Dataset and Code for Automated Dewey Decimal Classification from Bibliographic Metadata

This repository contains the dataset and analysis code for the study 'Automated Dewey Decimal Classification from Bibliographic Metadata: A comparitive study of machine learning Models.' Bibliographic records were collected from the DOAJ API and labelled using an LCC-to-DDC crosswalk.本代码仓库收录了题为《基于书目元数据（Bibliographic Metadata）的自动化杜威十进制分类（Automated Dewey Decimal Classification, DDC）：机器学习模型（Machine Learning Model）对比研究》的配套数据集与分析代码。本研究所使用的书目记录采集自DOAJ API，并通过美国国会图书馆分类法（Library of Congress Classification, LCC）与杜威十进制分类法（DDC）的映射对照表完成标注。