| |||||||||||
WSCD 2013 : Workshop on Web Search Click Data | |||||||||||
Link: http://research.microsoft.com/en-us/um/people/nickcr/wscd2013 | |||||||||||
| |||||||||||
Call For Papers | |||||||||||
WSCD 2013 Call for Refereed Papers
---------------------------------- The WSCD 2013 chairs invite you to submit articles to the Third Workshop on Web Search Click Data. This workshop will be held in conjunction with WSDM 2013 on February 4, 2013, Rome, Italy. --A dataset will be provided to all participants. Web search click data has caught the interest of a growing community of professional during the last five years. It provides a snapshot of the typical information access patterns of the user population, unlike a group of relevance judges or the tags provided on collaborative sites. Issued queries and clicked document records have the potential to give an accurate view of millions of people's daily interests, how these interests evolve, how they are related, etc. Yet this information is not easily extracted because in spite of its abundance it is sparse, most queries are repeated only a few time if at all, and the clicktrhough rate cannot be interpreted as document relevance directly. Moreover, user clicks are strongly biased by the search engine ranking, which mean that many documents are never seen in spite of being relevant. Of particular interest is the relation between log data and the user decision process that generated it. A user interacting with a search engine might at any point decide to click on a new link, request a new page of results, reformulate his query, switch search engine or end the session. Understanding how a sequence of actions relates to the user satisfaction is key to improve the experience and the popularity of the search engine. This applies to web search in general but also to most verticals like "local search" and to newer research areas like "diversity" where the question is how to introduce diversity in document ranking or "personalization" where the goal is to adapt the search results to take into account what is known from the user who issued the query. In this workshop, we will attempt to address these issues but we will also explore novel applications and use of these data for enhancing the user search experience. Data Set -------- Research on the incorporation of click data into information retrieval systems, and for understanding user search, has been hampered by a lack of shared datasets. This workshop provides a common click dataset and a forum for presenting new results and analysis in the area. The dataset includes user sessions extracted from Yandex logs, with queries, URL rankings, clicks and also search engine switching actions. To allay privacy concerns the user data is fully anonymized. So, only meaningless numeric IDs of users, queries, sessions, and URLs are released. In contrast to last year WSCD workshop, the data does not contain editorial relevance judgments. Challenge --------- A challenge is running in parallel to this workshop. The evaluation will be purely data-driven and will be focused on predicting user search engines switches for a sample of held-out sessions. More details will be soon available at http://switchdetect.yandex.ru/en !!! Note that it is not obligatory neither to participate in the Challenge, nor to use the provided dataset to submit a paper to the workshop. WSCD welcomes papers using any search logs available to the authors. !!! Paper Format ------------ Submissions should present original results and new ideas. They must report original research not accepted or under submission to any journal or conference with public proceedings (previous submissions in informal workshops or as posters are allowed, but must be indicated). Submissions must be formatted according to ACM guidelines and style files http://www.acm.org/sigs/publications/proceedings-templates and can be up to 8 pages in length, including diagrams, references and appendices if any. A submitted paper must be self-contained. Submissions shorter than 8 pages are also encouraged. All papers will be peer-reviewed by at least three reviewers from an International Program Committee; promising papers will then be discussed in a meeting of PC chairs, where the final selections will be made. Accepted papers will appear online on the workshop website and a jointly authored report will be submitted to SIGIR Forum. Paper Submissions ----------------- Papers must be submitted in PDF format to the paper submission Web site (http://www.easychair.org/conferences/?conf=wscd2013). PDF files must have all non-standard fonts embedded. After upload, please check the copy stored on the site. Submission that do not view or print properly may be rejected without a chance to rectify the problem. Please contact wscd2013@yahoo.com for any questions. Important Dates for Paper Submissions Papers due: December 3, 2012 Notification of Acceptance: January 10, 2013 Camera-Ready: January 17, 2013 Workshop: February 12, 2013 Important Dates for the Challenge Start of Challenge: October 23, 2012 End of Challenge: December 22, 2012 at 13:00, Moscow time The workshop website can be found at http://research.microsoft.com/en-us/um/people/nickcr/wscd2013. |
|