University of Illinois Urbana-Champaign

Using machine learning models to interpret disciplinary styles of metadiscourse in dissertation abstracts

Demarest, Bradford; Sugimoto, Cassidy R.

Content Files
459.pdf

Permalink

https://hdl.handle.net/2142/42038

Description

Title
Using machine learning models to interpret disciplinary styles of metadiscourse in dissertation abstracts
Author(s)
  • Demarest, Bradford
  • Sugimoto, Cassidy R.
Issue Date
2013-02
Keyword(s)
  • metadiscourse
  • disciplinarity
  • machine learning
  • support vector model
  • dissertation abstracts
  • bibliometrics and scholarly communication
Date of Ingest
2013-02-02T05:59:02Z
Abstract
This paper presents the results of a study of disciplinary stylistic differences among dissertation abstracts from physics, psychology, and philosophy. Based on differences in relative frequencies of metadiscourse terms as provided by Hyland (2005), we used a machine learning approach to construct SMO vector support models of each discipline whose average accuracy (88.3%) surpassed a baseline model by 22%. We found that model term weights supported the findings of previous qualitative research regarding differences between disciplines and by extension between hard sciences, social sciences, and humanities. Given the success of the metadiscourse-based model, we conclude by proposing an expanded study to investigate disciplinary style both across disciplines and over time.
Publisher
iSchools
Type of Resource
text
Genre of Resource
Conference Poster
Language
en
Permalink
http://hdl.handle.net/2142/42038
DOI
https://doi.org/10.9776/13459
Copyright and License Information
Copyright © 2013 is held by the authors. Copyright permissions, when appropriate, must be obtained directly from the authors.

Owning Collections

iConference 2013 poster abstracts PRIMARY