Time-sensitive Positive Influence Maximization in signed social networks

The purpose of influence maximization problem is to select a small seed set to maximize the number of nodes influenced by the seed set. For viral marketing, the problem of influence maximization plays a vital role. Current works mainly focus on the unsigned social networks, which include only positive relationship between users. However, the influence maximization in the signed social networks including positive and negative relationships between users is still a challenging issue. Moreover, the existing works pay more attention to the positive influence. Therefore, this paper first analyzes the positive maximization influence in the signed social networks. The purpose of this problem is to select the seed set with the most positive influence in the signed social networks. Afterwards, this paper proposes a model that incorporates the state of node, the preference of individual and polarity relationship, called Independent Cascade with the Negative and Polarity (ICWNP) propagation model. On the basis of the ICWNP model, this paper proposes a Greedy with ICWNP algorithm. Finally, on four real social networks, experimental results manifest that the proposed algorithm has higher accuracy and efficiency than the related methods.

Download Full-text

Positive influence maximization in signed social networks based on simulated annealing

Neurocomputing ◽

10.1016/j.neucom.2017.03.003 ◽

2017 ◽

Vol 260 ◽

pp. 69-78 ◽

Cited By ~ 16

Author(s):

Dong Li ◽

Cuihua Wang ◽

Shengping Zhang ◽

Guanglu Zhou ◽

Dianhui Chu ◽

...

Keyword(s):

Social Networks ◽

Simulated Annealing ◽

Positive Influence ◽

Influence Maximization ◽

Signed Social Networks

Download Full-text

Net positive influence maximization in signed social networks

Journal of Intelligent & Fuzzy Systems ◽

10.3233/jifs-191908 ◽

2021 ◽

pp. 1-12

Author(s):

Dong Li ◽

Yuejiao Wang ◽

Muhao Li ◽

Xin Sun ◽

Jingchang Pan ◽

...

Keyword(s):

Social Networks ◽

Greedy Algorithm ◽

Seed Set ◽

Social Systems ◽

Research Direction ◽

Negative Influence ◽

Positive Influence ◽

Influence Maximization ◽

The Real ◽

Signed Social Networks

In the real world, a large number of social systems can be modeled as signed social networks including both positive and negative relationships. Influence maximization in signed social networks is an interesting and significant research direction, which has gained some attention. All of existing studies mainly focused on positive influence maximization (PIM) problem. The goal of the PIM problem is to select the seed set with maximum positive influence in signed social networks. However, the selected seed set with maximum positive influence may also has a large amount of negative influence, which will cause bad effects in the real applications. Therefore, maximizing purely positive influence is not the final and best goal in signed social networks. In this paper, we introduce the concept of net positive influence and propose the net positive influence maximization (NPIM) problem for signed social networks, to select the seed set with as much positive influence as possible and as less negative influence as possible. Additionally, we prove that the objective function of NPIM problem under polarity-related independent cascade model is non-monotone and non-submodular, which means the traditional greedy algorithm is not applicable to the NPIM problem. Thus, we propose an improved R-Greedy algorithm to solve the NPIM problem. Extensive experiments on two Epinions and Slashdot datasets indicate the differences between positive influence and net positive influence, and also demonstrate that our proposed solution performs better than the state-of-the-art methods in terms of promoting net positive influence diffusion in less running time.

Download Full-text