CFP: AIRWeb 2007
URL (Conference): http://airweb.cse.lehigh.edu/2007/
URL (Call for Papers): http://airweb.cse.lehigh.edu/2007/cfp.html
AIRWeb is a series of international workshops focusing on Adversarial Information Retrieval on the Web that brings together both researchers and industry practitioners, to present and discuss advances in the state of the art.
This year, AIRWeb'2007 will be co-located with the WWW'07 conference in Banff, Canada. The workshop will include a Web Spam challenge that will test different spam detection techniques on a shared reference collection. Accepted papers will be posted on the ACM Digital Library.
Important dates
7 February 2007: E-mail intention to submit (optional, but helpful)
15 February 2007: Deadline for submissions — see Call for Papers
15 March 2007: Notifications
30 March 2007: Camera-ready copy due
30 March 2007: Submissions to the Web Spam challenge due.
8 May 2007: Date of workshop
Overview
The ubiquitous use of search engines to discover and access internet content shows clearly the success of information retrieval algorithms. However, unlike controlled collections, the vast majority of the Web pages lack an authority asserting their quality. This openness of the Web has been the key to its rapid growth and success, but this openness is also a major source of new adversarial challenges for information retrieval methods.
Adversarial Information Retrieval addresses tasks such as gathering, indexing, filtering, retrieving and ranking information from collections wherein a subset has been manipulated maliciously. On the Web, the predominant form of such manipulation is "search engine spamming" or spamdexing, i.e., malicious attempts to influence the outcome of ranking algorithms, aimed at getting an undeserved high ranking for some items in the collection. There is an economic incentive to rank higher in search engines, considering that a good ranking on them is strongly correlated with more traffic, which often translates to more revenue.
This, the third AIRWeb workshop, builds on the previous successful meetings at Chiba, Japan as part of WWW2005, and at Seattle, USA as part of SIGIR2006. This workshop provides a focused venue for both mature and early-stage work in web-based adversarial IR.
We solicit both full and short submissions on any aspect of adversarial information retrieval on the Web. Particular areas of interest include, but are not limited to:
-Link spam: nepotistic linking, collusion, link farms, link exchanges and link bombing.
-Content spam: keyword stuffing, phrase stitching, and other techniques for generating synthetic text.
-Cloaking: sending different content to a search engine than to regular visitors of a web site, which is often used in combination with other spamming techniques.
-Comment spam in legitimate sites: in blogs, forums, wikis, etc.
-Spam-oriented blogging: splogs, spings, etc
-Click fraud detection: including forging clicks for profit, or to deplete a competitor's advertising funds
-Reverse engineering of ranking algorithms
-Web content filtering: as used by governments, corporations or parents to restrict access to inappropriate content
-Advertisement blocking: developing software for blocking advertisements during browsing
-Stealth crawling: crawling the Web while avoiding detection
-Malicious tagging: for injecting keywords or for self-promotion in general
Papers addressing higher-level concerns, e.g., whether "open" algorithms can succeed in an adversarial environment, whether permanent solutions are possible, how the problem has evolved over years, what are the differences between "black-hat", "white-hat", and "gray-hat" techniques, where is the line between search engine optimization and spamming, etc., are also welcome.
At least three anonymous reviews will be provided per paper, judged on the basis of relevance, originality, quality, and presentation. Proceedings of the workshop will be included in the ACM Digital Library. Substantially longer papers may also be submitted to ACM Transactions on the Web (TWEB): special issue on adversarial issues in Web search.
Full papers are limited to 8 pages; work-in progress will be permitted 4 pages. See submission instructions for details.
Web Spam Challenge
This year, we are introducing a novel element: a Web Spam Challenge for testing web spam detection systems. We will be using the WEBSPAM-UK2006 collection for Web Spam Detection that comprises a large set of web pages, a web graph, and human-provided labels for a set of hosts. To reduce the amount work due to data processing, we will also provide a set of features extracted from the contents and links in the collection, which may be used by the participant teams in addition to any automatic technique they choose to use.
We ask that participants of the Web Spam Challenge submit predictions (normal/spam) for all unlabeled hosts in the collection. Predictions will be evaluated and results will be announced at the AIRWeb 2007 workshop. See the Web Spam Challenge website for details.
Participation on the challenge does not require a paper submission, and researchers submitting papers are not required to participate in the challenge. However, we encourage that participants of the Web Spam Challenge also submit research articles describing their systems, and we encourage authors submitting research articles on Web Spam detection to participate in the challenge.
