DBExplorer: Exploratory search in databases

Abstract

A traditional relational database can evaluate complex queries but requires users to precisely express their information need. But users often do not know what information is available in a database, and hence cannot correctly express their information need. Traditional databases do not provide convenient means for users to gain familiarity with the data. In this paper, we study the problem of exploratory search, which a user may wish to perform to get an understanding of the data set. We note that users often have some decisions already made, so what they need is not an overall database summary, but rather a summary “in context” of the relevant portion of the database. Towards this end, we devise a novel data summarization technique called the Conditional Attribute Dependency (CAD) View, which shows the conditional dependencies between attribute values conditioned on applied selections. The CAD View can help users to gain familiarity with structured datasets in an attribute-wise manner. To evaluate the CAD View, we perform a user study comprising three complex exploratory tasks on a real dataset. Our studies show that users are able to do all the tasks about 4-5 times faster and with better accuracy using the CAD View compared to the data summary shown in faceted navigation, which is currently the most popular search interface for e-commerce and has support for exploratory search.