Bridging quantum and computation: A bibliometric analysis of machine learning in quantum chemistry

This bibliometric study systematically explores the integration of Machine Learning (ML) into quantum chemistry, a multidisciplinary approach aimed at addressing complex chemical problems through the advanced computational capabilities of ML algorithms. Utilizing Scopus for comprehensive bibliographic data collection, the study adheres to the PRISMA flowchart methodology for rigorous screening, inclusion, and exclusion of research articles. Analytical processing and visualization of the data are accomplished using two prominent bibliometric analysis tools, Biblioshiny and CiteSpace, facilitating a multifaceted examination of the field's scholarly output. The study's findings are extensive, covering annual scientific production, which unveils the field's growth trajectory and burgeoning interest over time. It identifies the most productive author, thereby highlighting the leading contributors to the field and setting a benchmark for academic output. Coauthorship analysis reveals the collaborative networks within the community, illustrating the interconnectedness of researchers globally. Examination of the most globally cited documents provides insight into the foundational works and seminal papers that have shaped the field. This research further explored trend topics, thematic maps, and conceptual structure maps using Multiple Correspondence Analysis to discover innovative themes and the fields at the center of attention in the literature. In addition, a timeline network visualization of keyword co-occurrence and a cluster network visualization of cited authors illustrated a visual dynamic development of the research field and the scientific inheritance. Network visualization of cited journals and a timezone network visualization of countries’ cooperation demonstrated the interdisciplinary nature and the research being conducted globally. By examining research gaps and the scope of practical application, the present study not only described the current standing of knowledge but also guided future research paths. Finally, the findings support the transformative role of ML in quantum chemistry.