Keeping an eye on moving objects: processing continuous spatial-keyword range queries

With the emergence of GPS-equipped portable devices and Online Social Networks, geo-tagged textual data have been highly produced on a continuous basis, which can provide important information for various applications, such as marketing, disaster response, and so on. Therefore, processing continuous spatial-keyword queries over streaming data is a hot topic for the research community nowadays. However, applying such queries to moving objects is computationally expensive due to the frequent updates of objects' information that will continuously change the queries' answers. Few research works focus on processing spatial-keyword queries over moving objects, so this problem demands more exploration by research. This paper proposes Lagic; a cloud-based solution scheme to process continuous spatial-keyword range queries over moving objects. Lagic is the first model that provides an exact solution to the problem and minimizes the overhead on users' devices. A parallelized in-memory indexing structure is proposed to ensure the efficiency and scalability of Lagic. Short-term Safe Regions and a new approach for Buffer Regions are presented to reduce the number of required computations to update queries' answer sets in an incremental manner. Evaluations show that Lagic can reduce the total processing time to seven folds less than a baseline model. It also provides better computational scalability and efficiency. Furthermore, Lagic shows stability in continuous running time against variations of queries' and objects' attributes.