FAST: Frequency-Aware Spatio-Textual Indexing for In-Memory Continuous Filter Query Processing

The ubiquity of spatio-textual data comes from the popularity of GPS-enabled smart devices, e.g., smartphones. These devices provide a platform that supports a wide range of applications that generate and process spatio-textual data. These applications include social networks, micro-blogs, web-search for local attractions and events, and location-aware ad targeting. These applications need to process massive amounts of spatio-textual data in real-time. For example, in location-aware ad targeting systems, it is required to disseminate millions of ads and promotions to millions of users based on the locations and textual profiles of users. To support this data scale, these applications require efficient spatio-textual indexing. There exist several related spatio-textual indexes that typically integrate a spatial index with a textual index. However, these indexes usually have a high demand for main-memory and assume that the entire vocabulary of keywords is known in advance. Also, these indexes do not successfully capture the variations of the frequencies of keywords across different spatial regions and treat frequent and infrequent keywords similarly. Moreover, existing indexes do not adapt to the changes in workload over space and time. For example, some keywords may be trending at certain times in certain locations and this may change as time passes. To maintain high performance, the index needs to adapt to these changes. In this paper, we introduce FAST, a F requency-Aware Spatio-T extual index. FAST is a main-memory index that requires up to one third of the memory needed by the state-of-the-art index. FAST does not assume prior knowledge of the entire vocabulary of indexed objects. FAST accounts for the frequencies of keywords within their corresponding spatial regions to automatically choose the best indexing approach that optimizes the insertion and search times. Extensive experimental evaluation using two real datasets demonstrates that FAST is up to 3x faster in search time and 5x faster in insertion time than the state-of-the-art indexes.