id	author	title	date	pages	extension	mime	words	sentences	flesch	summary	cache	txt
cord-027431-6twmcitu	Mukhina, Ksenia	Spatiotemporal Filtering Pipeline for Efficient Social Networks Data Processing Algorithms	2020-05-25		.txt	text/plain	5461	308	61	To do that we propose a spatiotemporal data processing pipeline that is general enough to fit most of the problems related to working with LBSNs. The proposed pipeline includes four main stages: an identification of suspicious profiles, a background extraction, a spatial context extraction, and a fake transitions detection. Efficiency of the pipeline is demonstrated on three practical applications using different LBSN: touristic itinerary generation using Facebook locations, sentiment analysis of an area with the help of Twitter and VK.com, and multiscale events detection from Instagram posts. Thus, all studies based on social networks as a data source face two significant issues: wrong location information stored in the service (wrong coordinates, incorrect titles, duplicates, etc.) and false information provided by users (to hide an actual position or to promote their content).	./cache/cord-027431-6twmcitu.txt	./txt/cord-027431-6twmcitu.txt