The investigation of human activity in location-based social networks such as Twitter is one promising example of exploring spatial structures in order to infer underlying mobility patterns. Previous work regarding Twitter analysis is mainly focused on the spatiotemporal classification of events. However, since the information about the occurrence of a general event can in many cases be considered as given, one identified research gap is the exploration of human spatial behavior within specific mass events to potentially characterize underlying, locally occurring mobility clusters. One key challenge is to explore whether this noisy biased dataset can be a reliable source for the knowledge discovery of human mobility during mass events. In this paper we therefore present an advanced methodologycal framework, including a generative semantic topic modeling and local spatial autocorrelation approach, to observe both spatiotemporal and semantic clusters during a major sports event in Boston in the US. Our results of the observed spatiotemporally and semantically clustered tweets within the selected case study area have shown the possibility of deriving intra-urban event related mobility patterns with similar spatiotemporal movement.

In this paper, we propose a framework to detect human mobility transportation hubs and infer public transport flows from unstructured georeferenced social media data using semantic topic modeling and spatial clustering techniques. An infrastructure for receiving and storing large sets of social media data has been developed together with an ad hoc processing framework in order to consider the high uncertainty of our retrieved data. Given the detected and extracted social media signals indicating human mobility, we compared the results with the public transport network from OpenStreetMap and classified observed mobility patterns for an exemplary case study. To analyze collected datasets a web based visualization tool has been setup.

EVE Online is a massively multiplayer online roleplaying game (MMORPG) taking place in a large galaxy consisting of about 7 500 star systems. In comparison to many other online role-playing games, the users interact in the same instance of a persistent player-driven universe. Given the number of simultaneous pilots online at the same time - a number which at times reaches up to more than 50 000 concurrent accounts logged on to the same server - the EVE Online universe can present atypically difficult load-balancing challenges when the users decide to operate in a coordinated fashion, for example, to launch an attack on a particular system. We will present an scalable, automated statistical method for predicting such unexpected user gatherings by considering the evolving shortest-path distances from each user to each system. Here we present a case study analyzing nearly 300 million user movements in the EVE Online universe from over 700 thousand user accounts over a period of three months. We demonstrate an ability to predict sudden spikes in user presence (corresponding to actual events) before they happen, suggesting our techniques could be useful for automated load-balancing in such massive online games

During the past years the interest in the exploitation of mobility information has increased significantly. A growing number of companies and research institutions are interested in the analysis of mobility data with demand of a high level of spatial detail. Means of tracking persons in our environment can nowadays be fulfilled by utilizing several technologies, for example the Bluetooth technology, offering means to obtain movement data. This paper gives an overview of four case studies in the field of Bluetooth tracking which were conducted in order to provide helpful insights on movement aspects for decision makers in their specific microcosm. Aim is to analyse spatio-temporal validity of Bluetooth tracking, and in doing so, to describe the potential of Bluetooth in pedestrian mobility mining.

This paper provides a framework description for movement data analysis of agricultural telematics data. The framework implements interfaces for interacting with data providers and integrates performant spatial databases for passing storage intense analysis methods on complex datasets. Preprocessing steps include methods to efficiently handle raw data to filter erroneous records and detect noisy outliers. While previously mentioned steps are described briefly, the focus is on an approach to automatically extract geographic features such as field boundaries from the filtered data. This is done using the supervised k-Nearest Neighbors classification method to determine the specific working-mode of the machine and differentiate between field work and road. To find and construct meaningful metrics leading to the required objective, a so-called Space-Time-Cube was utilized which depicts trajectories from agricultural machines in 3dimen-sional space.