International Conference on Weblogs and Social Media

Contact Information
For questions, please e-mail:


March 26-28, 2007

CFP: International Conference on Weblogs and Social Media

March 26-28, 2007
Boulder, Colorado, U.S.A.

Availability of Data

Continuing the tradition from the WWE'06 workshop, we are once again offering a large blog dataset to conference participants. The data release comprises a complete set of weblog posts collected by Nielsen BuzzMetrics for May 2006 (consisting of about 14M posts from 3M weblogs). The data set includes the full content of the posts plus mark-up and represents an unprecedented collection for blog researchers. Our hope is that a communal dataset, approached from many different directions, will yield many interesting results. More information on the dataset, which is available for immediate download, can be found at:

Call For Papers

Recent years have seen a flourishing of social media - the promise of the WWW coming to fruition. Across the world, individuals can share opinions, experiences and expertise at the push of a button. There has been a fundamental shift thanks to significant advances in the ease of publishing content. Creating web content was for years the domain of tech-savvy people; now the barrier has been torn down.

Perhaps the most visible among the successes of social media in recent years is the blogosphere. Tens of thousands of new blogs are created every day; blog content is becoming ubiquitous, surfacing in news portals, search results and corporate public relations. Even those who are unaware of the blogosphere are still influenced by its content. Although blogs are highly visible currently, other forms of conversational spaces continue to flourish, especially message boards, mailing lists, review sites and Usenet.

Social media covers all forms of sharing: from photos, to videos, to recommendations. In the past few years, many examples of social media have become hugely successful. Flickr is a premier photo sharing site; has become a touchstone for sharing recommendations of websites; Web 2.0 applications in general abound with newcomers in the social media space.

One of the fascinating aspects of social media has been the drive from within to study the ecology as it evolves. People act at once as creators, observers and influencers of the space in which they participate. At the same time, businesses are quickly grasping the potential benefit to attending to the new space of social media. Monitoring the aggregate trends and opinions revealed by social media provides valuable insight to a number of business applications: marketing intelligence, competitive intelligence.

The fast growing blogosphere and social media space is a fruitful area for investigations across many disciplines. For example:

  • Natural language processing and machine learning researchers study the extraction of factual information from text; can blogs be processed in a robust manner and can knowledge bases be populated with facts from blogs?
  • Social network researchers and graph theory researchers are concerned with inferring community structure; analyzing the linkage patterns among blog entries can provide explicit community structure; can we infer implicit communities through the content of the blogs?
  • Political scientists are looking at ways of identifying influencers in a community; who are the influential bloggers whose voice is echoed by others?
  • Multimedia researchers are attempting to categorize audio and video content, aggregate information from diverse sources (textual, audio, video); can visual & audio social media be stored in a way that allows search across different modalities?
  • Market analysis researchers are concerned with what people think of the products and services of a company; can we process blogs automatically and find consumer complaints and breaking reports about vulnerabilities of products; also when does a burst of blogging activity become a trend?
  • Social psychologists study the response to current events, including emotional and attitudinal dimensions as well as content and patterns of influence.

Despite the growing relevance of blogs and social media, existing research has only begun to address the spectrum of issues that arise in their analysis. Blogs, for example, are a different kind of document than the relatively clean text that NLP research is based on. Such differences in term of structure, content and grammaticality will be a challenge considering that blogs will likely represent the most common way of publicly accessible personal expression.

Areas of interest

The conference aims to bring together researchers from different subject areas (e.g., computer science, linguistics, psychology, statistics, sociology, multimedia and semantic web technologies) and foster discussions about ongoing research in the following areas:

[01] AI methods for ethnographic analysis through social media.
[02]Blogosphere vs. mediasphere; measuring the influence of blogs on the media.
[03]Centrality/influence of bloggers/blogs; ranking/relevance of blogs; web pages ranking based on blogs.
[04]Crawling/spidering and indexing.
[05] Human Computer Interaction; social media tools; navigation.
[06]Multimedia; audio/visual processing; aggregating information from different modalities.
[07] Semantic analysis; cross-system and cross-media name tracking; named relations and fact extraction; discourse analysis; summarization.
[08]Semantic Web; unstructured knowledge management.
[09]Sentiment analysis; polarity/opinion identification and extraction.
[10]Social Network Analysis; communities identification; expertise discovery; collaborative filtering.
[11]Text categorization; gender/age identification; spam filtering.
[12] Time Series Forecasting; measuring predictability of phenomena based on social media.
[13]Trend identification/tracking.
[14]Visualization, aggregation and filtering.
[15]New social media applications, interfaces, interaction techniques.

Important dates

Submissions:December 8, 2006
Tutorial Proposals:December 15, 2006
Acceptance Notifications:February 2, 2007
Camera Ready Copies:February 16, 2007
Tutorials:March 25, 2007
Conference:March 26-28, 2007


People interested in participating should submit through the conference website a technical paper (up to 8 pages), a short paper (up to 4 pages), a poster or demo description (up to 2 pages) by midnight (PST) of Dec 8, 2006. Each submission should, to the extent possible, indicate a list of relevant areas from the list above (e.g., 03, 04, 10).


  • Natalie Glance, Nielsen BuzzMetrics.
  • Nicolas Nicolov, Umbria Inc.


  • Eytan Adar, Univ. of Washington.
  • Matthew Hurst, Nielsen BuzzMetrics.
  • Mark Liberman, Univ. of Pennsylvania.
  • Franco Salvetti, Univ. of Colorado at Boulder & Umbria Inc.

Local Chair

  • James H. Martin, Univ. of Colorado at Boulder.

Tutorials Chair

  • Belle Tseng, NEC Labs America, USA

Local Coordinator

  • Assad Jarrahian, Univ. of Colorado at Boulder

Program committee

  • Paolo Avesani, ITC-irst, Italy
  • Bran Boguraev, IBM Research, USA
  • Chris Brooks, Univ. of San Francisco, USA
  • Claire Cardie, Cornell Univ., USA
  • Scott Carter, UC Berkeley, USA
  • Steve Cayzer, HP Labs Bristol, UK
  • Thierry Declerck, DFKI Language Lab, Germany
  • Donghui Feng, ISI, Univ. of Southern California, USA
  • Tim Finin, Univ. of Maryland, Baltimore County, USA
  • Kathy Gill, Univ. of Washington, USA
  • Michelle Gumbrecht, Stanford Univ., USA
  • John Henderson, MITRE, USA
  • Eduard Hovy, ISI, USC, USA
  • Assad Jarrahian, Univ. of Colorado at Boulder
  • Jussi Karlgren, SICS, Sweden
  • Laura Knudsen, OSC, USA
  • Moshe Koppel, Bar-Ilan Univ., Israel
  • Cameron Marlow, Yahoo! Research, USA
  • Lluis Marquez, Univ. Poli. de Catalunya, Spain
  • Rada Mihalcea, Univ. of North Texas, USA
  • Gilad Mishne, Univ. of Amsterdam, The Netherlands
  • Tomoyuki Nanno, Google, Japan
  • Apostol Natsev, IBM Research, USA
  • Kamal Nigam, Google, USA
  • Peter Norvig, Google Inc., USA.
  • Jon Oberlander, Univ. of Edinburgh, Scotland
  • Peter Pirolli, PARC, USA
  • Oana Postolache, Univ. of Saarland, Germany
  • John Prager, IBM Research, USA
  • Alessandro Provetti, Univ. of Messina, Italy
  • Drago Radev, Univ. of Michigan, USA
  • Jonathon Read, Univ. of Sussex, UK
  • Maarten de Rijke, Univ. of Amsterdam, The Netherlands
  • Laura Ripamonti, Univ. of Milan, Italy
  • Irina Rish, IBM Watson Research Center, USA
  • Dan Roth, Univ. of Illinois at Urbana-Champaign, USA
  • James G. Shanahan, Turn Inc., USA
  • Emma Shen, OSC, USA
  • Suresh Sood, Univ. of Tech. Sydney, Australia
  • Savitha Srinivasan, IBM Research, USA
  • Carlo Strapparava, ITC-irst, Italy
  • V.S. Subrahmanian, Univ. of Maryland, USA
  • Belle Tseng, NEC Labs America, USA
  • Janyce M. Wiebe, Univ. of Pittsburgh, USA
  • Tong Zhang, Yahoo Research, USA
  • Liang Zhou, ISI, University of Southern California, USA
  • Ethan Zuckerman, Berkman Center, Harvard Univ., USA.


The conference will take place at Marriott Boulder ( located near downtown Boulder, Colorado.


  • Google, Inc.
  • Microsoft Live Labs
  • NEC Labs America
  • Sphere


  • Nielsen BuzzMetrics
  • Umbria, Inc.
  • University of Pennsylvania
  • University of Maryland, Baltimore County

ICWSM is endored by the IW3C2 ( and AAAI (


The International Conference on Weblogs and social media grew out of two events: the annual series of Workshops on the Weblogging Ecosystem (WWE 2006, WWE 2005, WWE 2004) held in conjunction with the International World Wide Web Conference and the Spring Symposium organized by the American Association for Artificial Intelligence (AAAI) on Computational Approaches to Analyzing Weblogs (CAAW 2006).


a [JPG] of our e-mail