Aggregation of web search engines based on users’ preferences in WebFusion

Improving minimax disparity model to determine the OWA operator weights

“…Keyhanipour et al [11] (see also Emrouznejad [8]) used OWA operators to rank the performance of the search engines, considering factors such as the average click rate, total relevancy of the returned results, and the variance of the clicked results, to calculate the relevancy measure. …”

“…Relevant items were scored as 2, irrelevant ones as 0, and undecided items as 1. One sample from the judgment of users which is extracted from Keyhanipour et al [11] is seen in Table 3; note this is the result of searching for a specific query only. Table 3 Judgment of users for a sample query and OWA score ða ¼ 0:75Þ.…”

CF-Rank: Learning to rank by classifier fusion on click-through data

“…As base classifiers Q, R and C are linear combinations of click-through features which their calculation scenarios are presented in section 4.2, they are independent and therefore, make uncorrelated errors with respect to one another. The Ordered Weighted Operators (OWA) operators were introduced by Yager (Yager, 1988) and its usefulness in approved in different applications such as web information retrieval systems (Keyhanipour et al, 2007), biology (Kazemian et al, 2005;Zakeri, Moshiri, & Sadeghi, 2011), intelligent transportation systems (Badello et al, 2011) and geography (Moradi, Delavar, & Moshiri, 2013). An OWA operator of dimension n is a mapping R R f n  :…”

“…However, raw search logs may contain large amount of useless logs such as images and scripts beside user behaviors. According to such observations, the concept of Click-through data was firstly A C C E P T E D M A N U S C R I P T 4 Dumais, 2006; Keyhanipour et al, 2007). Later, it was approved that click-through data could also be useful in the improvement of learning to rank methods (Dou et al, 2008;Macdonald & Ounis, 2009).…”

A3CRank: An adaptive ranking method based on connectivity, content and click-through data

“…Although, similar work has been done in the meta search engines area. For example in (Keyhanipour, Moshiri, & Kazemian, 2007), a solution for aggregation of results in meta search engines that uses click-through data and also the OWA operator for merging has been proposed. Also this method is adaptive and they have achieved interesting results through the aggregation of nine search engines.…”