The development of artificial intelligence (AI) as a field has impacted almost all aspects of human life. More recently it has found a role in addressing developmental challenges, specifically the Sustainable Development Goals (SDGs). However, there are not enough systematic studies on analysis of the role of AI research towards the SDGs. Therefore, this article attempts to bridge this gap by identifying the major bibliometric trends and concept‐evolution trajectories in the area of AI applications for sustainable‐development goals. The research publication data for the last 20 years in the areas of artificial intelligence, machine learning, deep learning, and so forth, is obtained and computationally analysed using a framework comprising bibliometrics, path analysis and content analysis. The findings show an incremental trend in overall publications on the application of AI for SDGs across the different regions of the world. SDGs 3 (good health & well‐being) and 7 (affordable and clean energy) are found as the areas with the most applications of AI. In SDG3, the literature reflects application of AI techniques such as deep learning for precision and personalised medicine while in SDG7, a number of studies have employed AI techniques for the integration of systems for efficient generation of solar power and improving the energy efficiency of a building. Furthermore, SDG 4 (quality education), SDG 13 (climate action), SDG 11 (sustainable cities and communities) and SDG 16 (peace, justice and strong institutions) are the other SDGs where AI approaches and techniques are applied. The analytical results present a detailed insight of application of AI for achieving the SDGs.

Publication of a large number of research papers during the last few decades motivated creation of scholarly databases for indexing the publications and recording citations. The publication metadata fields in scholarly databases are now retrieved for various purposes ranging from information search and retrieval to research evaluation. Traditionally, Web of Science and Scopus have been major database sources used. However, with the creation of newer databases like Dimensions, the choice has expanded further. The coverage and citation data of the major databases have been compared in many previous studies. However, there is no existing work on comparison of metadata fields provided by the scholarly databases and the impact that metadata fields provided may have on scientometric research. This work, therefore, attempts to bridge this research gap by comparing the metadata fields contained in the data downloaded through the User Interface (UI) based search from three major scholarly databases-Web of Science, Scopus and Dimensions. The effect of existence or absence of a metadata field in a database on the possibilities and the ease of doing scientometric analysis is explored. The findings are useful for scientometric researchers, practitioners and database managers.

United Nations Sustainable Development Goals (SDGs) and their targets are highly interconnected and require international collaboration. In this context, the G20 organization of 20 countries/units, founded in 1999 holds an important position being an important political and economic platform for addressing various developmental concerns. With 75% of global population, the Group Nations accounts for 85% of the global GDP and about 75% of the global trade. Considering the strength, resources and representation of these countries, they hold the major part of the responsibility towards achieving the SDGs. Scientific and technological research is a major requirement for achieving the SDGs. Given that the G20 has about 88.8% of the world’s researchers, 93.2% of research spending and produce about 90.6% of scientific publications, it would be interesting to analyse what quantum of this research is focused on achieving the SDGs. However, there are no existing studies on this aspect. This study, therefore, attempts to bridge this research gap by presenting a quantitative analysis of research on SDGs by the G20 member countries. Important patterns are identified, which can be useful for different policy perspectives.

Vivek Kumar Singh1, Mousumi Karmakar2, Anurag Kanaujia1 and Sujit Bhattacharya3 Author informationPDFCitations 1Department of Computer Science, Banaras Hindu University, Array 2Department of Computer Science and Engineering, Alliance University, Bangalore, INDIA 3CSIR-National Institute of Science Communication and Policy Research (NIScPR), New Delhi, INDIA Corresponding author. Correspondence: Anurag Kanaujia Department of Computer Science, Banaras Hindu University, Varanasi-221005,