UNIGIS Abschlussarbeiten

Der krönende Abschluss eines UNIGIS MSc Studiums ist sicherlich die Master Thesis. Mit ihr belegen unsere MSc-AbsolventInnen, dass sie den akademischen Grad "Master of Science (Geographical Information Science & Systems)" zu Recht führen.  Im UNIGIS professional Studiengang muss keine Abschlussarbeit verfasst werden. Dennoch nehmen einige Studierende die Möglichkeit war, ein Geoinformatikprojekt durchzuführen und entsprechend zu dokumentieren.

Sie sind auf der Suche nach aktueller Literatur zu Geoinformatik-Themen?
Hier finden sie die mitunter preisgekrönten Abschlussarbeiten unserer AbsolventInnen!

Ingo Rickmeyer [01-2017]:

spatial point pattern analysis of social media feeds during crisis events

Diese Arbeit ist online verfügbar: Download

The flow of information during crisis events is a critical and an integral part of information management. Contemporary communication platforms like social networks provide an opportunity to study such flow and derive early-warning sensors. In this thesis, an attempt is made to assess the potential of using harvested social media for modelling the distribution of social media feeds during crisis events. Therefore a mechanism based on latent Dirichlet allocation (LDA) and document clustering is proposed to model flood and hurricane semantic information, while spatial point pattern analysis is applied explore spatial patterns and to assess the spatial dependence between incident-topic tweets and crisis events. A global Monte Carlo K-test is indicated that the incident-topic tweets and flickr massages is significantly clustered at different scales up to 2500 m. A covariate from the density of human settlements and transport infrastructure for a better fit of the models is implemented. The fitted model is diagnosed using residual analysis as well and also QQ-Plots with simulated data. To test the occurrence of complete spatial randomness (CSR), a spatial Kolmogorov- Smirnov test in two dimensions is made. A spatial-temporal approach with a visualisation of a 3D-scatterplot shows the relation of the sentiment (“negative”) and emotion (“fear”) marks of the social media stream within the chronology of the observed event. The results of the thesis support the basic notion that social media feeds as volunteered geographic information can be used as sensors, enhancing the awareness of crisis events and their impact on humans.

Zurck weitere Arbeiten ...