Machine Learning applications in Social Networking: Bibliometric analysis and future avenues for research

Abstract

This research paper provides a comprehensive descriptive analysis of the application of machine learning techniques within the realm of social networks, focusing on scholarly contributions and emerging trends over a 21-year period. Through an examination of prominent nations, authors, journals, and thematic clusters, key findings underscore the central role of China and the USA in machine learning research applied to social networks. Furthermore, the study identifies IEEE Access and Journal of Machine Learning Research as leading journals in the field, while highlighting Lise Getoor as a preeminent author within the domain. The emergent themes of sentiment analysis, feature extraction, natural language processing, deep learning, and social media analysis underscore the evolving landscape of machine learning in social network research. Finally, a conceptual framework derived from thematic mapping offers insights into future research directions, highlighting applications of machine learning techniques such as neural networks, deep learning, and support vector machines in predicting online customer engagement, detecting fake accounts, and addressing other pertinent issues in the digital marketing landscape. This research encapsulates the key findings and implications of the research, serving as a guide for scholars and practitioners in the field.