Artificial Intelligence For Innovation: A Bibliometric Analysis And Structural Variation Approach

Artificial intelligence (AI) has gained significant popularity in recent years. This study critically examines the existing literature on the role and potential of AI, machine learning (ML) and big data in driving innovation. To the best of our knowledge, no existing survey has provided a comprehensive overview of this topic. The aim of this paper is thus to provide a coherent overview of theoretical cornerstones as well as recent trends in research on AI and data analytics for innovation. Using various bibliometric analyses of themes including publication counts and trends, co-citations, co-authorship, and keyword co-occurrence, we infer the thematic structure of AI research in innovation for the period from 1991 to 2021. The publications are grouped into three major clusters, with Cluster 1 remaining a constantly dominant theme in the digital innovation publication landscape. Cluster 2 includes published studies on big data, which also received much research attention. Cluster 3, which is the most prominent, includes business performance, business analytics, and information systems. We also analyse publication citation counts in the literature using Poisson and negative binomial regressions. The results show that the structural variation approach provides a new method for tracking and evaluating the potential of freshly published studies in context. The findings of the current study will be significant in identifying new areas of research of potential interest to scholars and practitioners in the field of AI for innovation worldwide. We conclude this review with limitations and theoretical and practical orientations.