Application of search engine focusing on trend-related queries to market of data.

This paper examines the applicability of a search engine focusing on trend-related queries to the market of data. As the task of answering trend-related queries is supposed to be common in various domains, we expect it could be used for various purposes. As one of promising target domain for the proposed search engine, we focus on the market of data, where value creation from data fusion is crucial activity. As many data resources from various domains have temporal characteristics in common, the proposed search engine can be useful for finding connection between different data resources in terms of temporal trend. This paper describes the proposed search engine, and shows the result of a user study, in which test participants used it to find relationship between items. The result shows the participants could find related items from various viewpoints. The improved version of an interface for submitting queries is also introduced, which is shown to be effective for suppressing incorrect queries. [ABSTRACT FROM AUTHOR]