Learning Concept Interestingness for Identifying Key Structures from Social Networks

Abstract

Identifying key structures from social networks that aims to discover hidden patterns and extract valuable information is an essential task in the network analysis realm. These different structure detection tasks can be integrated naturally owing to the topological nature of key structures. However, identifying key network structures in most studies has been performed independently, leading to huge computational overheads. To address this challenge, this paper proposes a novel approach for handling key structures identification tasks simultaneously under the unified Formal Concept Analysis (FCA) framework. Specifically, we first implement the FCA-based representation of a social network and then generate the fine-grained knowledge representation, namely concept. Then, an efficient concept interestingness calculation algorithm suitable for social network scenarios is proposed. Next, we then leverage concept interestingness to quantify the hidden relations between concepts and network structures. Finally, an efficient algorithm for jointly key structures detection is developed based on constructed mapping relations. Extensive experiments conducted on real-world networks demonstrate that the efficiency and effectiveness of our proposed approach.