@inproceedings{fetterly2009measuring,
author = {Fetterly, Dennis and Craswell, Nick and Vinay, Vishwa},
title = {Measuring the Search Effectiveness of a Breadth-First Crawl},
booktitle = {Proceedings of the 31st European Conference on Information Retrieval (ECIR)},
year = {2009},
month = {April},
abstract = {Previous scalability experiments found that early precision improves as collection size increases. However, that was under the assumption that a collection's documents are all sampled with uniform probability from the same population.  We contrast this to a large breadth-first web crawl, an important scenario in real-world Web search, where the early documents have quite different characteristics from the later documents. Having observed that NDCG@100 (measured over a set of reference queries) begins to plateau in the initial stages of the crawl, we investigate a number of possible reasons for this behaviour. These include the web-pages themselves, the metric used to measure retrieval effectiveness as well as the set of relevance judgements used.},
publisher = {Springer Verlag},
url = {http://approjects.co.za/?big=en-us/research/publication/measuring-the-search-effectiveness-of-a-breadth-first-crawl/},
edition = {Proceedings of the 31st European Conference on Information Retrieval (ECIR) },
}