Towards annotation of text worlds in a literary work
This work addresses the problem of automating literary analysis for researchers and corpus studies, but it is incremental as it builds on prior attempts with small collections and standalone rules.
The authors tackled the challenge of annotating text worlds in literary works by conducting an experiment with lexical annotation and quantitative comparison methods, finding that strict rules are needed for agreed tag assignments but fuzzy modeling is required for subjective interpretations.
Literary texts are usually rich in meanings and their interpretation complicates corpus studies and automatic processing. There have been several attempts to create collections of literary texts with annotation of literary elements like the author's speech, characters, events, scenes etc. However, they resulted in small collections and standalone rules for annotation. The present article describes an experiment on lexical annotation of text worlds in a literary work and quantitative methods of their comparison. The experiment shows that for a well-agreed tag assignment annotation rules should be set much more strictly. However, if borders between text worlds and other elements are the result of a subjective interpretation, they should be modeled as fuzzy entities.