bibliometrix is not a standalone tool: it is the core of a growing ecosystem of packages, collectively known as the Biblioverse.
Each tool in this ecosystem is designed to integrate seamlessly with bibliometrix, extending its capabilities across the full research pipeline: from data collection to advanced text and content analysis.
The Biblioverse is organized into two families of tools:
These packages allow researchers to programmatically retrieve bibliographic data from major scientific databases via API, feeding directly into the bibliometrix workflow.
An R interface to the OpenAlex API, one of the most comprehensive open bibliographic databases, covering hundreds of millions of scholarly works. openalexR allows users to query and collect metadata on publications, authors, institutions, and concepts at scale, with full integration into bibliometrix data structures.
Citation:
Aria, M., Le, T., Cuccurullo, C., Belfiore, A., & Choe, J. (2024). openalexR: An R-Tool for Collecting Bibliometric Data from OpenAlex. R J., 15(4), 167-180.
An R interface to the PubMed API, the leading database for biomedical and life sciences literature.
pubmedR enables automated retrieval of publication records directly from NCBI, making it ideal for systematic reviews and bibliometric studies in health and medicine.
Citation:
Aria, M. and Cuccurullo, C. (2020). pubmedR: Gathering Metadata About Publications, Grants, Clinical Trials from ‘PubMed’ Database. R package version 0.0.3.
An R interface to the Dimensions API, a multidisciplinary database covering publications, grants, patents, clinical trials, and policy documents. dimensionsR provides programmatic access to one of the broadest sources of research intelligence currently available.
Citation:
Aria, M. and Cuccurullo, C. (2020). dimensionsR: Gathering Bibliographic Records from ‘Digital Science Dimensions’ Using ‘DSL’ API. R package version 0.0.3.
These packages extend the analytical capabilities of bibliometrix, enabling deeper investigation of scientific content beyond metadata-level analysis.
contentanalysis is an R package that goes beyond bibliographic metadata to analyze the full text of scientific publications.
Starting from PDF documents, it enables researchers to extract structured content, perform citation analysis, build citation networks, and conduct text miningm, with AI-enhanced support via Google’s Gemini API for parsing complex document layouts.
Key capabilities include automatic section detection (Abstract, Introduction, Methods, Results, Discussion), narrative and parenthetical citation extraction, interactive citation network visualization, readability metrics, and integration with CrossRef and OpenAlex for metadata enrichment.
TALL is an interactive R Shiny application for comprehensive text analysis, designed for researchers without programming skills.
It unifies the entire text analytics pipeline, from data import and pre-processing to statistical modeling and visualization, into a single, code-free interface.
TALL supports tokenization, lemmatization, and Part-of-Speech tagging across 56 languages (with 87 pre-trained models), and offers topic modeling, co-occurrence network analysis, word embeddings, sentiment and emotion detection, and AI-assisted interpretation via TALL AI, powered by Google Gemini. All outputs are documented, exportable, and fully reproducible.
TALL article is published in SoftwareX (2026) and the package is available on CRAN.
K-Synth Srl
Dept of Economics and Statistics University of Naples Federico II
Via Cinthia, Monte Santangelo Building 3, Sector D, 2nd floor I
80126 Naples, Italy
www.k-synth.com
info@k-synth.com
info@bibliometrix.org
Monthly download from CRAN:
Total download from CRAN:
© Copyright 2026 K-Synth Srl, Academic Spin-Off of the University of Naples Federico II – All Rights Reserved ©