Literature-based discovery (LBD) aims to discover valuable latent relationships between disparate sets of literatures. This paper presents the first inclusive scientometric overview of LBD research. We utilize a comprehensive scientometric approach incorporating CiteSpace to systematically analyze the literature on LBD from the last four decades (1986–2020). After manual cleaning, we have retrieved a total of 409 documents from six bibliographic databases and two preprint servers. The 35 years’ history of LBD could be partitioned into three phases according to the published papers per year: incubation (1986–2003), developing (2004–2008), and mature phase (2009–2020). The annual production of publications follows Price’s law. The co-authorship network exhibits many subnetworks, indicating that LBD research is composed of many small and medium-sized groups with little collaboration among them. Science mapping reveals that mainstream research in LBD has shifted from baseline co-occurrence approaches to semantic-based methods at the beginning of the new millennium. In the last decade, we can observe the leaning of LBD towards modern network science ideas. In an applied sense, the LBD is increasingly used in predicting adverse drug reactions and drug repurposing. Besides theoretical considerations, the researchers have put a lot of effort into the development of Web-based LBD applications. Nowadays, LBD is becoming increasingly interdisciplinary and involves methods from information science, scientometrics, and machine learning. Unfortunately, LBD is mainly limited to the biomedical domain. The cascading citation expansion announces deep learning and explainable artificial intelligence as emerging topics in LBD. The results indicate that LBD is still growing and evolving.

中文翻译：

---

基于文献的发现的科学计量分析和知识图谱（1986-2020）

基于文献的发现（LBD）旨在发现不同文献集之间有价值的潜在关系。本文首次介绍了 LBD 研究的包容性科学计量学概述。我们利用结合 CiteSpace 的综合科学计量方法来系统地分析过去四年（1986-2020 年）关于 LBD 的文献。经过人工清理，我们从六个书目数据库和两个预印本服务器中总共检索到了 409 篇文献。LBD 的 35 年历史可以根据每年发表的论文分为三个阶段：孵化（1986-2003）、发展（2004-2008）和成熟期（2009-2020）。出版物的年度生产遵循普莱斯定律。共同作者网络展示了许多子网络，表明 LBD 研究由许多中小型团体组成，它们之间几乎没有合作。科学地图显示，在新千年伊始，LBD 的主流研究已从基线共现方法转向基于语义的方法。在过去的十年中，我们可以观察到 LBD 向现代网络科学思想的倾斜。在应用意义上，LBD 越来越多地用于预测药物不良反应和药物再利用。除了理论上的考虑，研究人员在基于 Web 的 LBD 应用程序的开发上也投入了大量精力。如今，LBD 正变得越来越跨学科，涉及来自信息科学、科学计量学和机器学习的方法。不幸的是，LBD 主要限于生物医学领域。级联引文扩展宣布深度学习和可解释的人工智能成为 LBD 中的新兴主题。结果表明 LBD 仍在增长和演变。