Information Diffusion Analysis Research Articles

Evolutionary Dynamics of Information Diffusion Over Social Networks

Social networks have become ubiquitous in our daily life, as such it has attracted great research interests recently. A key challenge is that it is of extremely large-scale with tremendous information flow, creating the phenomenon of "Big Data". Under such a circumstance, understanding information diffusion over social networks has become an important research issue. Most of the existing works on information diffusion analysis are based on either network structure modeling or empirical approach with dataset mining. However, the information diffusion is also heavily influenced by network users' decisions, actions and their socio-economic connections, which is generally ignored in existing works. In this paper, we propose an evolutionary game theoretic framework to model the dynamic information diffusion process in social networks. Specifically, we analyze the framework in uniform degree and non-uniform degree networks and derive the closed-form expressions of the evolutionary stable network states. Moreover, the information diffusion over two special networks, Erd\H{o}s-R\'enyi random network and the Barab\'asi-Albert scale-free network, are also highlighted. To verify our theoretical analysis, we conduct experiments by using both synthetic networks and real-world Facebook network, as well as real-world information spreading dataset of Twitter and Memetracker. Experiments shows that the proposed game theoretic framework is effective and practical in modeling the social network users' information forwarding behaviors.

Sparse Multi-Task Learning for Detecting Influential Nodes in an Implicit Diffusion Network

How to identify influential nodes is a central research topic in information diffusion analysis. Many existing methods rely on the assumption that the network structure is completely known by the model. However, in many applications, such a network is either unavailable or insufficient to explain the underlying information diffusion phenomena. To address this challenge, we develop a multi-task sparse linear influence model (MSLIM), which can simultaneously predict the volume for each contagion and automatically identify sets of the most influential nodes for different contagions. Our method is based on the linear influence model with two main advantages: 1) it does not require the network structure; 2) it can detect different sets of the most influential nodes for different contagions. To solve the corresponding convex optimization problem for learning the model, we adopt the accelerated gradient method (AGM) framework and show that there is an exact closed-form solution for the proximal mapping. Therefore, the optimization procedure achieves the optimal first-order convergence rate and can be scaled to very large datasets. The proposed model is validated on a set of 2.6 millions tweets from 1000 users of Twitter. We show that MSLIM can efficiently select the most influential users for specific contagions. We also present several interesting patterns of the selected influential users.

An Information Diffusion-Based Recommendation Framework for Micro-Blogging

Micro-blogging is increasingly evolving from a daily chatting tool into a critical platform for individuals and organizations to seek and share real-time news updates during emergencies. However, seeking and extracting useful information from micro-blogging sites poses significant challenges due to the volume of the traffic and the presence of a large body of irrelevant personal messages and spam. In this paper, we propose a novel recommendation framework to overcome this problem. By analyzing information diffusion patterns among a large set of micro-blogs that play the role of emergency news providers, our approach selects a small subset as recommended emergency news feeds for regular users. We evaluate our diffusion-based recommendation framework on Twitter during the early outbreak of H1N1 Flu. The evaluation results show that our method results in more balanced and comprehensive recommendations compared to benchmark approaches.

An Information Diffusion Based Recommendation Framework for Micro-Blogging

Micro-blogging is increasingly extending its role from a daily chatting tool into a critical platform for individuals and organizations to seek and share real-time news updates during emergencies. However, seeking and extracting useful information from micro-blogging sites poses significant challenges due to the volume of the traffic and the presence of a large body of irrelevant personal messages and spams. In this paper, we propose a novel recommendation framework to overcome this problem. By analyzing information diffusion patterns among a large set of micro-blogs who play the role of emergency news providers, our approach could select a small subset as recommended emergency news feeds for regular users. We have evaluated our diffusion-based recommendation framework on Twitter during the early outbreak of H1N1 Flu. The evaluation results show that our method results in more balanced and comprehensive recommendations compared to benchmark approaches.