Spatial Correlations in Social Media Data
Identification and Quantification of Spatial Correlation Structures in Georeferenced Twitter Feeds
Social media feeds are one of the growing numbers of sources of volunteered geographic information. Thereby, over recent years, this kind of data has proven to be a rich source of information for many areas of research. This proposal aims to contribute methodological advancements, whereby we focus on Twitter data. Specifically, we aim to explore novel ways to derive spatial correlation structures within social media feeds. Our work builds upon the mature theory of spatial autocorrelation, which is the traditional way of measuring spatial structure.
The first research question is concerned with integrating the theory of spatial autocorrelation with the geometric stochasticity of tweets. The latter is typically investigated by means of stochastic geometry. We aim to combine principles from both fields in order to derive more accurate correlation structures within tweets. In a first step we investigate the effect of the stochastic geometries on spatial autocorrelation measures. This includes point pattern modelling and a Monte Carlo simulation study. That investigation will provide insights regarding a better interpretation of autocorrelation results. Moreover, the gained knowledge allows detailed insights into the variability of inter-tweet correlations of certain social activities. After this exploratory study, we investigate a measure of spatial autocorrelation that acknowledges the stochasticity of the underlying geometric structure and is thus able to obtain meaningful patterns within social media data.
Secondly we investigate the mutually overlapping character of phenomena that are reflected within the tweets. This overlap is caused by the autonomous behaviour of the users, which report about multiple phenomena simultaneously in space and time. We aim to explore ways of separating relevant tweets from non-relevant ones. This is done by means of Dempster-Shafer theory and Dirichlet processes. The challenge thereby is to disentangle the geometrically overlapping neighbourhoods. In a second step we expand spatial autocorrelation measures towards acknowledging this overlapping character by means of partial autocorrelation functions. This will prevent mixing different phenomena and leads to realistic dependency structures.
While the first two packages focus on the point level, the third aspect addresses suitable aggregation strategies. These strategies involve traditional clustering techniques and indices from point pattern analysis. This allows analysing dependencies between different kinds of compound social activities. Further, aggregating tweets allows investigating the relationship of social processes towards their immediate surroundings. This will be a second step of this work package.
Overall, our research will enable for gaining an increased and detailed understanding of social activities and their respective spatial mechanisms through improved methods allowing to analyse representations of these within socio-technical systems.
We cordially invite everybody interested to our next open GIScience colloquium talk The speaker is Mathias Gröbe Technical University of Dresden, Department of Geosciences, Institute of Cartography When: Monday 23.04.2018, 14:15 Where: INF 348, room 015 (Institute of Geography, Heidelberg University) Micro Diagrams: A Multi-Scale Approach for Geovisual Analysis of Categorised Point Datasets Location-based social media from different platforms such as Twitter and [...]
In the era of big data, ubiquitous Flickr geotagged photos have opened a considerable opportunity for discovering valuable geographic information. Point of interest (POI) and region of interest (ROI) are significant reference data that are widely used in geospatial applications. A recently published study (Kuo et al 2018) study aims to develop an efficient method [...]
The following article is the Top Most Cited Article of the last two years in [...]
we cordially invite everybody interested to our next open GIScience colloquium talk Travel History: Reconstructing Travelers Semantic Trajectories Based on Heterogeneous Social Footprints Amon Veiga Santana Heidelberg University, Institute of Geography, GIScience Research Group Time and date: Mon, December 18, 2:15 pm Venue: INF 348, Room 015, Department of Geography, Heidelberg University Travel specialized services on the web have increased their sociability [...]
we cordially invite everybody interested to our next open GIScience colloquium talk Geospatial Visual Analytics Applications for Predictive Analysis Dr. Alexandra Diehl University of Konstanz, Department of Computer and Information Science, Data Analysis and Visualization Time and date: Mon, December 11, 2:15 pm Venue: INF 348, Room 015, Department of Geography, Heidelberg University In this talk, the speaker will introduce her [...]
we cordially invite everybody interested to our next open GIScience colloquium talk State of the Art of Event Detection from Geo-tagged Twitter Data Diao Lin Chair of Cartography, Technical University of Munich Time and date: Mon, November 27, 2:15 pm Venue: INF 348, Room 015, Department of Geography, Heidelberg University The speaker tries to give a structured and comprehensive overview of [...]
The current status of ou Healthy Routing research was presented in the SemGeoSoc Workshop hosted by the Zürich University and organized by prominent researchers in the area of geoinformatics. The workshop offered the opportunity for presenting and discussing ongoing work on the areas of location-based services supported by VGI, social media, citizen & science and [...]
This year AGILE celebrated its 20th birthday and conference from May 10 - 12 at Wageningen University, Netherlands. The conference organizers chose “societal geo-information” to be the main theme of the research presented. The GIScience Research Group Heidelberg was represented by its members Tessio Novack, Franz-Benjamin Mocnik and Benjamin Herfort. On Tuesday, the day before the [...]
Tourism is a economically highly important industry. It is, however, vulnerable to disaster events. Geotagged social media data, as one of the forms of volunteered geographic information (VGI), has been widely explored to support the prevention, preparation, and response phases of disaster management, while little effort has been put on the recovery phase. A recently [...]
Recently the paper “Understanding human activity patterns based on space-time-semantics” by Wei Huang, and Songnian Li (Ryerson University, Toronto, Canada) has been selected as the best paper published in 2016 (volumes 111-122) in the ISPRS Journal of Photogrammetry and Remote Sensing. Dr. Wei Huang is since late 2016 team member of the GIScience Research Group. [...]