Search engines evaluation using users efforts

The performance evaluation of search engines continues to become an research problem. Numerous researchers tried to measure the quality of information retrieval systems with different parameters and achieved several milestones. in case of graded relevance dependent measures, the Discounted Cumulative Gain metric exists that deals with the position of the retrieved results. In this paper, we present the task of learning rankings with the help of human assessment and click hits. we combined experts judgments about the results with the users clicks hits and found that this strategy is effective to assign ranking. The proposed ranking method can be seen as an extension of Expected Reciprocal Ranking that correlates better with clicks metrics than editorial metrics.