Citation :

Yameen Faridi, Suraj Kumar Gupta,Dr. Vishal Shrivastava, Dr. Akhil Pandey , 2026. "Social Network Analysis using AI and its Survey" ESP International Journal of Advancements in Science & Technology (ESP-IJAST)  Volume 4, Issue 4: 33-39.

Abstract :

Artificial intelligence (AI) and deep learning (DL) are progressively used in social network analysis (SNA) to improve topology classification, link prediction, and community detection, thereby reducing manual analytical errors. This study addresses the use of graph neural networks, especially the Stacked Graph Convolutional Network (Stacked GCN-GAT) model, in social structural diagnosis and node interaction classification. The proposed method combines graph structural preprocessing, feature classification, and evaluation of the AI-based method. The solution strategies focus on improving link prediction accuracy and reducing computational overhead in large-scale graphs. This study is simulated in Python using approximately 275,000 node-edge interaction subgraphs with various structural embeddings from benchmark social network datasets. Our goal is to compare the performance of our AI-based model against traditional graph-theoretic approaches, highlighting its advantages, limitations, and practical applications. The results showed that deep learning architectures can significantly facilitate early dynamic relationship prediction and anomaly detection in social networks.

References :

[1] Ramadan, S. Z. "Methods Used in Computer-Aided Diagnosis for Complex Network Analysis: A Review." Journal of Healthcare Engineering, 2020.

[2] Brooks, A. D., et al. "Modern Social Network Topology Detection: A Technological Review." International Journal of Biomedical Imaging, 2009.

[3] Kabir, H. M. D., et al. "Non-linear Graph Down-Sampling and Structural Reconstruction." 2010 IEEE Conference, 2010.

[4] Chougrad, H., Zouaki, H., & Alheyane, O. "Deep Convolutional Networks for Graph Structural Screening." Computer Methods and Programs in Biomedicine, 2018.

[5] Yadav, S. S., & Jadhav, S. M. "Deep Neural Network Based Medical and Social Network Classification." Journal of Big Data, 2019.

[6] Valvano, G., et al. "Convolutional Neural Networks for the Segmentation of Anomalous Subgraphs." Journal of Healthcare Engineering, 2019.

[7] Lundervold, A. S., & Lundervold, A. "An Overview of Deep Learning in Complex Spatial Systems." Zeitschrift für Medizinische Physik, 2019.

[8] Al Nahid, A., Mehrabi, M. A., & Kong, Y. "Social Network Image and Graph Classification by Deep Neural Network Techniques Guided by Local Clustering." Biomedical Research International, 2018.

[9] Khan, M. H. M., et al. "Multi-Class Classification of Network Interaction Abnormalities Using Deep Convolutional Neural Network." PLoS One, 2021.

[10] Zhou, X., et al. "A New Deep Graph Convolutional Model for Automated Social Anomaly Detection." IEEE BESC, 2020.

[11] Chukwu, J. K., Sani, F. B., & Nuhu, A. S. "Social Graph Node Classification Using Deep Neural Networks." FUOYE Journal of Engineering and Technology, 2021.

[12] Janowczyk, A. "Use Case 6: Dynamic Social Graph Link Segmentation and Community Discovery." Online Resource, 2015.

[13] Wahab, N., & Khan, A. "Multifaceted Fused-GNN Based Scoring of Social Network Subgraphs." Applied Soft Computing, 2020.

[14] Ramadan, S. Z. "Using Graph Convolutional Networks with Cheat Sheet and Data Augmentation to Detect Anomalies in Networks." Computational and Mathematical Methods, 2020.

[15] Hamad, Y. A., Simonov, K., & Naeem, M. B. "Social Network Anomaly Detection and Classification Using Artificial Neural Networks." 1st Annual International Conference on Information and Sciences (AiCIS), 2018.

Keywords :

Social Network Analysis, Gcn, Gat, Graph Dataset, Deep Learning, Link Prediction, Graph Neural Networks, Community Detection.