skip navigation
ERPAePRINTS  logo: erpanet skip navigation

Feature Type Analysis in Automated Genre Classification

Kim, Dr Yunhyong and Ross, Prof Seamus (2007) Feature Type Analysis in Automated Genre Classification.

Full text available as:
PDF - Requires Adobe Acrobat Reader or other PDF viewer.

Abstract

In this paper, we compare classifiers based on language model, image, and stylistic features for automated genre classification. The majority of previous studies in genre classification have created models based on an amalgamated representation of a document using a multitude of features. In these models, the inseparable roles of different features make it difficult to determine a means of improving the classifier when it exhibits poor performance in detecting selected genres. By independently modeling and comparing classifiers based on features belonging to three types, describing visual, stylistic, and topical properties, we demonstrate that different genres have distinctive feature strengths.

Item Type:Preprint
Subjects:M Resource Discovery
L Digital Repository, Digital Archive and Digital Library Models > LA Ingest
E Data Description, Documentation and Standards > EA Metadata
Document Language:English
ID Code:128
Deposited By:Kim, Dr Yunhyong
Deposited On:25 May 2007