An unsupervised approach to automatic classification of scientific literature utilizing bibliographic metadata

Abstract

This article describes an unsupervised approach for automatic classification of scientific literature archived in digital libraries and repositories according to a standard library classification scheme. The method is based on identifying all the references cited in the document to be classified and, using the subject classification metadata of extracted references as catalogued in existing conventional libraries, inferring the most probable class for the document itself with the help of a weighting mechanism. We have demonstrated the application of the proposed method and assessed its performance by developing a prototype software system for automatic classification of scientific documents according to the Dewey Decimal Classification (DDC) scheme. A dataset of one thousand research articles, papers, and reports from a well-known scientific digital library, CiteSeer, were used to evaluate the classification performance of the system. Detailed results of this experiment are presented and discussed.

Categorical Metadata Representation for Customized Text Classification

“…As shown in Figure 1, in addition to the text, a customizable text classifier is given a list of categories specific to the text to predict its class. Existing works applied metadata information to improve the performance of a model, such as user and product (Tang et al, 2015) information in sentiment classification, and author (Rosen-Zvi et al, 2004) and publication (Joorabchi and Mahdi, 2011) information in paper classification.…”

Bibliographic Classification in the Digital Age: Current Trends & Future Directions

“…LCC and DDC were researched for accuracy and precision by using a prototype model (Gnoli, Pusterla, Bendiscioli, & Recinella, 2016) for automatic text classification of electronic documents using classification metadata of library holdings from LCC and DDC datasets. It was observed that for precision, there is a need for increasing DDC and LCC bibliographic data on the Web, introducing searching capabilities for bibliographic data at the micro level of any document, and increasing the efficiency of user interfaces for navigation using DDC-based browsing structure (Joorabchi & Mahdi, 2009) (Joorabchi & Mahdi, 2011). Therefore, CC because of the pure faceted approach has high-level precision in search and resource discovery.…”

Positioning Libraries for a New Bibliographic Universe

“…Joorabchi and Mahdi propose a prototype software system for automatic classification of scientific documents according to DDC. 75 The authors applied DDC to references in research articles, papers, and reports from CiteSeer, a scientific digital repository.…”