Soboroff, I.
, Ounis, I.
and Macdonald, C.
(2012),
Overview of the TREC-2010 Blog Track, Proceedings of the Text REtrieval Conference (TREC 2010), [online], https://tsapps.nist.gov/publication/get_pdf.cfm?pub_id=910099
(Accessed April 19, 2024)
Official websites use .gov
A .gov website belongs to an official government organization in the United States.
Secure .gov websites use HTTPS
A lock (
) or https:// means you’ve safely connected to the .gov website. Share sensitive information only on official, secure websites.
Overview of the TREC-2010 Blog Track
Published
Author(s)
, Iadh Ounis, Craig Macdonald
Abstract
The Blog track aims to investigate the information seeking behavior in the blogosphere. The track was initiated in 2006, and has used an incremental approach in tackling several search tasks by their level of difficulty. In TREC 2010, the track has investigated two main search tasks: Faceted blog distillation: A blog search task where systems aim to retrieve bloggers (i.e. RSS feeds) that have a recurring and central interest in a topic X [6], and which also satisfy a number of facets (or attributes), representing the nature or the quality of the sought blogs (e.g. opinionated, factual). Top stories identification: A task that addresses news-related issues on the blogosphere, namely investigating whether the blogosphere can be leveraged to identify the top news stories of a given day in a real-time fashion. The task has also a search diversity flavor, where for a given story, a representative set of blog posts discussing the story from various perspectives is shown to the user.Citation
Proceedings of the Text REtrieval Conference (TREC 2010)
Pub Type
Others
Download Paper
Keywords
blog search, information retrieval
Citation
Created August 15, 2012, Updated February 19, 2017