Automatic Detection of Text Genre

TL;DR

This paper introduces a theory of text genres as bundles of facets correlated with surface cues, demonstrating that genre detection based on surface cues can be as effective as using deeper structural features.

Contribution

It proposes a novel theory of genres as facet bundles and shows surface cues are sufficient for genre detection, simplifying the classification process.

Findings

Genre detection based on surface cues is as successful as structural methods.

Genres can be modeled as bundles of facets correlating with surface cues.

Surface cue-based detection simplifies genre classification.

Abstract

As the text databases available to users become larger and more heterogeneous, genre becomes increasingly important for computational linguistics as a complement to topical and structural principles of classification. We propose a theory of genres as bundles of facets, which correlate with various surface cues, and argue that genre detection based on surface cues is as successful as detection based on deeper structural properties.