Zur Seitenansicht
 

Titelaufnahme

Titel
Geosocial Media Data as Predictors in a GWR Application to Forecast Crime Hotspots (Short Paper)
VerfasserRistea, Alina ; Kounadi, Ourania ; Leitner, Michael
Erschienen in
10th International Conference on Geographic Information Science (GIScience 2018) : Winter, Stephan; Griffin, Amy; Sester, Monika, Dagstuhl, 2018
Erschienen2018
SpracheEnglisch
SerieLeibniz International Proceedings in Informatics (LIPIcs) ; 114
DokumenttypAufsatz in einem Sammelwerk
Schlagwörter (EN)spatial crime prediction / street crime / population at risk / geographically weighted regression / geosocial media
ISBN9783959770835
URNurn:nbn:at:at-ubs:3-9690 Persistent Identifier (URN)
Zugriffsbeschränkung
 Das Werk ist frei verfügbar
Dateien
Geosocial Media Data as Predictors in a GWR Application to Forecast Crime Hotspots (Short Paper) [0.37 mb]
Links
Nachweis
Klassifikation
Zusammenfassung (Englisch)

In this paper we forecast hotspots of street crime in Portland, Oregon. Our approach uses geosocial media posts, which define the predictors in geographically weighted regression (GWR) models. We use two predictors that are both derived from Twitter data. The first one is the population at risk of being victim of street crime. The second one is the crime related tweets. These two predictors were used in GWR to create models that depict future street crime hotspots. The predicted hotspots enclosed more than 23% of the future street crimes in 1% of the study area and also outperformed the prediction efficiency of a baseline approach. Future work will focus on optimizing the prediction parameters and testing the applicability of this approach to other mobile crime types.

Statistik
Das PDF-Dokument wurde 6 mal heruntergeladen.