EUVIMEDEUVIMED entdecken
Crossref

Linguistic spatial classifications of event domains in narratives of crime

Blake Stephen Howald

Journal of Spatial Information Science · 2010

DOI: 10.5311/josis.2010.1.6 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Spatial Information Science, 2010. Verfasst von Blake Stephen Howald.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Structurally, formal definitions of the linguistic narrative minimally require two temporally linked past-timeevents. The role of spacein this definition, basedon spatial lan- guage indicating where events occur, is considered optional and non-structural. However, based on narratives with ah igh frequency of spatial language, recent research has ques- tioned this perspective, suggesting that space is more critical than may be readily apparent. Through an analysis of spatially rich serial criminal narratives, it will be demonstrated that spatial information qualitatively varies relative to narrative events. In particular, statistical classifiers in a supervised machine learning task achieve a 90% accuracy in predicting Pre-Crime, Crime, and Post-Crime events based on spatial (and temporal) information. Overall, these results suggest a deeper spatial organization of discourse, which not only provides practical event resolution possibilities, but also challenges traditional formal linguistic definitions of narrative.

Zitieren

APA

Howald, B. S. (2010). Linguistic spatial classifications of event domains in narratives of crime. Journal of Spatial Information Science. https://doi.org/10.5311/josis.2010.1.6

Vancouver

Howald BS. Linguistic spatial classifications of event domains in narratives of crime. Journal of Spatial Information Science. 2010. doi:10.5311/josis.2010.1.6

BibTeX
@article{Howald2010,
  author = {Howald, Blake Stephen},
  title = {Linguistic spatial classifications of event domains in narratives of crime},
  journal = {Journal of Spatial Information Science},
  year = {2010},
  doi = {10.5311/josis.2010.1.6}
}
Kostenlos starten →