Efficient Confident Search in Large Review Corpora

Given an extensive corpus of reviews on an item, a potential customer goes through the expressed opinions and collects information, in order to form an educated opinion and, ultimately, make a purchase decision. This task is often hindered by false reviews, that fail to capture the true quality of the item's attributes. These reviews may be based on insufficient information or may even be fraudulent, submitted to manipulate the item's reputation. In this paper, we formalize the Confident Search paradigm for review corpora. We then present a complete search framework which, given a set of item attributes, is able to efficiently search through a large corpus and select a compact set of high-quality reviews that accurately captures the overall consensus of the reviewers on the specified attributes. We also introduce CREST (Confident REview Search Tool), a user-friendly implementation of our framework and a valuable tool for any person dealing with large review corpora. The efficacy of our framework is demonstrated through a rigorous experimental evaluation.