leiden_labels_all.csv

An unsupervised analysis of aging research literature using NLP and ML techniques to analyze 461,789 PubMed abstracts related to aging published between 1925 and 2023. Preprocessed files complementing the GitHub repository https://github.com/jsanzros/aging_literature.

本数据集采用自然语言处理（Natural Language Processing，NLP）与机器学习（Machine Learning，ML）技术，对1925年至2023年间发表的461789篇衰老相关PubMed摘要开展无监督分析，所涉文献均为衰老研究领域的学术文献。本数据集附带与GitHub仓库https://github.com/jsanzros/aging_literature配套的预处理文件。