Efficient Processing of Relevant Nearest-Neighbor Queries

Novel Web technologies and resulting applications have led to a participatory data ecosystem that, when utilized properly, will lead to more rewarding services. In this work, we investigate the case of Location-Based Services, specifically how to improve the typical location-based Point-of-Interest (POI) request processed as a k-Nearest-Neighbor query. This work introduces Links-of-Interest (LOI) between POIs as a means to increase the relevance and overall result quality of such queries. By analyzing user-contributed content in the form of travel blogs, we establish the overall popularity of an LOI, that is, how frequently the respective POI pair was visited and is mentioned in the same context. Our contribution is a query-processing method for so-called k-Relevant Nearest Neighbor (k-RNN) queries that considers spatial proximity in combination with LOI information to retrieve close-by and relevant (as judged by the crowd) POIs. Our method is based on intelligently combining indices for spatial data (a spatial grid) and for relevance data (a graph) during query processing. Using landmarks as a means to prune the search space in the Relevance Graph, we improve the proposed methods. Using in addition A*-directed search, the query performance can be further improved. An experimental evaluation using real and synthetic data establishes that our approach efficiently solves the k-RNN problem.