Abstract:

Measuring effectiveness of information retrieval systems is essential for monitoring search quality in dynamic environments. In this merge, top-ranked documents in the merged result are employed to evaluate and rank the systems. As merging is a key component in a meta-search engine, the results from various search engines are collected and the meta-search system merges them into a single ranked list. We examine popular data fusion techniques designed to achieve improvements in effectiveness and clarify the conditions required for data fusion to show improvement.  The effectiveness of a meta-search engine is closely related to the result merging algorithm it employs. In this paper, we propose merging algorithm, based on a wide range of available information about the retrieved results, from their local ranks, their titles and subtitles, to the full documents of these results. Our approach is effective and outperforms the retrieved results as compared to previously proposed ranking methods.