Keywords: dynamic Social Network, Community detection, Centrality measures, Modularity function.

Size: px
Start display at page:

Download "Keywords: dynamic Social Network, Community detection, Centrality measures, Modularity function."

Transcription

1 Volume 6, Issue 1, January 2016 ISSN: X International Journal of Advanced Research in Computer Science and Software Engineering Research Paper Available online at: An Efficient and Fast Algorithm for Detecting Community Structure in Dynamic Social Network A. Meligy, Ahmed H. Samak, Mai E. Saad Faculty of Science, Menofia University, Egypt Abstract: Community structure is one of the most important properties in social networks. Many algorithms have been proposed to automatically detect communities in static networks but few studies have considered the detection of communities in dynamic networks. This article aims to detecting communities in dynamic social networks. In this paper, we introduce a new algorithm for updating the network communities at any time point by using the information from the previous snapshots as well as network changes whereas the static methods has to be performed on the whole network snapshot up to each time point. The static methods we are comparing to namely Louvain method, Danon algorithm, and SOM algorithm. The experimental results show that our algorithm achieves high modularity and fast running time against static algorithms. Keywords: dynamic Social Network, Community detection, Centrality measures, Modularity function. I. INTRODUCTION Social networks can be generally modeled by a graph, where is the set of vertices and it represents the social actors, and represents the set of edges connecting pairs of vertices and it represents the interactions between them. For a better analysis of a social network, it is usually decomposed into subunits or communities, i.e., a group of nodes sharing something like a group of friends in a social network or a group of web pages dealing with the same subject for instance. Communities are often defined using the network topology as groups of nodes with many links inside the groups but a few links between them. Real-world social networks, however, are not always static. Most studies focus on analyzing communities in static networks, and a few studies investigate the dynamics of communities in evolving social networks. An evolving network is often defined as a sequence of static networks, each of them representing the state of the network at different timestamps, shown in figure 1 [1]. Most complex networks of the real world networks evolve over time. Representing networks with graphs, this evolution can be modeled as the creation or removal of vertices and/or edges over time [2]. On an online social network (such as Facebook, Flicker, and Twitter) people start new relationship with each other, joining in or withdrawing from groups. Any of these changes seems to make a little effect to the structure of the network. Figure 1: Snapshot graphs Since each snapshot is a static graph, the first approach to compute communities on an evolving network is to use a community detection algorithm suited for static graphs on each snapshot. Studies on community detection on static networks can be found on an excellent surveys like [3,4].The main issue after detecting communities at each snapshot is to identify which community has evolved in to which community at time 1 these is the matching problem. A community may merge with another one, split, appear, or disappear overtime. The first approach to solve the matching problem in the context of evolving communities is [5]. It is based on the concept that two communities at successive timesteps are matched if they share a certain number of nodes and have similar size. This matching approach has been generalized in [6] where the authors define many similar rules to handle other cases of communities evolution: merge, split, appearance and disappearance. 2016, IJARCSSE All Rights Reserved Page 65

2 The other approach, which has not been widely followed, is using directly the temporal information during the community detection process. The major lake is now validation tools. However, there are quality functions for static network that people can use to evaluate their algorithms, such general quality functions or validation tools do not exist for evolving networks. In [7] the quality function is modified to integrate evolution. This paper splits the quality function in two terms: a part for the quality of the current snapshot and a part to ensure stability. In [8] Instead of modifying the quality function, Kim et al compute communities at time and if two nodes are in the same community at time and are also connected at, then the weight of the link between them is increased or decreased of a given factor to increase smooth-ness of a modularity optimization algorithm. Studies on community detection on dynamic networks can be found in an excellent survey [1]. II. PRELIMINARIES Notations Throughout this paper, we will use the notation proposed by Nguyen et al in [9]. We assume that undirected unweighted graph with nodes and edges representing a social network. The network community structure is denoted by, where is a community of. For each vertex, let are the community containing and the set of its adjacent communities, respectively. A dynamic network is a sequence of network snapshots evolving over time, with being a state of dynamic network recorded at time. Let be the change in term of the whole network with and denote the sets of vertices and edges to be added or removed from the network at time. Quality function The most popularity quality function is the modularity of Newman and Girvan [10]. The quality of a detected network community structure is often measured by a modularity function to quantify how good a partition is. Modularity can be formulated as be an where is the number of communities, is the total number of edges joining vertices of community,and is the sum of the degrees of the vertices of. In the above formula, the first term is the fraction of edges of the network inside the community, whereas the second term represents the expected fraction of edges that would be there if the network were a random network with the same degree for each vertex. The modularity of a partition is a scalar value between and. The higher modularity, the better the partition is [11]. III. METHOD DESCRIPTION Although one can run any of the static methods, to cluster snapshots of a dynamic graph from scratch, it has several disadvantage: First, the long running time on large networks. Second, optimizations of modularity suffer from local optima. Third, have same reaction approximately to small changes to some local part of the network. In this paper, we propose an algorithm for updating the network communities from previous known structure without reclustering from scratch. We process on network changes only, taking into account the previous network structure. This network changes can be one of newnode, removenode, newedge, removeedge whose details are as follows [9]: newnode ( ): A new node together with its associated edges are introduced. could come with no or more than one new edge(s). removenode ( ): A node and its adjacent edges are removed from the network. newedge( ): A new edge connecting two existing nodes is introduced. removeedge ( ): An existing edge in the network is removed. In this paper, we introduce two algorithms for updating community structure in only two cases (1) New node (2) New edge. Algorithms The first step of our method is to use any of the static community detection algorithms to obtain an initial community structure, in order to process further. 1) New node: The first case when new node and its associated edges are introduced. In this case we first put in a lone community, then compute the graph modularity when new node in a lone community. After that we compute each 2016, IJARCSSE All Rights Reserved Page 66

3 value of modularity when new node changes its initial community to each one of its adjacent communities, finally compare between them, the higher modularity, the better partition for the network. Note when new node come with no associated edges, we put in alone community, and leave the other communities as well as the overall modularity intact. The details of our algorithm are described as follows: Input: New Node with associated links; current structure. Output: An updated structure. 1: Create a new community of only ; 2: compute the graph modularity when new_node at a lone community. 3: for do 4: compute the value of modularity when change its community to the community of its neighbor. 5: end for 6: 7: 8: if 9: update 10: else 11: return Note that, we pre-processed above algorithm by pre-processing steps in [12]. These pre-processing steps will enhance the algorithm, and will make it execute with better results. 2) New edge: In the second case, a new edge connecting two existing vertices is introduced. In this case, we will use the algorithm of [9]. According to [9]this new edge can be divided into two cases : Intra-community link: totally inside a community. Inter-community link: connects two communities and. Lemma 1: For any, if then adding an edge within will increase its modularity contribution [9]. Theorem 1: if is a community of the current snapshot of, then adding any intra-community link to will not split it into smaller modules [9]. Theorem 2: Assume that a new edge is added to. Let and. If will increase the overall modularity [9]. then joining Corollary 1: if the condition in Theorem 2 is not satisfied, then neither nor its neighbors should be moved to [9]. We will do some modification to this algorithm [9] by adding pre-processing steps in [12]. These pre-processing steps capable of raising the modularity of algorithm, and make it execute with better results. IV. EXPERIMENTAL RESULTS In this section, we present the experimental results of our strategy on detecting the communities of dynamic social network. In particular, we will show in experiments the following quantities: modularity values, and the running time of our algorithms in comparison with static method when performed on the whole network snapshot up to each time point. The static methods we are comparing to 1) Louvain method (LM) [13], 2) Danon algorithm [14], 3) Self-organizing map (SOM) [15]. As our algorithm requires initial community structure, we use static algorithm we comparing to at each time to obtain basic structure. As a final comment, our algorithms identifying the network community structure at any time point by utilizing the information from the previous snapshots instead of computing from scratch up to each time point. Real networks We chose 6 networks whose features are reported in Table 1 to perform our experiments. Table 1. Real-World datasets NO. No. nodes No. edges Ref. 1 Karate [16] 2 Dolphins [17] [18] 2016, IJARCSSE All Rights Reserved Page 67 to

4 Common adjective and 4 noun adjacencies in David [19] Copperfield (adjnoun) [20] [21] Zachary's karate club: This is an undirected social network of friendship between 34 members of a karate club at US university. Edges connect individuals who were observed to interact outside the activities of the club. Dolphin social network: Contains an undirected social network of frequent associations of 62 dolphins living in New Zealand. Edges were set between animals that were seen together more often than expected by chance. Political Books: This dataset is the Amazon co-purchasing network with 105 books about US. Nodes are books and edges represent co-purchasing of books by the same buyers. Common adjective and noun adjacencies in David Copperfield: The network of common adjective and noun adjacencies for the novel "David Copperfield" by Charles Dickens. Nodes represent the most commonly occurring adjectives and nouns in the book. Edges connect words that occur in adjacent position in the text of the book. American college dataset: This dataset contains 115 nodes representing teams. An edge exists between two vertices if there is match between two teams. More games happen among teams within the same community than teams from different community. Jass musician network: This dataset is the collaboration network of jazz bands. There are 198 nodes representing the bands, and 2742 edges connecting the bands if there is at least one musician in common. Results 1) New node: The first case when we added a new random node to each of the above social networks, and compare the modularity values, and the running time when using our algorithm which we refer to as Dynamic algorithm with the modularity values when using static algorithm. The obtained results are reported on Table 2, Table 3, and Table 4. Table 2. Results of New_Node using Louvain as static algorithm Static Louvain modularity Time modularity Time Modularity Time Karate Dolphins adjnoun Table 3. Results of New_Node using Danon as static algorithm Static Danon modularity Time Modularity Time Modularity Time Karate Dolphins adjnoun Table 4. Results of New_Node using SOM as static algorithm Static SOM modularity Time modularity Time modularity Time Karate Dolphins , IJARCSSE All Rights Reserved Page 68

5 adjnoun ) New edge: In the second case we added a new edge between two vertices randomly. After that, we compare the modularity value, and the running time. The obtained results are shown in Table 5, Table 6, and Table 7. Table 5. Results of New_Edge using Louvain as static algorithm Static Louvain Modularity Time modularity Time modularity Time Karate Dolphins adjnoun Table 6. Results of New_Edge using Danon as static algorithm Static Danon Modularity Time modularity Time modularity Time Karate Dolphins adjnoun Table 7. Results of New_Edge using SOM as static algorithm Static SOM modularity Time modularity Time modularity Time Karate Dolphins adjnoun V. CONCLUSION In this paper, we introduce a new algorithm for identifying community structure in dynamic social network. Our algorithm updating the network communities at any time point by using the basic community structure and processes on the network changes only whereas static algorithm has to be performed on the whole network snapshot up to each time point. The static methods we are comparing to namely Louvain method, Danon algorithm, and SOM algorithm. Experimental results show that our algorithms achieve better result in modularity values, and fast running time against static algorithms. REFERENCES [1] T. Aynaud, J.-L. Guillaume, Q. Wang, and E. Fleury. Communities in evolving networks: definitions, detections and analysis techniques [2] M. Seifi, J.-L. Guillaume : Community Cores in Evolving Networks, Mining Social Network Dynamic 2012 Workshop (MSND), In conjunction with the international conference World Wide Web WWW 2012, Lyon, France, pp (2012) 2016, IJARCSSE All Rights Reserved Page 69

6 [3] M. Porter, J. Onnela, P. Mucha, Communities in networks, Notices of the American Mathematical Society 56 (9) ,(2009). [4] S. Fortunato," Community detection in graphs", Physics Reports 486 (3 5) ,(2010). [5] J. Hopcroft, O. Khan, B. Kulis, B. Selman, Tracking evolving communities in large linked networks, in: National Academy of Sciences of the United States of America, volume 101, National Acad Sciences, 2004, p [6] M. Spiliopoulou, I. Ntoutsi, Y. Theodoridis, R. Schult, Monic: modeling and monitoring cluster transitions, in: Proceedings of the 12th ACM SIGKDD international conference on Knowledge discovery and data mining, ACM New York, NY, USA, 2006, pp. 706{711. [7] R. Kumar, A. Tomkins, D. Chakrabarti, Evolutionary clustering, in: In Proc. of the 12th ACM SIGKDD Conference. [8] M. Kim, J. Han, A particle-and-density based evolutionary clustering method for dynamic networks, Proceedings of the VLDB Endowment 2 (2009) 622{633. [9] Nguyen, N.P.; Dinh, T.N.; Xuan, Y.; Thai, M.T. Adaptive Algorithms for Detecting Community Structure in Dynamic Social Networks. In Proceedings of the IEEE Conference on Computer. [10] M. E. J. Newman, "Modularity and community structure in networks", Proceedings of the National Academy of Sciences (PNAS), 103(23), , [11] F. Borko, "Hand book of Social Network Technologies and Applications" 2010, Springer. [12] A Meligy, Ahmed H Samak and Mai E Saad. Article: A new Pre-processing Strategy for Improving Community Detection Algorithms. International Journal of Computer Applications 119(16):16-20, June [13] V. Blondel, J. Guillaume, R. Lambiotte, E. Lefebvre, "Fast unfolding of communities in large networks, Journal of Statistical Mechanics", Theory and Experiment,10, (P10008), (2008) [14] L. Danon, A. Díaz-Guilera, A. Arenas," The effect of size heterogeneity on community identification in complex networks", J. Stat. Mech. 11 (2006). [15] Z. Li, R. Wang, X. Zhang, and L. Chen, "Self-organizing map of complex networks for community detection", Journal of Systems Science and Complexity, 23(5), , [16] W. Zachary, "An information flow model for conflict and fission in small groups", Journal of Anthropological Research, 33: , [17] D. Lusseau, K. Schneider, J. Oliver Boisseau, P. Haase, E. Slooten, and S. Dawson," The bottlenose dolphin community of Doubtful Sound features a large proportion of long-lasting associations", Behavioral Ecology and Sociobiology, 54(4): , [18] V. Krebs, [ [19] M. E. J. Newman."Finding community structure in networks using the eigenvectors of matrices",phys. Rev. E, 74:036104, [20] M. Girvan, M. E. J. Newman, "Community structure in social and biological networks", Proceedings of the National Academy of Sciences (PNAS), 99(12), , [21] P. Gleiser and L Danon." Community structure in jazz", Advances in Complex Systems, 06(04): , , IJARCSSE All Rights Reserved Page 70

A new Pre-processing Strategy for Improving Community Detection Algorithms

A new Pre-processing Strategy for Improving Community Detection Algorithms A new Pre-processing Strategy for Improving Community Detection Algorithms A. Meligy Professor of Computer Science, Faculty of Science, Ahmed H. Samak Asst. Professor of computer science, Faculty of Science,

More information

Discovery of Community Structure in Complex Networks Based on Resistance Distance and Center Nodes

Discovery of Community Structure in Complex Networks Based on Resistance Distance and Center Nodes Journal of Computational Information Systems 8: 23 (2012) 9807 9814 Available at http://www.jofcis.com Discovery of Community Structure in Complex Networks Based on Resistance Distance and Center Nodes

More information

CUT: Community Update and Tracking in Dynamic Social Networks

CUT: Community Update and Tracking in Dynamic Social Networks CUT: Community Update and Tracking in Dynamic Social Networks Hao-Shang Ma National Cheng Kung University No.1, University Rd., East Dist., Tainan City, Taiwan ablove904@gmail.com ABSTRACT Social network

More information

Static community detection algorithms for evolving networks

Static community detection algorithms for evolving networks Static community detection algorithms for evolving networks Thomas Aynaud, Jean-Loup Guillaume To cite this version: Thomas Aynaud, Jean-Loup Guillaume. Static community detection algorithms for evolving

More information

Community Detection Methods using Eigenvectors of Matrices

Community Detection Methods using Eigenvectors of Matrices Community Detection Methods using Eigenvectors of Matrices Yan Zhang Abstract In this paper we investigate the problem of detecting communities in graphs. We use the eigenvectors of the graph Laplacian

More information

EXTREMAL OPTIMIZATION AND NETWORK COMMUNITY STRUCTURE

EXTREMAL OPTIMIZATION AND NETWORK COMMUNITY STRUCTURE EXTREMAL OPTIMIZATION AND NETWORK COMMUNITY STRUCTURE Noémi Gaskó Department of Computer Science, Babeş-Bolyai University, Cluj-Napoca, Romania gaskonomi@cs.ubbcluj.ro Rodica Ioana Lung Department of Statistics,

More information

Social Data Management Communities

Social Data Management Communities Social Data Management Communities Antoine Amarilli 1, Silviu Maniu 2 January 9th, 2018 1 Télécom ParisTech 2 Université Paris-Sud 1/20 Table of contents Communities in Graphs 2/20 Graph Communities Communities

More information

Network community detection with edge classifiers trained on LFR graphs

Network community detection with edge classifiers trained on LFR graphs Network community detection with edge classifiers trained on LFR graphs Twan van Laarhoven and Elena Marchiori Department of Computer Science, Radboud University Nijmegen, The Netherlands Abstract. Graphs

More information

Crawling and Detecting Community Structure in Online Social Networks using Local Information

Crawling and Detecting Community Structure in Online Social Networks using Local Information Crawling and Detecting Community Structure in Online Social Networks using Local Information Norbert Blenn, Christian Doerr, Bas Van Kester, Piet Van Mieghem Department of Telecommunication TU Delft, Mekelweg

More information

SOMSN: An Effective Self Organizing Map for Clustering of Social Networks

SOMSN: An Effective Self Organizing Map for Clustering of Social Networks SOMSN: An Effective Self Organizing Map for Clustering of Social Networks Fatemeh Ghaemmaghami Research Scholar, CSE and IT Dept. Shiraz University, Shiraz, Iran Reza Manouchehri Sarhadi Research Scholar,

More information

On community detection in very large networks

On community detection in very large networks On community detection in very large networks Alexandre P. Francisco and Arlindo L. Oliveira INESC-ID / CSE Dept, IST, Tech Univ of Lisbon Rua Alves Redol 9, 1000-029 Lisboa, PT {aplf,aml}@inesc-id.pt

More information

Dynamic network generative model

Dynamic network generative model Dynamic network generative model Habiba, Chayant Tantipathanananandh, Tanya Berger-Wolf University of Illinois at Chicago. In this work we present a statistical model for generating realistic dynamic networks

More information

Using Stable Communities for Maximizing Modularity

Using Stable Communities for Maximizing Modularity Using Stable Communities for Maximizing Modularity S. Srinivasan and S. Bhowmick Department of Computer Science, University of Nebraska at Omaha Abstract. Modularity maximization is an important problem

More information

Community Structure Detection. Amar Chandole Ameya Kabre Atishay Aggarwal

Community Structure Detection. Amar Chandole Ameya Kabre Atishay Aggarwal Community Structure Detection Amar Chandole Ameya Kabre Atishay Aggarwal What is a network? Group or system of interconnected people or things Ways to represent a network: Matrices Sets Sequences Time

More information

Community Detection: Comparison of State of the Art Algorithms

Community Detection: Comparison of State of the Art Algorithms Community Detection: Comparison of State of the Art Algorithms Josiane Mothe IRIT, UMR5505 CNRS & ESPE, Univ. de Toulouse Toulouse, France e-mail: josiane.mothe@irit.fr Karen Mkhitaryan Institute for Informatics

More information

Non Overlapping Communities

Non Overlapping Communities Non Overlapping Communities Davide Mottin, Konstantina Lazaridou HassoPlattner Institute Graph Mining course Winter Semester 2016 Acknowledgements Most of this lecture is taken from: http://web.stanford.edu/class/cs224w/slides

More information

ALTERNATIVES TO BETWEENNESS CENTRALITY: A MEASURE OF CORRELATION COEFFICIENT

ALTERNATIVES TO BETWEENNESS CENTRALITY: A MEASURE OF CORRELATION COEFFICIENT ALTERNATIVES TO BETWEENNESS CENTRALITY: A MEASURE OF CORRELATION COEFFICIENT Xiaojia He 1 and Natarajan Meghanathan 2 1 University of Georgia, GA, USA, 2 Jackson State University, MS, USA 2 natarajan.meghanathan@jsums.edu

More information

Adaptive Algorithms for Detecting Community Structure in Dynamic Social Networks

Adaptive Algorithms for Detecting Community Structure in Dynamic Social Networks This paper was presented as part of the main technical program at IEEE INFOCOM 2 Adaptive Algorithms for Detecting Community Structure in Dynamic Social Networks Nam P. Nguyen, Thang N. Dinh, Ying Xuan,

More information

Community Detection Algorithm based on Centrality and Node Closeness in Scale-Free Networks

Community Detection Algorithm based on Centrality and Node Closeness in Scale-Free Networks 234 29 2 SP-B 2014 Community Detection Algorithm based on Centrality and Node Closeness in Scale-Free Networks Sorn Jarukasemratana Tsuyoshi Murata Xin Liu 1 Tokyo Institute of Technology sorn.jaru@ai.cs.titech.ac.jp

More information

Community Detection by Affinity Propagation

Community Detection by Affinity Propagation Community Detection by Affinity Propagation Zhiyuan Liu, Peng Li, Yabin Zheng, and Maosong Sun Department of Computer Science and Technology, State Key Lab on Intelligent Technology and Systems, National

More information

Basics of Network Analysis

Basics of Network Analysis Basics of Network Analysis Hiroki Sayama sayama@binghamton.edu Graph = Network G(V, E): graph (network) V: vertices (nodes), E: edges (links) 1 Nodes = 1, 2, 3, 4, 5 2 3 Links = 12, 13, 15, 23,

More information

arxiv: v1 [cs.si] 11 Jan 2019

arxiv: v1 [cs.si] 11 Jan 2019 A Community-aware Network Growth Model for Synthetic Social Network Generation Furkan Gursoy furkan.gursoy@boun.edu.tr Bertan Badur bertan.badur@boun.edu.tr arxiv:1901.03629v1 [cs.si] 11 Jan 2019 Dept.

More information

Detecting Community Structure for Undirected Big Graphs Based on Random Walks

Detecting Community Structure for Undirected Big Graphs Based on Random Walks Detecting Community Structure for Undirected Big Graphs Based on Random Walks Xiaoming Liu 1, Yadong Zhou 1, Chengchen Hu 1, Xiaohong Guan 1,, Junyuan Leng 1 1 MOE KLNNIS Lab, Xi an Jiaotong University,

More information

Efficient Community Detection Algorithm with Label Propagation using Node Importance and Link Weight

Efficient Community Detection Algorithm with Label Propagation using Node Importance and Link Weight Efficient Community Detection Algorithm with Label Propagation using Node Importance and Link Weight Mohsen Arab, Mahdieh Hasheminezhad* Department of Computer Science Yazd University, Yazd, Iran Abstract

More information

An Empirical Analysis of Communities in Real-World Networks

An Empirical Analysis of Communities in Real-World Networks An Empirical Analysis of Communities in Real-World Networks Chuan Sheng Foo Computer Science Department Stanford University csfoo@cs.stanford.edu ABSTRACT Little work has been done on the characterization

More information

V4 Matrix algorithms and graph partitioning

V4 Matrix algorithms and graph partitioning V4 Matrix algorithms and graph partitioning - Community detection - Simple modularity maximization - Spectral modularity maximization - Division into more than two groups - Other algorithms for community

More information

Community detection using boundary nodes in complex networks

Community detection using boundary nodes in complex networks Community detection using boundary nodes in complex networks Mursel Tasgin and Haluk O. Bingol Department of Computer Engineering Bogazici University, Istanbul In this paper, we propose a new community

More information

Community detection. Leonid E. Zhukov

Community detection. Leonid E. Zhukov Community detection Leonid E. Zhukov School of Data Analysis and Artificial Intelligence Department of Computer Science National Research University Higher School of Economics Network Science Leonid E.

More information

My favorite application using eigenvalues: partitioning and community detection in social networks

My favorite application using eigenvalues: partitioning and community detection in social networks My favorite application using eigenvalues: partitioning and community detection in social networks Will Hobbs February 17, 2013 Abstract Social networks are often organized into families, friendship groups,

More information

SCALABLE LOCAL COMMUNITY DETECTION WITH MAPREDUCE FOR LARGE NETWORKS

SCALABLE LOCAL COMMUNITY DETECTION WITH MAPREDUCE FOR LARGE NETWORKS SCALABLE LOCAL COMMUNITY DETECTION WITH MAPREDUCE FOR LARGE NETWORKS Ren Wang, Andong Wang, Talat Iqbal Syed and Osmar R. Zaïane Department of Computing Science, University of Alberta, Canada ABSTRACT

More information

CAIM: Cerca i Anàlisi d Informació Massiva

CAIM: Cerca i Anàlisi d Informació Massiva 1 / 72 CAIM: Cerca i Anàlisi d Informació Massiva FIB, Grau en Enginyeria Informàtica Slides by Marta Arias, José Balcázar, Ricard Gavaldá Department of Computer Science, UPC Fall 2016 http://www.cs.upc.edu/~caim

More information

Detecting and Analyzing Communities in Social Network Graphs for Targeted Marketing

Detecting and Analyzing Communities in Social Network Graphs for Targeted Marketing Detecting and Analyzing Communities in Social Network Graphs for Targeted Marketing Gautam Bhat, Rajeev Kumar Singh Department of Computer Science and Engineering Shiv Nadar University Gautam Buddh Nagar,

More information

MULTI-SCALE COMMUNITY DETECTION USING STABILITY AS OPTIMISATION CRITERION IN A GREEDY ALGORITHM

MULTI-SCALE COMMUNITY DETECTION USING STABILITY AS OPTIMISATION CRITERION IN A GREEDY ALGORITHM MULTI-SCALE COMMUNITY DETECTION USING STABILITY AS OPTIMISATION CRITERION IN A GREEDY ALGORITHM Erwan Le Martelot, Chris Hankin Imperial College London, Department of Computing, South Kensington Campus,

More information

Fast algorithm for detecting community structure in networks

Fast algorithm for detecting community structure in networks PHYSICAL REVIEW E 69, 066133 (2004) Fast algorithm for detecting community structure in networks M. E. J. Newman Department of Physics and Center for the Study of Complex Systems, University of Michigan,

More information

Mining Social Network Graphs

Mining Social Network Graphs Mining Social Network Graphs Analysis of Large Graphs: Community Detection Rafael Ferreira da Silva rafsilva@isi.edu http://rafaelsilva.com Note to other teachers and users of these slides: We would be

More information

A New Vertex Similarity Metric for Community Discovery: A Local Flow Model

A New Vertex Similarity Metric for Community Discovery: A Local Flow Model JOURNAL OF SOFTWARE, VOL 6, NO 8, AUGUST 2011 1545 A New Vertex Similarity Metric for Community Discovery: A Local Flow Model Yueping Li, Yunming Ye and Xiaolin Du Shenzhen Graduate School, Harbin Institute

More information

Modularity CMSC 858L

Modularity CMSC 858L Modularity CMSC 858L Module-detection for Function Prediction Biological networks generally modular (Hartwell+, 1999) We can try to find the modules within a network. Once we find modules, we can look

More information

Studying the Properties of Complex Network Crawled Using MFC

Studying the Properties of Complex Network Crawled Using MFC Studying the Properties of Complex Network Crawled Using MFC Varnica 1, Mini Singh Ahuja 2 1 M.Tech(CSE), Department of Computer Science and Engineering, GNDU Regional Campus, Gurdaspur, Punjab, India

More information

An Efficient Algorithm for Community Detection in Complex Networks

An Efficient Algorithm for Community Detection in Complex Networks An Efficient Algorithm for Community Detection in Complex Networks Qiong Chen School of Computer Science & Engineering South China University of Technology Guangzhou Higher Education Mega Centre Panyu

More information

Expected Nodes: a quality function for the detection of link communities

Expected Nodes: a quality function for the detection of link communities Expected Nodes: a quality function for the detection of link communities Noé Gaumont 1, François Queyroi 2, Clémence Magnien 1 and Matthieu Latapy 1 1 Sorbonne Universités, UPMC Univ Paris 06, UMR 7606,

More information

Weighted Label Propagation Algorithm based on Local Edge Betweenness

Weighted Label Propagation Algorithm based on Local Edge Betweenness Weighted Label Propagation Algorithm based on Local Edge Betweenness Hamid Shahrivari Joghan, Alireza Bagheri, Meysam Azad Department of Computer Engineering and Information Technology, Amir Kabir University

More information

2007 by authors and 2007 World Scientific Publishing Company

2007 by authors and 2007 World Scientific Publishing Company Electronic version of an article published as J. M. Kumpula, J. Saramäki, K. Kaski, J. Kertész, Limited resolution and multiresolution methods in complex network community detection, Fluctuation and Noise

More information

Generalized Louvain method for community detection in large networks

Generalized Louvain method for community detection in large networks Generalized Louvain method for community detection in large networks Pasquale De Meo, Emilio Ferrara, Giacomo Fiumara, Alessandro Provetti, Dept. of Physics, Informatics Section. Dept. of Mathematics.

More information

A Novel Particle Swarm Optimization Algorithm for Network Clustering

A Novel Particle Swarm Optimization Algorithm for Network Clustering A Novel Particle Swarm Optimization Algorithm for Network Clustering Zhaoxing Li 1, 2*, Lile,He 1,Ze Li 1,Yunrui Li 3 1 School of Mechanical & Electrical Engineering Xi an University of Architecture and

More information

Oh Pott, Oh Pott! or how to detect community structure in complex networks

Oh Pott, Oh Pott! or how to detect community structure in complex networks Oh Pott, Oh Pott! or how to detect community structure in complex networks Jörg Reichardt Interdisciplinary Centre for Bioinformatics, Leipzig, Germany (Host of the 2012 Olympics) Questions to start from

More information

Finding Hierarchical Communities in Complex Networks Using Influence-Guided Label Propagation

Finding Hierarchical Communities in Complex Networks Using Influence-Guided Label Propagation Finding Hierarchical Communities in Complex Networks Using Influence-Guided Label Propagation Wenjun Wang and W. Nick Street Department of Management Sciences University of Iowa Iowa City, IA 52242, USA

More information

Research Article An Improved Topology-Potential-Based Community Detection Algorithm for Complex Network

Research Article An Improved Topology-Potential-Based Community Detection Algorithm for Complex Network e Scientific World Journal, Article ID 121609, 7 pages http://dx.doi.org/10.1155/2014/121609 Research Article An Improved Topology-Potential-Based Community Detection Algorithm for Complex Network Zhixiao

More information

Community Detection in Networks using Node Attributes and Modularity

Community Detection in Networks using Node Attributes and Modularity Community Detection in Networks using Node Attributes and Modularity Yousra Asim Rubina Ghazal Wajeeha Naeem Abstract Community detection in network is of vital importance to find cohesive subgroups. Node

More information

An information-theoretic framework for resolving community structure in complex networks

An information-theoretic framework for resolving community structure in complex networks An information-theoretic framework for resolving community structure in complex networks Martin Rosvall, and Carl T. Bergstrom PNAS published online Apr 23, 2007; doi:10.1073/pnas.0611034104 This information

More information

Hierarchical Overlapping Community Discovery Algorithm Based on Node purity

Hierarchical Overlapping Community Discovery Algorithm Based on Node purity Hierarchical Overlapping ommunity Discovery Algorithm Based on Node purity Guoyong ai, Ruili Wang, and Guobin Liu Guilin University of Electronic Technology, Guilin, Guangxi, hina ccgycai@guet.edu.cn,

More information

Efficient Mining Algorithms for Large-scale Graphs

Efficient Mining Algorithms for Large-scale Graphs Efficient Mining Algorithms for Large-scale Graphs Yasunari Kishimoto, Hiroaki Shiokawa, Yasuhiro Fujiwara, and Makoto Onizuka Abstract This article describes efficient graph mining algorithms designed

More information

A locally optimal heuristic for modularity maximization of networks. Abstract

A locally optimal heuristic for modularity maximization of networks. Abstract A locally optimal heuristic for modularity maximization of networks Sonia Cafieri Dept. Mathématiques et Informatique, École Nationale de l Aviation Civile, 7 ave. E. Belin, F-31055 Toulouse, France Pierre

More information

CS224W: Analysis of Networks Jure Leskovec, Stanford University

CS224W: Analysis of Networks Jure Leskovec, Stanford University CS224W: Analysis of Networks Jure Leskovec, Stanford University http://cs224w.stanford.edu 11/13/17 Jure Leskovec, Stanford CS224W: Analysis of Networks, http://cs224w.stanford.edu 2 Observations Models

More information

A Seed-Centric Community Detection Algorithm based on an Expanding Ring Search

A Seed-Centric Community Detection Algorithm based on an Expanding Ring Search Proceedings of the First Australasian Web Conference (AWC 2013), Adelaide, Australia A eed-centric Community Detection Algorithm based on an Expanding Ring earch Kwan Hui Lim Amitava Datta chool of Computer

More information

Edge Representation Learning for Community Detection in Large Scale Information Networks

Edge Representation Learning for Community Detection in Large Scale Information Networks Edge Representation Learning for Community Detection in Large Scale Information Networks Suxue Li 1, Haixia Zhang 1, Dalei Wu 2, Chuanting Zhang 1, and Dongfeng Yuan 1 1 Shandong Provincial Key Laboratory

More information

Adaptive Modularity Maximization via Edge Weighting Scheme

Adaptive Modularity Maximization via Edge Weighting Scheme Information Sciences, Elsevier, accepted for publication September 2018 Adaptive Modularity Maximization via Edge Weighting Scheme Xiaoyan Lu a, Konstantin Kuzmin a, Mingming Chen b, Boleslaw K. Szymanski

More information

Chapter 2 Detecting the Overlapping and Hierarchical Community Structure in Networks 2.1 Introduction

Chapter 2 Detecting the Overlapping and Hierarchical Community Structure in Networks 2.1 Introduction Chapter 2 Detecting the Overlapping and Hierarchical Community Structure in Networks 2.1 Introduction As described in the previous chapter, community structure is a common and important topological characteristic

More information

Characteristics of Preferentially Attached Network Grown from. Small World

Characteristics of Preferentially Attached Network Grown from. Small World Characteristics of Preferentially Attached Network Grown from Small World Seungyoung Lee Graduate School of Innovation and Technology Management, Korea Advanced Institute of Science and Technology, Daejeon

More information

Context-Sensitive Detection of Local Community Structure

Context-Sensitive Detection of Local Community Structure Context-Sensitive Detection of Local Community Structure L. Karl Branting The MITRE Corporation 7525 Colshire Drive McLean, Virginia USA Email: lbranting@mitre.org Abstract Local methods for detecting

More information

Community Detection via Semi Synchronous Label Propagation Algorithms

Community Detection via Semi Synchronous Label Propagation Algorithms Community Detection via Semi Synchronous Label Propagation Algorithms Gennaro Cordasco and Luisa Gargano Dipartimento di Informatica ed Applicazioni R.M. Capocelli University of Salerno, Fisciano 84084,

More information

An Optimal Allocation Approach to Influence Maximization Problem on Modular Social Network. Tianyu Cao, Xindong Wu, Song Wang, Xiaohua Hu

An Optimal Allocation Approach to Influence Maximization Problem on Modular Social Network. Tianyu Cao, Xindong Wu, Song Wang, Xiaohua Hu An Optimal Allocation Approach to Influence Maximization Problem on Modular Social Network Tianyu Cao, Xindong Wu, Song Wang, Xiaohua Hu ACM SAC 2010 outline Social network Definition and properties Social

More information

Community Detection in Bipartite Networks:

Community Detection in Bipartite Networks: Community Detection in Bipartite Networks: Algorithms and Case Studies Kathy Horadam and Taher Alzahrani Mathematical and Geospatial Sciences, RMIT Melbourne, Australia IWCNA 2014 Community Detection,

More information

A Simple Acceleration Method for the Louvain Algorithm

A Simple Acceleration Method for the Louvain Algorithm A Simple Acceleration Method for the Louvain Algorithm Naoto Ozaki, Hiroshi Tezuka, Mary Inaba * Graduate School of Information Science and Technology, University of Tokyo, Tokyo, Japan. * Corresponding

More information

Analysis of Dendrogram Tree for Identifying and Visualizing Trends in Multi-attribute Transactional Data

Analysis of Dendrogram Tree for Identifying and Visualizing Trends in Multi-attribute Transactional Data Analysis of Dendrogram Tree for Identifying and Visualizing Trends in Multi-attribute Transactional Data D.Radha Rani 1, A.Vini Bharati 2, P.Lakshmi Durga Madhuri 3, M.Phaneendra Babu 4, A.Sravani 5 Department

More information

Loops and multiple edges in modularity maximization of networks. Abstract

Loops and multiple edges in modularity maximization of networks. Abstract Loops and multiple edges in modularity maximization of networks Sonia Cafieri, Pierre Hansen, and Leo Liberti LIX, École Polytechnique, F-91128 Palaiseau, France (Dated: January 25, 2010) Abstract The

More information

Modeling Dynamic Behavior in Large Evolving Graphs

Modeling Dynamic Behavior in Large Evolving Graphs Modeling Dynamic Behavior in Large Evolving Graphs R. Rossi, J. Neville, B. Gallagher, and K. Henderson Presented by: Doaa Altarawy 1 Outline - Motivation - Proposed Model - Definitions - Modeling dynamic

More information

Community Detection by Modularity Maximization using GRASP with Path Relinking

Community Detection by Modularity Maximization using GRASP with Path Relinking Community Detection by Modularity Maximization using GRASP with Path Relinking Mariá C. V. Nascimento 1 and Leonidas S. Pitsoulis 2 1 Instituto de Ciência e Tecnologia, Universidade Federal de São Paulo

More information

Social-Network Graphs

Social-Network Graphs Social-Network Graphs Mining Social Networks Facebook, Google+, Twitter Email Networks, Collaboration Networks Identify communities Similar to clustering Communities usually overlap Identify similarities

More information

CSE 316: SOCIAL NETWORK ANALYSIS INTRODUCTION. Fall 2017 Marion Neumann

CSE 316: SOCIAL NETWORK ANALYSIS INTRODUCTION. Fall 2017 Marion Neumann CSE 316: SOCIAL NETWORK ANALYSIS Fall 2017 Marion Neumann INTRODUCTION Contents in these slides may be subject to copyright. Some materials are adopted from: http://www.cs.cornell.edu/home /kleinber/ networks-book,

More information

Overlapping Communities

Overlapping Communities Yangyang Hou, Mu Wang, Yongyang Yu Purdue Univiersity Department of Computer Science April 25, 2013 Overview Datasets Algorithm I Algorithm II Algorithm III Evaluation Overview Graph models of many real

More information

Collaborative Filtering based on Dynamic Community Detection

Collaborative Filtering based on Dynamic Community Detection Collaborative Filtering based on Dynamic Community Detection Sabrine Ben Abdrabbah, Raouia Ayachi, and Nahla Ben Amor LARODEC, Université de Tunis, ISG Tunis, 2000, Bardo, Tunisia abidrabbah.sabrine@gmail.com,raouia.ayachi@gmail.com,nahla.benamor@gmx.fr

More information

Social Networks. of Science and Technology, Wuhan , China

Social Networks. of Science and Technology, Wuhan , China l 1 -Graph Based Community Detection in Online Social Networks Liang Huang 1,RuixuanLi 1,, Yuhua Li 1, Xiwu Gu 1, Kunmei Wen 1, and Zhiyong Xu 2 1 School of Computer Science and Technology, Huazhong University

More information

Generalized Modularity for Community Detection

Generalized Modularity for Community Detection Generalized Modularity for Community Detection Mohadeseh Ganji 1,3, Abbas Seifi 1, Hosein Alizadeh 2, James Bailey 3, and Peter J. Stuckey 3 1 Amirkabir University of Technology, Tehran, Iran, aseifi@aut.ac.ir,

More information

Graph Sampling Approach for Reducing. Computational Complexity of. Large-Scale Social Network

Graph Sampling Approach for Reducing. Computational Complexity of. Large-Scale Social Network Journal of Innovative Technology and Education, Vol. 3, 216, no. 1, 131-137 HIKARI Ltd, www.m-hikari.com http://dx.doi.org/1.12988/jite.216.6828 Graph Sampling Approach for Reducing Computational Complexity

More information

Privacy-Preserving of Check-in Services in MSNS Based on a Bit Matrix

Privacy-Preserving of Check-in Services in MSNS Based on a Bit Matrix BULGARIAN ACADEMY OF SCIENCES CYBERNETICS AND INFORMATION TECHNOLOGIES Volume 15, No 2 Sofia 2015 Print ISSN: 1311-9702; Online ISSN: 1314-4081 DOI: 10.1515/cait-2015-0032 Privacy-Preserving of Check-in

More information

Online Social Networks and Media. Community detection

Online Social Networks and Media. Community detection Online Social Networks and Media Community detection 1 Notes on Homework 1 1. You should write your own code for generating the graphs. You may use SNAP graph primitives (e.g., add node/edge) 2. For the

More information

Social and Technological Network Analysis. Lecture 4: Community Detec=on and Overlapping Communi=es. Prof. Cecilia Mascolo

Social and Technological Network Analysis. Lecture 4: Community Detec=on and Overlapping Communi=es. Prof. Cecilia Mascolo Social and Technological Network Analysis Lecture 4: Community Detec=on and Overlapping Communi=es Prof. Cecilia Mascolo Communi=es Weak =es (Lecture 2) seemed to bridge groups of =ghtly coupled nodes

More information

ISSN: (Online) Volume 2, Issue 1, January 2014 International Journal of Advance Research in Computer Science and Management Studies

ISSN: (Online) Volume 2, Issue 1, January 2014 International Journal of Advance Research in Computer Science and Management Studies ISSN: 2321-7782 (Online) Volume 2, Issue 1, January 2014 International Journal of Advance Research in Computer Science and Management Studies Research Paper Available online at: www.ijarcsms.com A Survey

More information

Community Detection in Social Networks

Community Detection in Social Networks San Jose State University SJSU ScholarWorks Master's Projects Master's Theses and Graduate Research Spring 5-24-2017 Community Detection in Social Networks Ketki Kulkarni San Jose State University Follow

More information

A Parallel Community Detection Algorithm for Big Social Networks

A Parallel Community Detection Algorithm for Big Social Networks A Parallel Community Detection Algorithm for Big Social Networks Yathrib AlQahtani College of Computer and Information Sciences King Saud University Collage of Computing and Informatics Saudi Electronic

More information

caution in interpreting graph-theoretic diagnostics

caution in interpreting graph-theoretic diagnostics April 17, 2013 What is a network [1, 2, 3] What is a network [1, 2, 3] What is a network [1, 2, 3] What is a network [1, 2, 3] What is a network a collection of more or less identical agents or objects,

More information

Dynamic Clustering of Data with Modified K-Means Algorithm

Dynamic Clustering of Data with Modified K-Means Algorithm 2012 International Conference on Information and Computer Networks (ICICN 2012) IPCSIT vol. 27 (2012) (2012) IACSIT Press, Singapore Dynamic Clustering of Data with Modified K-Means Algorithm Ahamed Shafeeq

More information

Supplementary material to Epidemic spreading on complex networks with community structures

Supplementary material to Epidemic spreading on complex networks with community structures Supplementary material to Epidemic spreading on complex networks with community structures Clara Stegehuis, Remco van der Hofstad, Johan S. H. van Leeuwaarden Supplementary otes Supplementary ote etwork

More information

Understanding complex networks with community-finding algorithms

Understanding complex networks with community-finding algorithms Understanding complex networks with community-finding algorithms Eric D. Kelsic 1 SURF 25 Final Report 1 California Institute of Technology, Pasadena, CA 91126, USA (Dated: November 1, 25) In a complex

More information

A Convex Formulation of Modularity Maximization for Community Detection

A Convex Formulation of Modularity Maximization for Community Detection Proceedings of the Twenty-Second International Joint Conference on Artificial Intelligence A Convex Formulation of Modularity Maximization for Community Detection Emprise Y. K. Chan Dit-Yan Yeung Department

More information

Overlapping Community Detection in Social Network Using Disjoint Community Detection

Overlapping Community Detection in Social Network Using Disjoint Community Detection 2015 IEEE Symposium Series on Computational Intelligence Overlapping Community Detection in Social Network Using Disjoint Community Detection Jaswant Meena Department of Computer Science and Automation

More information

Community Detection based on Structural and Attribute Similarities

Community Detection based on Structural and Attribute Similarities Community Detection based on Structural and Attribute Similarities The Anh Dang, Emmanuel Viennet L2TI - Institut Galilée - Université Paris-Nord 99, avenue Jean-Baptiste Clément - 93430 Villetaneuse -

More information

The Establishment Game. Motivation

The Establishment Game. Motivation Motivation Motivation The network models so far neglect the attributes, traits of the nodes. A node can represent anything, people, web pages, computers, etc. Motivation The network models so far neglect

More information

A new method for community detection in social networks based on message distribution

A new method for community detection in social networks based on message distribution 298 A new method for community detection in social networks based on message distribution Seyed Saeid Hoseini 1*, Seyed Hamid Abbasi 2 1 Student, Department of Computer Engineering, Islamic Azad University,

More information

Community Mining in Signed Networks: A Multiobjective Approach

Community Mining in Signed Networks: A Multiobjective Approach Community Mining in Signed Networks: A Multiobjective Approach Alessia Amelio National Research Council of Italy (CNR) Inst. for High Perf. Computing and Networking (ICAR) Via Pietro Bucci, 41C 87036 Rende

More information

Fast Parallel Algorithm For Unfolding Of Communities In Large Graphs

Fast Parallel Algorithm For Unfolding Of Communities In Large Graphs Fast Parallel Algorithm For Unfolding Of Communities In Large Graphs Charith Wickramaarachchi, Marc Frincu, Patrick Small and Viktor K. Prasanna Department of Computer Science Department of Electrical

More information

A Fast Algorithm to Find Overlapping Communities in Networks

A Fast Algorithm to Find Overlapping Communities in Networks A Fast Algorithm to Find Overlapping Communities in Networks Steve Gregory Department of Computer Science University of Bristol, BS 1UB, England steve@cs.bris.ac.uk Abstract. Many networks possess a community

More information

Approximation of the Maximal α Consensus Local Community detection problem in Complex Networks

Approximation of the Maximal α Consensus Local Community detection problem in Complex Networks Approximation of the Maximal α Consensus Local Community detection problem in Complex Networks Patricia Conde-Céspedes Université Paris 13, L2TI (EA 343), F-9343, Villetaneuse, France. patricia.conde-cespedes@univ-paris13.fr

More information

LICOD: Leaders Identification for Community Detection in Complex Networks

LICOD: Leaders Identification for Community Detection in Complex Networks 2011 IEEE International Conference on Privacy, Security, Risk, and Trust, and IEEE International Conference on Social Computing LICOD: Leaders Identification for Community Detection in Complex Networks

More information

An Exploratory Journey Into Network Analysis A Gentle Introduction to Network Science and Graph Visualization

An Exploratory Journey Into Network Analysis A Gentle Introduction to Network Science and Graph Visualization An Exploratory Journey Into Network Analysis A Gentle Introduction to Network Science and Graph Visualization Pedro Ribeiro (DCC/FCUP & CRACS/INESC-TEC) Part 1 Motivation and emergence of Network Science

More information

Link Prediction for Social Network

Link Prediction for Social Network Link Prediction for Social Network Ning Lin Computer Science and Engineering University of California, San Diego Email: nil016@eng.ucsd.edu Abstract Friendship recommendation has become an important issue

More information

CEIL: A Scalable, Resolution Limit Free Approach for Detecting Communities in Large Networks

CEIL: A Scalable, Resolution Limit Free Approach for Detecting Communities in Large Networks CEIL: A Scalable, Resolution Limit Free Approach for Detecting Communities in Large etworks Vishnu Sankar M IIT Madras Chennai, India vishnusankar151gmail.com Balaraman Ravindran IIT Madras Chennai, India

More information

[Gidhane* et al., 5(7): July, 2016] ISSN: IC Value: 3.00 Impact Factor: 4.116

[Gidhane* et al., 5(7): July, 2016] ISSN: IC Value: 3.00 Impact Factor: 4.116 IJESRT INTERNATIONAL JOURNAL OF ENGINEERING SCIENCES & RESEARCH TECHNOLOGY AN EFFICIENT APPROACH FOR TEXT MINING USING SIDE INFORMATION Kiran V. Gaidhane*, Prof. L. H. Patil, Prof. C. U. Chouhan DOI: 10.5281/zenodo.58632

More information

A. Papadopoulos, G. Pallis, M. D. Dikaiakos. Identifying Clusters with Attribute Homogeneity and Similar Connectivity in Information Networks

A. Papadopoulos, G. Pallis, M. D. Dikaiakos. Identifying Clusters with Attribute Homogeneity and Similar Connectivity in Information Networks A. Papadopoulos, G. Pallis, M. D. Dikaiakos Identifying Clusters with Attribute Homogeneity and Similar Connectivity in Information Networks IEEE/WIC/ACM International Conference on Web Intelligence Nov.

More information

Complex networks: A mixture of power-law and Weibull distributions

Complex networks: A mixture of power-law and Weibull distributions Complex networks: A mixture of power-law and Weibull distributions Ke Xu, Liandong Liu, Xiao Liang State Key Laboratory of Software Development Environment Beihang University, Beijing 100191, China Abstract:

More information