Spatial, Temporal, and Textual Retrieval and Analysis of Geotagged Posts
Mehta, Paras · Universitätsbibliothek der FU Berlin Hochschulschriftenstelle u. Dokumentenserver · 2018
The proliferation of GPS-equipped mobile devices, as well as online social networks, has led to the creation of increasingly large volumes of spatio- textual data, i.e., data containing spatial and textual information, such as geotagged messages on Twitter and reviews for restaurants on Foursquare. Similarly, a growing amount of Internet searches now carry a spatial intent. From looking up nearby grocery stores to searching for local news, we increasingly use the Internet to find local information. Due to these factors, queries combining spatial and textual predicates, termed spatial keyword queries, have been studied extensively over the past few years. Different types of spatial keyword queries have been studied in the literature, ranging from the simplest that retrieve the top-k relevant objects to more complex variants that identify groups of objects jointly satisfying the query. Still, the majority of existing research focuses mainly on static settings, such as searching for information about places. In contrast, social networks are a dynamic source of crowdsourced spatio-textual data in the form of geotagged posts (e.g., tweets, check-ins) made by users, which is being produced in large amounts and is evolving continuously. These characteristics of geotagged posts create several new opportunities and challenges, and call for the enhancement of existing techniques to handle this type of data. Thus, in this thesis, we present novel techniques for the retrieval and analysis of geotagged posts. Initially, since posts consist of not only spatial and textual attributes, but also temporal information, we extend spatio-textual access methods to support spatial-temporal-textual filtering of trajectories generated via social networks. Following this, considering that the number of results found by this plain filtering can be quite high, and thus overwhelming for users, we propose a new method for identifying a small set of representative posts for a given spatial-temporal-textual filter, to allow spatio-temporal exploration of the large number of relevant posts. Nevertheless, these results can quickly become outdated with time as fresh posts are made. Thus, in our subsequent analysis, we propose methods for continuously maintaining a concise summary of a stream of posts within a sliding window, and updating the summary dynamically as the window slides. Finally, given their crowdsourced nature, geotagged posts are a rich source of people’s local knowledge and opinions, which we exploit by inferring two types of patterns. First, we develop a system for the discovery and exploration of local hotspots of certain keywords, termed locally trending topics. In the second, we use the digital trails generated by mobile users posting on social networks for mining thematic associations among groups of locations.