Preference relations based unsupervised rank aggregation for metasearch

• We propose a preference relations based unsupervised rank aggregation algorithm.
• The algorithm gives weights to input rankers depending on their qualities.
• Ranker quality is estimated in unsupervised way using a variant of majority opinion.
• Performed experimental evaluation using supervised and unsupervised metrics.
• Kendall-Tau distance not suitable for evaluating metasearch algorithms.

Rank aggregation mechanisms have been used in solving problems from various domains such as bioinformatics, natural language processing, information retrieval, etc. Metasearch is one such application where a user gives a query to the metasearch engine, and the metasearch engine forwards the query to multiple individual search engines. Results or rankings returned by these individual search engines are combined using rank aggregation algorithms to produce the final result to be displayed to the user. We identify few aspects that should be kept in mind for designing any rank aggregation algorithm for metasearch. For example, generally equal importance is given to the input rankings while performing the aggregation. However, depending on the indexed set of web pages, features considered for ranking, ranking functions used etc. by the individual search engines, the individual rankings may be of different qualities. So, the aggregation algorithm should give more weight to the better rankings while giving less weight to others. Also, since the aggregation is performed when the user is waiting for response, the operations performed in the algorithm need to be light weight. Moreover, getting supervised data for rank aggregation problem is often difficult. In this paper, we present an unsupervised rank aggregation algorithm that is suitable for metasearch and addresses the aspects mentioned above.We also perform detailed experimental evaluation of the proposed algorithm on four different benchmark datasets having ground truth information. Apart from the unsupervised Kendall-Tau distance measure, several supervised evaluation measures are used for performance comparison. Experimental results demonstrate the efficacy of the proposed algorithm over baseline methods in terms of supervised evaluation metrics. Through these experiments we also show that Kendall-Tau distance metric may not be suitable for evaluating rank aggregation algorithms for metasearch.