Explainable Artificial Intelligence for Social Network Analysis: A Graph-based Framework

Abstract

This study presents a graph-based explainable artificial intelligence framework for social network analysis, integrating graph neural models with SHAP (Shapley Additive Explanations) and other post-hoc explanation techniques. The framework is evaluated on the Stanford Network Analysis Project (SNAP) Facebook Dataset consisting of 15,000 nodes and 45,000 edges. Results from experiments show that the suggested model enhances classification performance by 7–12% compared to baseline methods while providing interpretable feature-level insights. The findings highlight the potential of combining graph learning with explainability to support transparent decision-making in network analysis tasks.