Location-Based Top-k Term Querying over Sliding Window

摘要: In part due to the proliferation of GPS-equipped mobile devices, massive svolumes geo-tagged streaming text messages are becoming available on social media. It is great interest discover most frequent nearby terms from such tremendous stream data. this paper, we present novel indexing, updating, and query processing techniques that capable discovering top-k locally popular over a sliding window. Specifically, given location set within window, study problem searching for by considering both term frequency proximities between containing location. We develop efficient mechanism solve problem, including quad-tree based indexing structure, update technique, best-first algorithm. An empirical conducted show our proposed fit users’ requirements through varying number parameters.