5G Core is the backbone of digital transformation with ultra-low latency, network slicing, and dense IoT integration. In the study, 635 academic studies indexed in Web of Science were clustered using Leiden, Louvain, HDBSCAN, and K-Means, and five main themes were identified: service-based architecture, security (post-quantum, blockchain), artificial intelligence/machine learning Network Data Analytics Functionality (NWDAF), deep reinforcement learning), cloud/edge computing, and network resource management. The clustering methods were evaluated using the Silhouette, Davies-Bouldin, and Calinski-Harabasz quality metrics. Although K-means appears to be at the top in terms of quality metrics, Leiden and Louvain outperform K-means in terms of interpretability. A hybrid Large Language Models (LLMs) approach was used for theme interpretation. General themes were identified using Qwen3-Max-Preview, and then the previously identified themes were supported using cloud-based free Nemotron, gpt-oss-20b, and Sonoma SkyAlpha models via OpenRouter. Qwen3 stands out in terms of semantic depth and summarization accuracy. This methodology, which combines quantitative clustering with qualitative LLM analysis, highlights the strategic role of 5G Core in both communication and as the architecture, security, and AI infrastructure of digital transformation, in a multidimensional way.
Parmaksız et al. (Mon,) studied this question.