手法を比較

	科学テキストマイニング	書誌計量分析
分野	テキストマイニング	科学計量学
系統	Process / pipeline	Process / pipeline
提唱年	2019–2020 (modern transformer era); roots in earlier computational linguistics	1969 (term coined); practice dates to 1920s–1930s
提唱者	Community-developed; SciBERT (Beltagy et al., 2019) and SPECTER (Cohan et al., 2020) are landmark models	Alan Pritchard (coined term); earlier quantitative work by Paul Otlet (1934) and S. C. Bradford (1934)
種類	NLP pipeline for scientific literature	Quantitative literature analysis
原典	Beltagy, I., Lo, K., & Cohan, A. (2019). SciBERT: A Pretrained Language Model for Scientific Text. EMNLP 2019.	Pritchard, A. (1969). Statistical bibliography or bibliometrics? Journal of Documentation, 25(4), 348–349.
別名	Bilimsel Metin Madenciliği, scholarly NLP, academic text mining, scientific literature mining	bibliometrics, bibliometric study, bibliometric mapping, publication analysis
関連	4	6
概要	Scientific text mining is a natural-language-processing pipeline applied to academic literature. Grounded in domain-specific pretrained models such as SciBERT (Beltagy et al., 2019) and SPECTER (Cohan et al., 2020), it automatically extracts hypotheses, methodologies, findings, and scholarly contributions from full-text papers or abstracts, enabling systematic review automation, research-trend analysis, and science mapping at scale.	Bibliometric analysis applies statistical and mathematical methods to bibliographic records — publications, citations, authors, journals, and keywords — to measure and map the structure, output, and intellectual evolution of a research field. It is widely used to identify influential works, prolific authors, productive journals, collaboration networks, and emerging research themes across any academic discipline.