Skip to the main content

Original scientific paper

https://doi.org/10.5562/cca4229

AI Deployment in Chemistry: Bibliometric and Topic Analysis of Top-Cited Papers (2015−2025)

Andrea Usenik orcid id orcid.org/0000-0003-1995-8705 ; Department of Chemistry, University of Zagreb Faculty of Science, 10000 Zagreb, Croatia
Ernest Meštrović ; University of Zagreb Faculty of Chemical Engineering and Technology, 10000 Zagreb, Croatia
Mirjana Pejić Bach orcid id orcid.org/0000-0003-3899-6707 ; University of Zagreb, Faculty of Economics & Business, 10000 Zagreb, Croatia *

* Corresponding author.


Full text: english pdf 2.841 Kb

page P1-P18

downloads: 52

cite

Supplements: cca4229_supplement.pdf


Abstract

Over the past decade, artificial intelligence (AI) has moved from a promising novelty to a pervasive discovery engine across the chemical sciences. The goal of this paper is to provide a data-driven overview of how AI is reshaping chemical research and where the next breakthroughs are likely to emerge, using bibliometric and topic analysis. To gain insight into this transformation, the 224 most–cited papers on artificial intelligence (AI) indexed in the Web of Science Core Collection between 2015 and 2024 in the field of chemistry research were analyzed. After extracting complete bibliographic metadata, abstracts, keywords, and references, a two-phase study was conducted: (i) descriptive bibliometrics to profile publication growth, document types, venues, countries, institutions, and funding sources; and (ii) VOSviewer-based text-mining to build co-occurrence networks of keywords and countries, revealing thematic and geographic research fronts. Results show an almost exponential rise in highly cited output, from five papers in 2015 to 184 in 2023, driven primarily by China and the United States. Keyword clustering highlights seven dominant application arenas: (1) electronic-skin sensors and functional nanomaterials, (2) cheminformatics and computer-aided synthesis, (3) sustainable processes and Industry 4.0, (4) deep-learning-enabled drug discovery, (5) neuromorphic devices, (6) energy harvesting and storage, and (7) AI-assisted healthcare and delivery systems. Institutional mapping confirms the Chinese Academy of Sciences as the leading contributor, while collaboration networks illustrate a growing but still uneven global engagement.

Keywords

artificial intelligence; AI; chemistry; chemical sciences; drug discovery; machine learning; materials; pharmaceutical chemistry; sensors

Hrčak ID:

347833

URI

https://hrcak.srce.hr/347833

Publication date:

17.1.2026.

Visits: 175 *