Influence Maximization In Social Networks Research Articles

Identifying influential nodes in social networks via community structure and influence distribution difference

This paper aims to effectively solve the problem of the influence maximization in social networks. For this purpose, an influence maximization method that can identify influential nodes via the community structure and the influence distribution difference is proposed. Firstly, the network embedding-based community detection approach is developed, by which the social network is divided into several high-quality communities. Secondly, the solution of influence maximization is composed of the candidate stage and the greedy stage. The candidate stage is to select candidate nodes from the interior and the boundary of each community using a heuristic algorithm, and the greedy stage is to determine seed nodes with the largest marginal influence increment from the candidate set through the sub-modular property-based Greedy algorithm. Finally, experimental results demonstrate the superiority of the proposed method compared with existing methods, from which one can further find that our work can achieve a good tradeoff between the influence spread and the running time.

A neighbour scale fixed approach for influence maximization in social networks

Influence maximization is currently a most extensively researched topic in social network analysis. Existing approaches tackle this task by either pursuing the real influence strength of a node or designing proper measurements for estimating it. The degree is a popularly adopted influence strength metric, based on which a variety of methods have been developed. Though with good efficiency, degree-based methods suffer unsatisfactory accuracy since this metric only covers a limited considered scale over the whole network of interest and also lacks discriminatory power. In this paper, we propose a novel influence maximization method, named Fixed Neighbour Scale (FNS), which extracts useful information from multiple levels of neighbours for a target node to estimate its influence strength, rather than only considering directly connected neighbours as in degree-based methods. To facilitate the implementation of FNS, we also present a centrality measurement termed FNS-dist, which estimates a node’s influence strength by summing its multi-level neighbours’ weights that are mainly determined by their distances to the target node. Experiments conducted on nine networks of different sizes and categories show that the proposed FNS method achieves excellent and stable performance compared with other algorithms based on designing metrics for measuring influence strength. We also exhibit that FNS-dist is a superior alternative centrality which is more proper and precise than the degree.

TSIM: A Two-Stage Selection Algorithm for Influence Maximization in Social Networks

The influence maximization problem is aimed at finding a small subset of nodes in a social./network to maximize the expected number of nodes influenced by these nodes. Influence maximization plays an important role in viral marketing and information diffusion. However, some existing algorithms for influence maximization in social networks perform badly in either efficiency or accuracy. In this paper, we put forward an efficient algorithm, called a two-stage selection for influence maximization in social networks (TSIM). Moreover, a discount-degree descending technology and lazy-forward technology are proposed, called DDLF, to select a certain number of influential nodes as candidate nodes. Firstly, we utilize the strategy to select a certain number of nodes as candidate nodes. Secondly, this paper proposes the maximum influence value function to estimate the marginal influence of each candidate node. Finally, we select seed nodes from candidate nodes according to their maximum influence value. The experimental results on six real-world social networks show that the proposed algorithm outperforms other contrast algorithms while considering accuracy and efficiency comprehensively.

Efficient Influence Maximization in Social-Networks Under Independent Cascade Model

Abstract With in a social network, users interact with each other by sharing news, picture, videos, political content or product promotion content. This makes social networks information diffusion(or marketing) platform. To realize the extent of the adoption of such ideas, it becomes important to study the dynamics of adoption underlying within the social network. However, to analyze social networks as information diffusion/marketing platform, many challenges have to be met. In this paper, we address one of the challenge, namely Influence Maximization in Social Networks. Our main purpose is to select k influential users which can gain maximum spread while cost of selecting k users is minimum. In this paper, a) We have proposed an degree heuristic algorithm under Independent Cascade Model (ICM) to extract top k influential users efficiently. b) A modification in ICM is proposed which derives propagation probability based on similarity metrics. The proposed work is implemented and evaluated on two network data- sets, academic collaboration is taken from the online archival database arXiv.org. The obtained results prove that degree heuristic algorithm is very efficient and has influence spread far better than many centrality based heuristics and close to benchmark greedy algorithm. On the other hand, modification in ICM has a significant stable increase in the influence achieved for implemented algorithms compared to influence achieved by the same algorithms on classic ICM.

Potential-Driven Model for Influence Maximization in Social Networks

The adoption of a new technology, the spreading of ideologies, the transmission of contagions, are examples of spreading phenomena that can be modelled at two distinct levels of resolution, a macroscopic and a microscopic level.In the present work, we consider the network at the microscopic level and represent its nodes as a system of interacting particles and propose a novel, physics-inspired approach. This approach assumes that nodes interact via `forces' that derive from the `potential' that each node creates at the location of the other nodes, leading to a potential gradient that indicates the `natural' direction of diffusion through the network. A set of influencers in the network, is determined from strategically selected nodes based on the value of their net potential. We use synthetic networks of various sizes and compare the influence spread resulting from a seed set determined from the potential-based model and alternate approaches, including the greedy algorithm of Kempe et al. Our findings indicate that this approach achieves comparable results to those of the greedy algorithm without the prohibitive computational cost, and consistently outperforms the other approaches by a large margin. We then apply our methodology to information spreading related to the Twitter Higgs Boson user dataset. The results are analyzed in the context of influence maximization, and we provide insights into the general application of this technique for information dissemination.

LGIM: A Global Selection Algorithm Based on Local Influence for Influence Maximization in Social Networks

Influence maximization is to select k nodes from social networks to maximize the expected number of nodes activated by these selected nodes. Influence maximization problem plays a vital role in commercial marketing, news propagation, rumor control and public services. However, the existing algorithms for influence maximization usually tend to select one aspect from efficiency and accuracy as its main improving objective. This method of excessively pursuing one metric often leads to performing poorly in other metrics. Hence, we think that algorithms for influence maximization should make a suitable compromise between computation efficiency and result accuracy instead of excessively pursuing for one metric. Based on the above understanding, this paper proposes a new algorithm, called Global Selection Based on Local Influence (LGIM). The basic idea of the proposed algorithm is following: if a node can influence another node with large influence, the node also has large influence. Therefore, a two-stage filtering strategy of candidate nodes is proposed, which can reduce a large number of running time. Moreover, this paper also proposes a new objective function to estimate the influence spread of a node set. In summarize, the proposed algorithm utilizes the two-stage filtering strategy of candidate nodes to avoid unnecessary computation, and adopts a new objective function to replace time-consuming Monte-Carle simulations. Experimental results on six real-world social networks demonstrate that the proposed algorithm outperforms other four comparison algorithms when comprehensively considering computation efficiency and result accuracy.

A Modified Degree Discount Heuristic for Influence Maximization in Social Networks

Social networks have become an essential part of our daily lives. These networks are also becoming part of many of our financial and social decisions. Identifying the most influential users in a social network can help minimize the cost of information spread. The search for the most influential users falls within the scope of the influence maximization problem, which is proven to be NP-hard. Many studies have proposed influence maximization heuristics, such as degree and degree-discount algorithms. In this paper, we propose a modified degree-discount (MDD) heuristic and evaluate its performance against single-degree discount, degree, and random algorithms as a baseline. The heuristics are compared using a subgraph of a real Twitter dataset containing 6000 nodes. The results show that the proposed MDD algorithm outperforms the benchmarks in terms of influence maximization for different initial seed sizes.

Neighborhood Matters: Influence Maximization in Social Networks with Limited Access

Influence maximization (IM) aims at maximizing the spread of influence by offering discounts to influential users (called seeding). In many applications, due to user's privacy concern, overwhelming network scale etc., it is hard to target any user in the network as one wishes. Instead, only a small subset of users is initially accessible. Such access limitation would significantly impair the influence spread, since IM often relies on seeding high degree users, which are particularly rare in such a small subset due to the power-law structure of social networks. In this paper, we attempt to solve the limited IM in real-world scenarios by the adaptive approach with seeding and diffusion uncertainty considered. Specifically, we consider fine-grained discounts and assume users accept the discount probabilistically. The diffusion process is depicted by the independent cascade model. To overcome the access limitation, we prove the set-wise friendship paradox (FP) phenomenon that neighbors have higher degree in expectation, and propose a two-stage seeding model with the FP embedded, where neighbors are seeded. On this basis, for comparison we formulate the non-adaptive case and adaptive case, both proven to be NP-hard. In the non-adaptive case, discounts are allocated to users all at once. We show the monotonicity of influence spread w.r.t. discount allocation and design a two-stage coordinate descent framework to decide the discount allocation. In the adaptive case, users are sequentially seeded based on observations of existing seeding and diffusion results. We prove the adaptive submodularity and submodularity of the influence spread function in two stages. Then, a series of adaptive greedy algorithms are proposed with constant approximation ratio.

TPH: A Three-Phase-based Heuristic algorithm for influence maximization in social networks

Influence maximization is a fundamental problem, which is aimed to specify a small number of individuals as seed set to influence the largest number of individuals under a certain influence cascade model. Most existing works on influence maximization may have either high effectiveness or good efficiency,which can not balance both the effectiveness and efficiency. One of the reason is that they do not consider the effect of influence overlap on the effectiveness. That is, these works ignore the phenomenon that the same set of nodes may be influenced by a subset of different influential nodes. To tackle the effectiveness of heuristic algorithm, we propose a three-phase-based heuristic algorithm, called Three-Phase-based Heuristic (TPH), which uses K-shell method to find influential nodes firstly. Moreover, we utilize weighed degree to make up for the coarse-grained of K-shell method. At last, we take advantage of similarity index to reduce the effect of influence overlap by covering the similar neighbor nodes with low influence. Furthermore, exhaustive experiments indicate that the proposed algorithm outperforms the other baseline algorithms in the aspects of influence spread and running time.

Hurst exponent based approach for influence maximization in social networks

Influence maximization in online social networks is a trending research area due to its use in many real-world domains. Influence maximization addresses the problem of identifying a k-size subset of nodes in a social network which can trigger a cascade of further adoptions, leading to maximum influence spread across the social network. In this paper, influence maximization has been proposed by combining a node’s connections and its actual past activity pattern. Analyzing node’s activity with respect to interaction frequency and self-similarity trend, provides a more realistic view of the node’s influence potential. Inspired by this concept, HAC-Rank algorithm has been proposed for identification of initial adopters based on both their connections and past behaviour. Furthermore, a Hurst-based Influence Maximization (HBIM) model for diffusion, wherein a node’s activation depends upon its connections and the self-similarity trend exhibited by its past activity, has also been proposed. For assessing the self-similarity trend in a node’s activity pattern, Hurst exponent (H) has been computed. Based on the results achieved, proposed algorithm has been found to perform better than other state-of-art algorithms for initial adopter identification.

Three-hop velocity attenuation propagation model for influence maximization in social networks

In the study of influence maximization in social networks, the speed of information dissemination decreases with increasing time and distance. The investigation of the characteristics of information dissemination is of great significance to the management and control of public opinion. A three-hop velocity decay propagation model is proposed to determine the propagation speed in information dissemination and the time and distance attenuation factors of information dissemination were modeled. We simulated the three-hop information propagation and developed an influence maximization algorithm based on the rate attenuation propagation model (IMMRA). Experiments using two example data sets showed that the proposed algorithm had higher accuracy and time efficiency than a greedy algorithm.

Semantics-aware influence maximization in social networks

Influence Maximization (IM) plays an essential role in various social network applications. One such application is viral marketing to trigger a large cascade of product adoption from a small number of users by utilizing “Word-of-Mouth” effect in social networks. IM aims to return a set of users that can influence the largest fraction of a network, such as the early user who demonstrates the good features of a product in marketing. The traditional IM algorithms treat all users equally and ignore semantic context associated with the users, though it has been studied previously. To consider the semantics, we introduce a semantics-aware influence maximization (SIM) problem. The SIM problem integrates semantic information of users with influence maximization by measuring influence spread based on semantic values under a given model, and it aims to find a set of users that maximizes the influence spread, shown to be NP-hard. Generalized Reverse Influence Set based framework for SIM problems (GRIS-SIM) is used to solve SIM with different semantics, which provides a (1−1/e−ε)-approximation solution for each SIM instance. To our knowledge, the guarantee is state-of-the-art in the IM studies. GRIS-SIM enables auto-generation of sampling strategies for various social networks. In this study, we also present three sampling strategies that can be generated to achieve the best approximation guarantee, and one of the three is proved to be the optimal strategy by having the same performance guarantee within the optimal time. Furthermore, in order to show the generality and effectiveness of the proposed GRIS technique, we apply it into solving other IM problems (e.g., the distance-aware influence maximization, DAIM). Extensive experiments on both real-life and synthetic datasets demonstrate the effectiveness, efficiency, and scalability of our methods. The results on large real data show that GRIS-SIM is able to achieve 58% improvement on average in expected influence compared with rivals, and the method adopting GRIS can achieve 65% improvement on average.

A node activity and connectivity-based model for influence maximization in social networks

Influence maximization deals with the problem of identifying k-size subset of nodes in a social network that can maximize the influence spread in the network. In this paper, the problem of influence maximization using two aspects, node connectivity and node activity level, has been studied. To measure node connectivity, the widely popular and intuitive measure of out-degree of node has been used, and for node activity, node’s past interactions have been taken into consideration. For studying influence spread, two activity-based diffusion models, namely Activity-based Independent Cascade model and Activity-based Linear Threshold model, have been proposed in which influence propagation is driven by a node’s activity that it has actually performed in the past. Activity-based models aim at studying influence spread by incorporating a more realistic aspect corresponding to user behavior. Motivated by the belief that activity is as important as connectivity, UAC-Rank algorithm for the identification of initial adopters has been proposed.

Pareto Optimization for Subset Selection with Dynamic Cost Constraints

In this paper, we consider the subset selection problem for function f with constraint bound B which changes over time. We point out that adaptive variants of greedy approaches commonly used in the area of submodular optimization are not able to maintain their approximation quality. Investigating the recently introduced POMC Pareto optimization approach, we show that this algorithm efficiently computes a φ = (αf/2)(1− α1f )-approximation, where αf is the sube modularity ratio of f, for each possible constraint bound b ≤ B. Furthermore, we show that POMC is able to adapt its set of solutions quickly in the case that B increases. Our experimental investigations for the influence maximization in social networks show the advantage of POMC over generalized greedy algorithms.

A discrete shuffled frog-leaping algorithm to identify influential nodes for influence maximization in social networks

Influence maximization problem aims to select a subset of k most influential nodes from a given network such that the spread of influence triggered by the seed set will be maximum. Greedy based algorithms are time-consuming to approximate the expected influence spread of given node set accurately and not well scalable to large-scale networks especially when the propagation probability is large. Conventional heuristics based on network topology or confined diffusion paths tend to suffer from the problem of low solution accuracy or huge memory cost. In this paper an effective discrete shuffled frog-leaping algorithm (DSFLA) is proposed to solve influence maximization problem in a more efficient way. Novel encoding mechanism and discrete evolutionary rules are conceived based on network topology structure for virtual frog population. To facilitate the global exploratory solution, a novel local exploitation mechanism combining deterministic and random walk strategies is put forward to improve the suboptimal meme of each memeplex in the frog population. The experimental results of influence spread in six real-world networks and statistical tests show that DSFLA performs effectively in selecting targeted influential seed nodes for influence maximization and is superior than several state-of-the-art alternatives.

Grassroots VS elites: Which ones are better candidates for influence maximization in social networks?

How to select a set of seed users under a limited budget from the social networks to maximize information/influence diffusion is a critical task in the social computing filed, called as influence maximization (IM) problem. Existing studies usually seek users with high influence (“elites”) as seeds. Each selected elite user can take a large influence increment, however, s/he also consumes a high cost (e.g. money). In the time of Web 2.0, ordinary users (“grassroots”) become the main body of the internet and online society, instead of elites. Therefore, we consider whether allocating proportionally the cost of one elite to several grassroots to promote information diffusion can achieve a greater diffusion performance. Following this mind, we propose an alternative solution for the IM problem that attempts to select ordinary grassroots as seeds in this paper. Specifically, we first empirically prove that grassroots are better choices than elites in the IM problem from the aspects of relationship strengths and polarities, based on statistics and analysis of real datasets. Next, we develop a grassroots-oriented seed users seeking algorithm which fully explores the community information of the network structure. Comprehensive experiments on Epinions and Slashdot demonstrate the effectiveness and efficiency of our method.

A most influential node group discovery method for influence maximization in social networks: A trust-based perspective

Developing a computational method for discovering the most influential nodes in social networks is a significant challenge that reveals an approach for maximizing the influence diffusion. To improve the influence degree evaluation mechanism, we propose a trust-based most influential node discovery (TMID) method for discovering influential nodes in a social network. Four phases are performed to establish influence degrees for influential node discovery: (1) an influence propagation process, which reveals the influence diffusion records among nodes for obtaining the categories of nodes in the social network; (2) a trust evaluation method, which provides methods for calculating two types of trust relationships among users, namely, direct trust and indirect trust; (3) an influence evaluation phase, which calculates the explicit binary influence among users (named active influence), the potential binary influence among users (named inactive influence), and the unary influence of nodes (named node influence); and (4) a set of algorithms for discovering the most influential nodes, which comprise two phases: a heuristic phase and a greedy phase. We also list the results of a series of simulation tests for evaluating the performance of our mechanism.

Influence Maximization in Social Network Considering Memory Effect and Social Reinforcement Effect

Social networks have attracted a lot of attention as novel information or advertisement diffusion media for viral marketing. Influence maximization describes the problem of finding a small subset of seed nodes in a social network that could maximize the spread of influence. A lot of algorithms have been proposed to solve this problem. Recently, in order to achieve more realistic viral marketing scenarios, some constrained versions of influence maximization, which consider time constraints, budget constraints and so on, have been proposed. However, none of them considers the memory effect and the social reinforcement effect, which are ubiquitous properties of social networks. In this paper, we define a new constrained version of the influence maximization problem that captures the social reinforcement and memory effects. We first propose a novel propagation model to capture the dynamics of the memory and social reinforcement effects. Then, we modify two baseline algorithms and design a new algorithm to solve the problem under the model. Experiments show that our algorithm achieves the best performance with relatively low time complexity. We also demonstrate that the new version captures some important properties of viral marketing in social networks, such as such as social reinforcements, and could explain some phenomena that cannot be explained by existing influence maximization problem definitions.

Influence Maximization in Social Network with Negative Influence

Influence Maximization in Social Network with Negative Influence

TIFIM: A Two-stage Iterative Framework for Influence Maximization in Social Networks

Influence Maximization is an important problem in social networks, and its main goal is to select some most influential initial nodes (i.e., seed nodes) to obtain the maximal influence spread. The existing studies primarily concentrate on the corresponding methods for influence maximization, including greedy algorithms, heuristic algorithms and their extensions to determine the most influential nodes. However, there is little work to ensure efficiency and accuracy of the proposed schemes at the same time. In this paper, a Two-stage Iterative Framework for the Influence Maximization in social networks, (i.e., TIFIM) is proposed. In order to exclude less influential nodes and decrease the computation complexity of TIFIM, in the first stage, an iterative framework in descending order is proposed to select the candidate nodes. In particular, based on the results of the last iteration and the two-hop measure, the First-Last Allocating Strategy (FLAS) is presented to compute the spread benefit of each node. We prove that TIFIM converges to a stable order within the finite iterations. In the second stage, we define the apical dominance to calculate the overlapping phenomenon of spread benefit among nodes and further propose Removal of the Apical Dominance (RAD) to determine seed nodes from the candidate nodes. Moreover, we also prove that the influence spread of TIFIM according to RAD converges to a specific value within finite computations. Finally, simulation results show that the proposed scheme has superior influence spread and running time than other existing ones.