The problem of low-quality information on the Web is nowhere more important than in the domain of health, where unsound information and misleading advice can have serious consequences. The quality of health web sites can be rated by subject experts against evidence-based guidelines. We previously developed an automated quality rating technique (AQA) for depression websites and showed that it correlated 0.85 with such expert ratings. In this paper, we use AQA to filter or rerank Google results returned in response to queries relating to depression. We compare this to an unrestricted quality-oriented (AQA based) focused crawl starting from an Open Directory category and a conventional crawl with manually constructed seedlist and inclusion rules. The results show that post-processed Google outperforms other forms of search engine restricted to the domain of depressive illness on both relevance and quality.
%0 Conference Paper
%1 Tang:2009
%A Tang, Thanh
%A Hawking, David
%A Sankaranarayana, Ramesh
%A Griffiths, Kathleen M.
%A Craswell, Nick
%B ECIR '09 Proceedings of the 31th European Conference on IR Research on Advances in Information Retrieval
%C Berlin, Heidelberg
%D 2009
%I Springer
%K EBM search evidence retrieval
%T Quality-oriented Search for Depression Portals
%X The problem of low-quality information on the Web is nowhere more important than in the domain of health, where unsound information and misleading advice can have serious consequences. The quality of health web sites can be rated by subject experts against evidence-based guidelines. We previously developed an automated quality rating technique (AQA) for depression websites and showed that it correlated 0.85 with such expert ratings. In this paper, we use AQA to filter or rerank Google results returned in response to queries relating to depression. We compare this to an unrestricted quality-oriented (AQA based) focused crawl starting from an Open Directory category and a conventional crawl with manually constructed seedlist and inclusion rules. The results show that post-processed Google outperforms other forms of search engine restricted to the domain of depressive illness on both relevance and quality.
@inproceedings{Tang:2009,
abstract = {The problem of low-quality information on the Web is nowhere more important than in the domain of health, where unsound information and misleading advice can have serious consequences. The quality of health web sites can be rated by subject experts against evidence-based guidelines. We previously developed an automated quality rating technique (AQA) for depression websites and showed that it correlated 0.85 with such expert ratings. In this paper, we use AQA to filter or rerank Google results returned in response to queries relating to depression. We compare this to an unrestricted quality-oriented (AQA based) focused crawl starting from an Open Directory category and a conventional crawl with manually constructed seedlist and inclusion rules. The results show that post-processed Google outperforms other forms of search engine restricted to the domain of depressive illness on both relevance and quality.},
added-at = {2011-09-23T03:57:21.000+0200},
address = {Berlin, Heidelberg},
author = {Tang, Thanh and Hawking, David and Sankaranarayana, Ramesh and Griffiths, Kathleen M. and Craswell, Nick},
biburl = {https://www.bibsonomy.org/bibtex/2e10fc5b26bc35d58785f9ec62ad2ce47/diego_ma},
booktitle = {ECIR '09 Proceedings of the 31th European Conference on IR Research on Advances in Information Retrieval},
citeseerurl = {http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.156.5337},
interhash = {a67f3616ba84a8dd377a1db1e6b1bb9d},
intrahash = {e10fc5b26bc35d58785f9ec62ad2ce47},
keywords = {EBM search evidence retrieval},
library = {Web},
publisher = {Springer},
timestamp = {2011-09-23T03:57:21.000+0200},
title = {Quality-oriented Search for Depression Portals},
year = 2009
}