Detecting Family Resemblance: Automated Genre Classification

Authors

Yunhyong Kim Digital Curation Centre (DCC) & Humanities Advanced Technology Information Institute (HATII), University of Glasgow, Glasgow, UK
Seamus Ross Digital Curation Centre (DCC) & Humanities Advanced Technology Information Institute (HATII), University of Glasgow, Glasgow, UK

DOI:

https://doi.org/10.2481/dsj.6.S172

Keywords:

Automated genre classification, Metadata, Scientific information, Information management, Information extraction

Abstract

This paper presents results in automated genre classification of digital documents in PDF format. It describes genre classification as an important ingredient in contextualising scientific data and in retrieving targetted material for improving research. The current paper compares the role of visual layout, stylistic features, and language model features in clustering documents and presents results in retrieving five selected genres (Scientific Article, Thesis, Periodicals, Business Report, and Form) from a pool of materials populated with documents of the nineteen most popular genres found in our experimental data set.

Downloads

Published

2007-03-28

Issue

Vol. 6 (2007)

Section

Research Papers

License

This work is licensed under a Creative Commons Attribution 4.0 International License.

Authors who publish with this journal agree to the following terms. If a submission is rejected or withdrawn prior to publication, all rights return to the author(s):

Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work.

Submitting to the journal implicitly confirms that all named authors and rights holders have agreed to the above terms of publication. It is the submitting author's responsibility to ensure all authors and relevant institutional bodies have given their agreement at the point of submission.

Note: some institutions require authors to seek written approval in relation to the terms of publication. Should this be required, authors can request a separate licence agreement document from the editorial team (e.g. authors who are Crown employees).