Deep Community Detection Method for Social Networks

Abstract

With the fast development of the mobile Internet, the online platforms of social networks have rapidly been developing for the purpose of making friends, sharing information, etc. In these online platforms, users being related to each other forms social networks. Literature reviews have shown that social networks have community structure. Through the studies of community structure, the characteristics and functions of networks structure and the dynamical evolution mechanism of networks can be used for predicting user behaviours and controlling information dissemination. Therefore, this study proposes a deep community detection method which includes (1) matrix reconstruction method, (2) spatial feature extraction method and (3) community detection method. The original adjacency matrix in social network is reconstructed based on the opinion leader and nearer neighbors for obtaining spatial proximity matrix. The spatial eigenvector of reconstructed adjacency matrix can be extracted by an auto-encoder based on convolution neural network for the improvement of modularity. In experiments, four open datasets of practical social networks were selected to evaluate the proposed method, and the experimental results show that the proposed deep community detection method obtained higher modularity than other methods. Therefore, the proposed deep community detection method can effectively detect high quality communities in social networks.

Detailed analysis of Ethereum network on transaction behavior, community structure and link prediction

“…This study, however, lacks the analysis of the global Ethereum transaction network. Closest to our research would be the study by Wu et al (2021) where the community detection problem was examined in both the Bitcoin and Ethereum networks. The low-rank community detection algorithm proposed by Wai et al (2018) was used to detect communities in the Ethereum network.…”

Identificação de perfis de comportamento de usuários no Ethereum utilizando técnicas de aprendizado de máquina

“…Ambos os trabalhos usam algoritmos de agrupamento não supervisionados para distinguir as contas da plataforma em vários grupos, segundo suas finalidades ou servic ¸os prestados. [Payette et al 2017, Wu et al 2021] também propõem modelos de categorizac ¸ão de usuários do Ethereum, utilizando algoritmos de agrupamentos. Os autores extraem características de transac ¸ões como em nosso trabalho.…”

“…Há também estudos caracterizando o Ethereum e a maneira como seus usuários agem [Mascarenhas et al 2018, Chen et al 2020, considerando propriedades estruturais da rede. Modelos de aprendizado de máquina vêm sendo amplamente utilizados para inferir comunidades de usuários em criptomoedas [Norvill et al 2017, Payette et al 2017, Wu et al 2021. Recentemente, buscou-se inferir em [Aspembitova et al 2021] o perfil de usuários no Ethereum com o foco em risco de investimento (e.g., pessimista ou otimista).…”

Networks of Ethereum Non-Fungible Tokens: A graph-based analysis of the ERC-721 ecosystem

“…The frequency distribution of degrees in transaction graphs can provide insight into user behavior when trading a particular collection of NFTs. Many realworld graphs for social media and the Internet show highly skewed, heavy-tailed degree distributions [5], [8], [12], [32]. This generally indicates that a significant portion of the information about node interactions needs to be extrapolated from the analysis of their tails, and in general demonstrates the existence of (several) high degree hubs.…”

“…This generally indicates that a significant portion of the information about node interactions needs to be extrapolated from the analysis of their tails, and in general demonstrates the existence of (several) high degree hubs. For example, in Ethereum ERC20 token networks hubs are exchanges [12], in social networks they are influencer nodes [8], [33], and in web networks they are popular and high-ranked websites [32]. Several kinds of networks have been confirmed to follow power laws in their degree distribution [5], [8], [12], [32].…”