods, and use of real-world data sets are particularly encouraged.

A special session during the workshop will be devoted to papers that directly address the theme.

Topics of Interest

We welcome papers in all areas of social Web search and data mining, especially those that address the special theme or are inter-disciplinary in nature. Examples of relevant topics include:

• Search and mining algorithms for large-scale social networks
  
• Real-time social search and mining infrastructures
  
• Microblog (e.g., Twitter, QQ, Jaiku) search and mining
  
• Search across heterogeneous user generated content
  
• Content aggregation, summarization, and reasoning across multiple data streams
  
• Personalized search for social interactions
  
• Credibility and provenance of social Web content
  
• Computational advertising for user generated content
  
• Cross-media search and mining of user generated content
  
• Collaborative filtering and recommender systems
  
• Community detection and network evolution analysis
  
• Sentiment analysis/opinion mining
  
• Social network analysis and social influence analysis
  
• Spam detection of social media
  
• Geospatial and temporal analysis of social media
  
• Applications of social search and mining
• Detecting and preventing false alarms in social media

Deadlines and Submission Guidelines

Submission deadline: May 15th, 2011

Notification date: June 1st, 2011

Camera ready: June 21st, 2011

Workshop: July 28, 2011

The best papers will be invited to submit their extensions to the JCST special issue on Data Mining on Social Networks and Social Web (SCI Indexed). Papers should be no more than 10 pages total in length, where up to 8 pages (including appendices, if any) are used for the content of the paper and the final two pages are used only for references. All submissions must be prepared using the ACM camera‐ready template (available at http://www.acm.org/sigs/pubs/proceed/template.html). Authors are required to submit their papers electronically in PDF format to the paper submission site.  All submissions should clearly present the author information including the names of the authors, the affiliations and the emails.

Organizing Committee

• Fernando Diaz, Yahoo! Labs, diazf@yahoo-inc.com
• Eduard Hovy, Information Sciences Institute, hovy@isi.edu
• Irwin King, AT&T Labs Research, San Francisco, USA, irwinking@gmail.com 
• Juanzi Li, Tsinghua University, China, ljz@keg.cs.tsinghua.edu.cn 
• Donald Metzler, Information Sciences Institute, metzler@isi.edu
• Marie-Francine Moens, Katholieke Universiteit Leuven, Belgium, marie-francine.moens@cs.kuleuven.be 
• Jie Tang, Tsinghua University, China, jietang@tsinghua.edu.cn 
• Lei Zhang, Microsoft Research Asia, leizhang@microsoft.com

Program Committee

• Omar Alonso, Microsoft, USA
• Roi Blanco, Yahoo!, Barcelona
• Keke Cai, IBM China Research Lab, CN    
• Carlos Castillo, Yahoo! Labs, Spain
• Hong Cheng, The Chinese University of Hong Kong, HK  
• Isaac Councill, Pennsylvania State University, US
• Gregory Grefenstette, Exalead, France
• Karl Gyllstrom, K.U. Leuven, Belgium
• Kathy Mckeown, Columbia University, USA
• Gabriella Pasi, University di Milano Bicocca, Italy        
• Ana-Maria Popescu, Yahoo! Labs, USA
• Kunal Punera, Yahoo! Research, USA  
• Hema Raghavan, IBM Research, USA
• Maarten de Rijke, University of Amsterdam, The Netherlands
• Pavel Serdyukov, Yandex, Russia