Polarity Related Influence Maximization in Signed Social Networks

Li, Dong; Xu, Zhiming; Chakraborty, Nilanjan; Gupta, Abhinav; Sycara, Katia; Li, Sheng

doi:10.1371/journal.pone.0102199

Cited by 59 publications

(25 citation statements)

References 25 publications

(7 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We compared the EGA with the IC-P Greedy, outdegree heuristic, and random selection method. The IC-P greedy is a recent algorithm for the IM problem [6]. Out-degree heuristic and random selection method are often used for benchmarking.…”

Section: The Competitors (Rakipler)mentioning

confidence: 99%

See 1 more Smart Citation

A New Greedy Algorithm For Influence Maximization On Signed Social Networks

Şimşek¹

2019

GMBD

View full text Add to dashboard Cite

Sosyal etki insanların görüşlerini şekillendiren büyük olgulardan biridir. Bu bakımdan, Etki Maksimizasyonu (EM) problemi viral pazarlama, kamuoyu şekillendirme gibi pratik faydaları olduğu için sosyal ağ analizinde en fazla ilgili çeken araştırma alanlarından biridir. EM probleminin amacı bir sosyal ağ üzerindeki etkili kişi olarak adlandırılan az sayıdaki kişiyi kullanarak bir etkinin (bir fikir veya reklam) ağ üzerindeki yayılımını maksimize etmektir. Etkili kişilerin tespiti birçok durumda NP-Zor bir olasılıksal en iyileme problemidir. Bundan dolayı, EM problemi için birçok algoritma geliştirilmiştir ve geliştirilmeye devam etmektedir. Ne var ki, geliştirilen algoritmalar henüz çözüm kalitesi ve hız açısından istenen seviyede değildirler. Bu çalışmada, bireyler arasındaki olumlu ve olumsuz ilişkileri göz önünde bulunduran işaretli EM problemine odaklanılmıştır. Bu amaçla, en iyi k adet etkili kişiyi tespit etmek için Elitist Aç Gözlü Algoritma (EGA) olarak adlandırılan bir aç gözlü algoritma geliştirmiştir. EGA'nın performansı 2 adet açık veriseti üzerinde rasgele seçim, çıkış derecesi merkeziliği, ve bir güncel algoritma ile kıyaslanmıştır. EGA çözüm kalitesi açısından rakiplerine göre daha iyi sonuçlar vermiştir.https://dx.The social influence is one of the major phenomenons that shape people's decisions. In this respect, Influence Maximization (IM) problem is one of the most attractive research topics in the social network analysis because its practical benefits in viral marketing, public opinions shaping etc. The IM problem aims to maximize the spread of an influence (e.g. an opinion, an advertisement) in a social network by using a small number of the most effective individuals, whom is called influencers. Detecting the influencers is the NP-Hard combinatorial optimization problem in most cases. Therefore, many algorithms have been and are being developed for the IM problem. However, the algorithms have not yet achieved to the desired solution quality and speed. In this study, we focused on the signed IM problem that considers both positive and negative influence between the individuals. For this purpose, we developed a greedy algorithm called the Elitist Greedy Algorithm (EGA) for detecting top-k influencers set. We compared the EGA's performance on 2 public datasets with random seed selection, out degree heuristic, and one stateof-the-art greedy algorithm. The EGA outperforms the competitors in terms of the achieved total influence. https://dx.

show abstract

Section: The Competitors (Rakipler)mentioning

confidence: 99%

“…friend or trust), as well as negative relationships (e.g. distrust) [5], [6]. There is a difference between maximizing the influence in unsigned social networks, and in signed social networks.…”

Section: Introduction (Gi̇ri̇ş)mentioning

confidence: 99%

A New Greedy Algorithm For Influence Maximization On Signed Social Networks

Şimşek¹

2019

GMBD

View full text Add to dashboard Cite

show abstract

“…but also can push the boundaries of researches about dynamical process in complex networks. In addition, empirical results on real-world signed networks demonstrate that incorporating link signs into information diffusion models usually gains influence Li et al 2014b;Shafaei and Jalili 2014]. For example, the voter model with negative links generates at maximum of 38% and 21% more influence in the Epinions dataset compared to the model with only positive links ].…”

Section: Actionsmentioning

confidence: 99%

“…After this opportunity, u i cannot take actions on u j any more in subsequent steps. The authors of [Li et al 2014b] propose a Polarity-related Independent Cascade (ICP) model for signed networks. Each node in the ICP model is assigned to one of [Shafaei and Jalili 2014] introduce an information diffusion model based on the threshold model for signed networks where each node maintains a payoff matrix.…”

Section: Independent Cascade Model For Signedmentioning

confidence: 99%

A Survey of Signed Network Mining in Social Media

et al. 2016

View full text Add to dashboard Cite

Many real-world relations can be represented by signed networks with positive and negative links, as a result of which signed network analysis has attracted increasing attention from multiple disciplines. With the increasing prevalence of social media networks, signed network analysis has evolved from developing and measuring theories to mining tasks. In this article, we present a review of mining signed networks in the context of social media and discuss some promising research directions and new frontiers. We begin by giving basic concepts and unique properties and principles of signed networks. Then we classify and review tasks of signed network mining with representative algorithms. We also delineate some tasks that have not been extensively studied with formal definitions and also propose research directions to expand the field of signed network mining.

show abstract

“…Widely studied diffusion models include epidemic model, independent cascade model, linear threshold model and the variants of these models. Using these models, some researchers investigated the challenging influence maximization problem [7], [8], [9], [10], which is related to viral marketing, and some explored the relationship between information diffusion and social network structures [11], [12]. Although theory-centric models provide partial solutions to the information diffusion problem, they also have inevitable shortcomings.…”

Section: Introductionmentioning

confidence: 99%

Modeling information diffusion over social networks for temporal dynamic prediction

Luo

et al. 2013

Proceedings of the 22nd ACM International Conference on Conference on Information &Amp; Knowledge Management - CIKM '13

Self Cite

View full text Add to dashboard Cite

Abstract-Modeling the process of information diffusion is a challenging problem. Although numerous attempts have been made in order to solve this problem, very few studies are actually able to simulate and predict temporal dynamics of the diffusion process. In this paper, we propose a novel information diffusion model, namely GT model, which treats the nodes of a network as intelligent and rational agents and then calculates their corresponding payoffs, given different choices to make strategic decisions. By introducing time-related payoffs based on the diffusion data, the proposed GT model can be used to predict whether or not the user's behaviors will occur in a specific time interval. The user's payoff can be divided into two parts: social payoff from the user's social contacts and preference payoff from the user's idiosyncratic preference. We here exploit the global influence of the user and the social influence between any two users to accurately calculate the social payoff. In addition, we develop a new method of presenting social influence that can fully capture the temporal dynamics of social influence. Experimental results from two different datasets, Sina Weibo and Flickr, demonstrate the rationality and effectiveness of the proposed prediction method with different evaluation metrics.

show abstract

Polarity Related Influence Maximization in Signed Social Networks

Cited by 59 publications

References 25 publications

A New Greedy Algorithm For Influence Maximization On Signed Social Networks

A New Greedy Algorithm For Influence Maximization On Signed Social Networks

A Survey of Signed Network Mining in Social Media

Modeling information diffusion over social networks for temporal dynamic prediction

Contact Info

Product

Resources

About