Automatic classification of older electronic texts into the Universal Decimal Classification–UDC

Abstract

PurposeThe purpose of this study is to develop a model for automated classification of old digitised texts to the Universal Decimal Classification (UDC), using machine-learning methods.Design/methodology/approachThe general research approach is inherent to design science research, in which the problem of UDC assignment of the old, digitised texts is addressed by developing a machine-learning classification model. A corpus of 70,000 scholarly texts, fully bibliographically processed by librarians, was used to train and test the model, which was used for classification of old texts on a corpus of 200,000 items. Human experts evaluated the performance of the model.FindingsResults suggest that machine-learning models can correctly assign the UDC at some level for almost any scholarly text. Furthermore, the model can be recommended for the UDC assignment of older texts. Ten librarians corroborated this on 150 randomly selected texts.Research limitations/implicationsThe main limitations of this study were unavailability of labelled older texts and the limited availability of librarians.Practical implicationsThe classification model can provide a recommendation to the librarians during their classification work; furthermore, it can be implemented as an add-on to full-text search in the library databases.Social implicationsThe proposed methodology supports librarians by recommending UDC classifiers, thus saving time in their daily work. By automatically classifying older texts, digital libraries can provide a better user experience by enabling structured searches. These contribute to making knowledge more widely available and useable.Originality/valueThese findings contribute to the field of automated classification of bibliographical information with the usage of full texts, especially in cases in which the texts are old, unstructured and in which archaic language and vocabulary are used.

Experiencia de clasificación automática de documentos sobre Ciencias de la Vida y Biomedicina obtenidos del Web of Science

“…Dentro de la bibliotecología y ciencias de la información, algunos de los trabajos más destacados son los siguientes: Contreras (2016) presentó un clasificador automático para documentos, basado en el área Z del Sistema de Clasificación de la Biblioteca del Congreso (L.C), teniendo resultados favorables en la clasificación del material bibliográfico. Kragelj, Matjaž, y Mirjana (2021) desarrollaron un modelo de clasificación automática de documentos antiguos, basado en el Sistema de Clasificación Decimal Universal (UDC). Como parte final, en el trabajo de Cassidy (2020) se utilizó el modelo Naïve Bayes para la clasificación de patentes, considerando códigos especializados para estos recursos.…”

Automatic Text Classification Model Based on Machine Learning

“…In the preprocessing process, it mainly involves the word frequency extraction, feature selection and other issues. Among them, the most basic and most important is to extract the most effective information and facilitate the research of using machine learning algorithms to obtain key data sets for recognition, and then whether the text classification task can be realized and how to accurately distinguish text and field become a difficulty [7][8]. However, at present, some existing automated text categories that have achieved significant improvement are only used as reference indicators.…”

Service for assigning a UDC code to mathematical articles based on semantic technologies

“…В [9] дан исчерпывающий обзор современных рекомендательный систем на основе глубокого машинного обучения. Методы машинного обучения используются в различных научных рекомендательных системах [10,11]. В [10] Нами был проведен опрос экспертов-математиков с целью выяснения, какие признаки являются для них определяющими при выборе классифицирующего кода УДК для научной статьи.…”