Community Detection in Blockchain Social Networks
Sissi Xiaoxiao Wu, Zixian Wu, Shihui Chen, Gangqiang Li, Shengli Zhang
Abstract
In this work, we consider community detection in blockchain networks. We specifically take the Bitcoin network and Ethereum network as two examples, where community detection serves in different ways. For the Bitcoin network, we modify the traditional community detection method and apply it to the transaction social network to cluster users with similar characteristics. For the Ethereum network, on the other hand, we define a bipartite social graph based on the smart contract transactions. A novel community detection algorithm which is designed for low-rank signals on graph can help find users' communities based on user-token subscription. Based on these results, two strategies are devised to deliver on-chain advertisements to those users in the same community. We implement the proposed algorithms on real data. By adopting the modified clustering algorithm, the community results in the Bitcoin network are basically consistent with the ground-truth of the betting site community which has been announced to the public. Meanwhile, we run the proposed strategy on real Ethereum data, visualize the results and implement an advertisement delivery on the Ropsten test net.