Comparing rankings of search results on the Web

@article{citeulike:405519, abstract = {The Web has become an information source for professional data gathering. Because of the vast amounts of information on almost all topics, one cannot systematically go over the whole set of results, and therefore must rely on the ordering of the results by the search engine. It is well known that search engines on the Web have low overlap in terms of coverage. In this study we measure how similar are the rankings of search engines on the overlapping results.We compare rankings of results for identical queries retrieved from several search engines. The method is based only on the set of URLs that appear in the answer sets of the engines being compared. For comparing the similarity of rankings of two search engines, the Spearman correlation coefficient is computed. When comparing more than two sets Kendall's W is used. These are well-known measures and the statistical significance of the results can be computed. The methods are demonstrated on a set of 15 queries that were submitted to four large Web search engines. The findings indicate that the large public search engines on the Web employ considerably different ranking algorithms.}, author = {Bar-Ilan, Judit }, citeulike-article-id = {405519}, comment = {The findings indicate that the large public search engines on the Web employ considerably different ranking algorithms. }, doi = {10.1016/j.ipm.2005.03.008}, journal = {Information Processing \& Management}, keywords = {relevance}, month = {December}, number = {6}, pages = {1511--1519}, posted-at = {2005-11-23 11:50:58}, priority = {2}, title = {Comparing rankings of search results on the Web}, url = {http://portal.acm.org/citation.cfm?id=1103329.1103343}, volume = {41}, year = {2005} }

TY - JOUR ID - citeulike:405519 L3 - citeulike-article-id:405519 TI - Comparing rankings of search results on the Web JF - Information Processing & Management VL - 41 IS - 6 SP - 1511 EP - 1519 N2 - The Web has become an information source for professional data gathering. Because of the vast amounts of information on almost all topics, one cannot systematically go over the whole set of results, and therefore must rely on the ordering of the results by the search engine. It is well known that search engines on the Web have low overlap in terms of coverage. In this study we measure how similar are the rankings of search engines on the overlapping results.We compare rankings of results for identical queries retrieved from several search engines. The method is based only on the set of URLs that appear in the answer sets of the engines being compared. For comparing the similarity of rankings of two search engines, the Spearman correlation coefficient is computed. When comparing more than two sets Kendall's W is used. These are well-known measures and the statistical significance of the results can be computed. The methods are demonstrated on a set of 15 queries that were submitted to four large Web search engines. The findings indicate that the large public search engines on the Web employ considerably different ranking algorithms. KW - relevance N1 - The findings indicate that the large public search engines on the Web employ considerably different ranking algorithms. AU - Bar-Ilan, Judit PY - 2005/12// UR - http://portal.acm.org/citation.cfm?id=1103329.1103343 ER -