Propagation history ranking in social networks: A causality-based approach

Abstract

Information diffusion is one of the most important issues in social network analysis. Unlike most existing works, which either rely on network topology or node profiles, this study focuses on the diffusion itself, i.e., the recorded propagation histories. These histories are the evidence of diffusion and can be used to explain to users what happened in their networks. However, these histories can quickly grow in size and complexity, limiting their capacity to be intuitively understood. To reduce this information overload, in this paper we present the problem of propagation history ranking. The goal is to rank participant edges/nodes by their contribution to the diffusion. We first discuss and adapt a causal measure, Difference of Causal Effects (DCE), as the ranking criterion. Then, to avoid the complex calculation of DCE, we propose two integrated ranking strategies by adopting two indicators. One is responsibility, which captures the necessity aspect of causal effects. We further give an approximate algorithm, which could guarantee a feasible solution, for this indicator. The other is capability, which captures the sufficiency aspect of causal effects. Finally, promising experimental results are presented to verify the feasibility of the proposed ranking strategies.

Blockchain Data Analysis from the Perspective of Complex Networks: Overview

“…However, the public chain data are open and cannot be tampered with, which provides an opportunity to identify illegal activities based on blockchain data analysis. In addition to the common analytical tools mentioned in this paper, causal or motivational reasoning is also a useful tool for exploring the underlying behavioral characteristics of blockchain data [101] . This section introduces two main illegal behaviors and puts forward the scheme, process, and idea of detecting illegal behaviors.…”

Collaborative city digital twin for the COVID-19 pandemic: A federated learning solution

“…Deep learning-based epidemic control: Historical insights from temporal infection data have been crucial for epidemic control and prevention, and could benefit other problems in smart city systems [13,14] or enhanced social network analysis [15] . Deep learningbased techniques have demonstrated a remarkable performance to model such temporal correlations and recognize multiple patterns [16,17] , including the deep neural network-based short-term and high-resolution epidemic forecasting for influenza-like illness [18] , the semi-supervised deep learning framework that integrates computational epidemiology and social media mining techniques for epidemic simulation, called SimNest [19] and EpiRP [20] , which use representational learning methods to capture the dynamic characteristics of epidemic spreading on social networks for epidemicsoriented clustering and classification.…”

Social Media and Crowd-sourced Opinions: Challenges and Future

“…This algorithm has revealed promising technological advancements [4].A framework has been developed to cluster large-scale social networks while considering their topology. To update the direct particle status within the network topology, a greedy particle swarm optimization (GDPSO) algorithm specifically designed for social network clustering is proposed [5]. The fast computational convergence optimization techniques address the continuous clustering optimization.…”