International Conference on Weblogs and Social Media

Contact Information
For questions, please e-mail:


March 26-28, 2007

Tutorial: Search and Discovery in the Blogspace

Friday, January 19, 2007

We're happy to announce the first Tutorial of ICWSM which will be held the Sunday before the conference starts. More info soon, but...

Title: Search and Discovery in the Blogspace
Presenters: Gilad Mishne and Maarten de Rijke, University of Amsterdam


With the increasing number of blogs available, effective ways of searching and exploring blogs are becoming more and more important. The tutorial gives a survey of current activities in the area of blog search and discovery. It identifies important blog search and discovery tasks, describes blog-specific crawling, and then goes on to present effective ways of blog indexing and retrieval methods for addressing these tasks. We also cover several advanced topics in blog search, such as serving advertisements with retrieved results.

The tutorial is organized into three parts. The first part provides information retrieval background, defining concepts and methods used later in the tutorial, as well as surveying a number of publicly-available tools for the task. Additionally, it introduces search scenarios in blogs, deriving the user needs in this domain. The second part focuses on the areas where blog retrieval departs from other retrieval settings: the crawling process, and one search task characteristic of the blogspace—identifying opinions and thoughts about a topic. This part also surveys the recent efforts on blog opinion retrieval at TREC 2006. The last part of the tutorial discusses two additional search tasks: blog (rather than blog post) search, and tasks related to the timelined nature of blogs. It also introduces some advanced topics in the area, such as contextual advertising for blogs, and search in social-networking sites.

Background of presenters

Gilad Mishne is a graduate student at the Information and Language Processing Systems group at the University of Amsterdam; he recently completed his dissertation on applying text analytics methods in the blogspace. Gilad holds a B.Sc in computer science from the Technion and an M.Sc from the University of Amsterdam; prior to his graduate studies, he has spent several years in the industry as a software engineer. He is a regular contributor to blog research venues, and co-organized the TREC 2006 Blog track.

Maarten de Rijke is a Professor of Web Information Processing and Head of the Information and Language Processing Systems group at the University of Amsterdam. His research focuses on modeling, development and evaluation of intelligent access to web information. In his recent work he has also addressed blog retrieval and discovery. He was a co-organizer of the TREC 2006 Blog track and of several tracks at CLEF. He regularly teaches (web) information retrieval courses at the bachelor and masters level, and has previously taught tutorials at various international summer schools as well as national and international graduate schools.

posted by ICWSM at 11:33 AM  


Blaine said...

When will the full agenda be available?

2:27 PM  

Post a Comment

<< Home