Classifying scientific publications using abstract features

Cornelia Caragea, Adrian Silvescu, Saurabh Kataria, Doina Caragea, Prasenjit Mitra

Research output: Chapter in Book/Report/Conference proceedingConference contribution

7 Scopus citations

Abstract

With the exponential increase in the number of documents available online, e.g., news articles, weblogs, scientific documents, effective and efficient classification methods are required in order to deliver the appropriate information to specific users or groups. The performance of document classifiers critically depends, among other things, on the choice of the feature representation. The commonly used "bag of words" representation can result in a large number of features. Feature abstraction helps reduce a classifier input size by learning an abstraction hierarchy over the set of words. A cut through the hierarchy specifies a compressed model, where the nodes on the cut represent abstract features. In this paper, we compare feature abstraction with two other methods for dimensionality reduction, i.e., feature selection and Latent Dirichlet Allocation (LDA). Experimental results on two data sets of scientific publications show that classifiers trained using abstract features significantly outperform those trained using features that have the highest average mutual information with the class, and those trained using the topic distribution and topic words output by LDA. Furthermore, we propose an approach to automatic identification of a cut in order to trade off the complexity of classifiers against their performance. Our results demonstrate the feasibility of the proposed approach.

Original languageEnglish (US)
Title of host publicationSARA 2011 - Proceedings of the 9th Symposium on Abstraction, Reformulation, and Approximation
Pages26-33
Number of pages8
StatePublished - Dec 1 2011
Event9th Symposium on Abstraction, Reformulation, and Approximation, SARA 2011 - Cardona, Catalonia, Spain
Duration: Jul 17 2011Jul 18 2011

Publication series

NameSARA 2011 - Proceedings of the 9th Symposium on Abstraction, Reformulation, and Approximation

Other

Other9th Symposium on Abstraction, Reformulation, and Approximation, SARA 2011
CountrySpain
CityCardona, Catalonia
Period7/17/117/18/11

All Science Journal Classification (ASJC) codes

  • Computer Science Applications

Fingerprint Dive into the research topics of 'Classifying scientific publications using abstract features'. Together they form a unique fingerprint.

Cite this