Overview of the TREC-2008 Blog Track
GLASGOW UNIV (UNITED KINGDOM)
Pagination or Media Count:
The Blog track explores the information seeking behaviour in the blogosphere. The track was introduced in 2006, with a main pilot search task, namely the opinion-finding task. In TREC 2007, the track investigated two main tasks inspired by the analysis of a commercial blog-search query log the opinion-finding task and the blog distillation task. In addition, the Blog 2007 track investigated a natural extension to the opinion-finding task, namely the polarity task. All tasks thus far investigated in the Blog track have used the so-called Blogs06 collection, which was created by the University of Glasgow. The Blogs06 collection was crawled over an 11-week period from 6th December 2005 until the 21st February 2006. The collection is 148GB in size, consisting of 38.6GB of feeds, 88.8GB of permalink documents, and 28.8GB of homepages. For TREC 2008, the track continued using the Blogs06 collection. It also continued investigating the opinion-finding, polarity, and blog distillation tasks. In addition, the Blog track 2008 introduced a baseline blog post retrieval task, to encourage participants to study the impact of their opinion-finding techniques across different underlying topic relevance baselines. As a consequence, following our conclusions from both the TREC 2006 and the Blog 2007 tracks, we structured the Blog track 2008 around four tasks 1 Baseline ad hoc blog post retrieval task 2 Opinion-finding blog post retrieval task 3 Polarity opinion-finding blog post retrieval task and 4 Blog feed distillation task.
- Information Science