Social Community Detection Research Articles

Network alignment in multiplex social networks using the information diffusion dynamics

Modern social networking applications (SNAs) typically rely on independent data management systems, leading to fragmented user identities and the creation of data silos. This fragmentation impedes the development of unified user profiles and limits the effectiveness of cross-platform behavioural analysis and personalized recommendations. As the demand for integrated services grows, the need for a unified user identity across platforms becomes increasingly critical. However, existing identity integration methods face significant challenges, including data isolation, privacy risks, and a lack of universal standards. To address these issues, we propose a framework that utilizes node dynamics time-series data for network alignment in multiplex social networks. Our approach employs the UIU diffusion model to simulate information diffusion dynamics across multiple platforms and uses the Expectation-Maximization (EM) algorithm for network alignment. Crucially, our method relies solely on publicly available user information from different platforms, avoiding the need for access to private user data, thereby enhancing security. Experimental results demonstrate the model’s efficacy, achieving F1 scores of 100% for interlayer links and over 90% for intralayer links on real-world datasets. These findings highlight the model’s potential for applications in social influence analysis, community detection, and recommendation systems.

Detailed-level modelling of influence spreading on complex networks

The progress in high-performance computing makes it increasingly possible to build detailed models to investigate spreading processes on complex networks. However, current studies have been lacking detailed computational methods to describe spreading processes in large complex networks. To fill this gap we present a new modelling approach for analysing influence spreading via individual nodes and links on various network structures. The proposed influence-spreading model uses a probability matrix to capture the spreading probability from one node to another in the network. This approach enables analysing network characteristics in a number of applications and spreading processes using metrics that are consistent with the quantities used to model the network structures. In addition, this study combines sub-models and offers a comprehensive look at different applications and metrics previously discussed in cases of social networks, community detection, and epidemic spreading. Here, we also note that the centrality measures based on the probability matrix are used to identify the most significant nodes in the network. Furthermore, the model can be expanded to include additional properties, such as introducing individual breakthrough probabilities for the nodes and specific temporal distributions for the links.

Social media content classification and community detection using deep learning and graph analytics

Social cybermedia has greatly changed the world’s perspective on information sharing and propagation. These platforms build virtual user communities in the form of followings or followers that can spread positive or negative content. These virtual communities play a vital role in the spread of hate content, which may create a severe law-and-order situation and social unrest in any country. Hate content can include offensive, anti-state, anti-religion, sexist, and racist posts. Classifying such content and identifying influential individuals who participate in these communities are challenging tasks for law enforcement agencies. This study proposes novel deep learning and graph-based approaches to identifying hate content, followed by approaches to detecting communities and exploring social media to detect hate content. Twitter is used as a case study, and tweets are extracted and annotated by linguistic experts to develop a dataset for experimentation and validation. The proposed customized LSTM-GRU model is used to classify hate content into six categories. The developed model offers an accuracy of 98.14% on the obtained dataset. The Girvan–Newman algorithm is employed for Twitter community detection and successfully identifies the most influential individuals. Moreover, the proposed approach precisely detects intraclass communities and highly influential persons. The developed model effectively identifies hate tweets and communities and can be used to monitor social media to identify any potential threat of unrest.

Community Detection in Social Networks Considering Social Behaviors

The study of community detection in networks has drawn great attention in recent years. To find communities and to understand community semantics, both network topology and network content are utilized. Unfortunately, none of them can explain the driving factors of generating community structure with semantics, which is significant for understanding the mechanisms of community generation. Our observations on a large number of networks show that specific user social behaviors are underlying factors for the generation of community structure. We exploit four types of social behaviors that widely exist in networks, i.e., reciprocity of interactions, posting preference, multitopic preference, and temporal variation of topics. We investigate their impacts on the formation process of links and content in networks, during which communities with topics form. Our analysis shows that they are highly related to community structure. Consequently, a generative community detection model SBCD (social behavior-based community detection) is proposed by combining network topology and content, in which the above social behaviors play a core role. The model is evaluated on two real datasets. The experimental results show that SBCD outperforms state-of-the-art baselines. Finally, a case study illustrates several significant observations with respect to the proposed social behaviors.

Multi-source propagation aware network clustering☆

Network cluster analysis is of great importance as it is closely related to diverse applications, such as social community detection, biological module identification, and document segmentation. Aiming to effectively uncover clusters in the network data, a number of computational approaches, which utilize network topology, single vector of vertex features, or both the aforementioned, have been proposed. However, most prevalent approaches are incapable of dealing with those contemporary network data whose vertices are characterized by features collected from multiple sources. To address this challenge, in this paper, we propose a novel framework, dubbed Multi-Source Propagation Aware Network Clustering (MSPANC) for uncovering clusters in network data possessing multiple sources of vertex features. Different from most previous approaches, MSPANC is able to infer the cluster preference for each vertex utilizing both network topology and multi-source vertex features. To improve the practical significance of the discovered clusters, the learning of cluster membership is also involved into the modeling of the maximization of intra-cluster propagation regarding multi-source features. We propose a unified objective function for MSPANC to perform the clustering task and derive an alternative manner of learning algorithm for model optimization. Besides, we theoretically prove the convergence of the algorithm for optimizing MSPANC. The proposed model has been tested on five real-world datasets, including social, biological and document networks, and has been compared with several competitive baselines. The remarkable experimental results validate the effectiveness of MSPANC.

SoLoMo cities: socio-spatial city formation detection and evolution tracking approach

The tremendous growth of telecommunication devices coupled with the huge number of social media users has revealed a new kind of development that turning our cities into information-rich smart platforms. We analyse the role of LBSN check-ins using social community detection methods to extract city structured communities, which we call 'SoLoMo cities', using a modified version of Louvain algorithm, then we track these communities' evolution patterns through a pairwise consecutive matching process to detect behavioural events changing city's communities. The findings of the experiments on the Brightkite dataset can be summarised as follows: online users' check-in activities reveal a set of well-formed physical land spaces of city's communities, the concentration of online social interactions and the formation of those cities are positively correlated with a percentage of 89%. Finally, we were able to track the evolution of the discovered communities through detecting three community behaviour events: survive, grow and shrink.

Identifying Maximal Cliques on Large Scale Network using the Genetic Algorithm

In graph theory, definition of clique is given as sub-graph(complete) where each node is connected to each other . Identifying functional units in complex network, modelling evolution of social network and community detection are some of the applications of maximum clique problem under graph theory. This problems comprises of a NP-Hard problem where all cliques are enumerating in large scale complex network . However, by applying heuristic based optimisation algorithms it may be possible to identify maximal clique in complex network in reasonable amount of time. The problem can be solved in polynomial time whereas, other NP-hard problems like Travelling Salesman Problem(TSP), graph colouring problem, 3-SAT problem etc. could be diminished to maximal clique problem in order to process in polynomial amount of time. Maximal Cliques are not subset of any other cliques. Out of all the maximal cliques, the clique with maximum cardinality or maximum weight is treated as maximum cliques in the network. Detection of maximum clique problem is formulated by combining the optimal problem where the aim is to maximize sum of weights or the cardinality of the sub graph. A number of approaches have been presented in literature to identify cliques in the network. Most of them are computationally expensive in analyzing large scale network. In this paper, an efficient genetic algorithm has been proposed to enumerate all the cliques in large scale network.The effectiveness of the proposed algorithm has been verified by comparing computational complexity with other existing algorithms.

CRANK: A Hybrid Model for User and Content Sentiment Classification Using Social Context and Community Detection

Recent works have shown that sentiment analysis on social media can be improved by fusing text with social context information. Social context is information such as relationships between users and interactions of users with content. Although existing works have already exploited the networked structure of social context by using graphical models or techniques such as label propagation, more advanced techniques from social network analysis remain unexplored. Our hypothesis is that these techniques can help reveal underlying features that could help with the analysis. In this work, we present a sentiment classification model (CRANK) that leverages community partitions to improve both user and content classification. We evaluated this model on existing datasets and compared it to other approaches.

A Temporal User Attribute-Based Algorithm to Detect Communities in Online Social Networks

The world is witnessing the daily emergence of a vast variety of online social networks and community detection problem is a major research area in online social network studies. The existing community detection algorithms are mostly edge-based and are evaluated using the modularity metric benchmarks. However, these algorithms have two inherent limitations. Firstly, they are based on a pure mathematical object which considers the number of connections in each community as the main measures. Consequently, a resolution limit and low accuracy in finding community members in often observed. Whereas, online social networks are dynamic networks and the key players are humans whose main attributes such as lifespan, geo-location, the density of interactions, and user weight, change over time. These attributes tend to influence the formation of user communities in any category of online social network. Secondly, the output structure of existing community detection algorithms is usually provided as a graph and dendrogram. A graph structure, is, however, characterized by a high memory complexity, and subsequently exponential search time complexity. Implementing dendrogram such a complex structure is complicated. To address memory complexity and the accuracy rate of the community detection issues, this paper proposes a new temporal user attribute-based algorithm, namely the recently largest interaction based on the attributes of a typical online social network user. Experimental results show that the proposed algorithm outperforms eight well-known algorithms in this domain.

Contextual Correlation Preserving Multiview Featured Graph Clustering.

Graph clustering, which aims at discovering sets of related vertices in graph-structured data, plays a crucial role in various applications, such as social community detection and biological module discovery. With the huge increase in the volume of data in recent years, graph clustering is used in an increasing number of real-life scenarios. However, the classical and state-of-the-art methods, which consider only single-view features or a single vector concatenating features from different views and neglect the contextual correlation between pairwise features, are insufficient for the task, as features that characterize vertices in a graph are usually from multiple views and the contextual correlation between pairwise features may influence the cluster preference for vertices. To address this challenging problem, we introduce in this paper, a novel graph clustering model, dubbed contextual correlation preserving multiview featured graph clustering (CCPMVFGC) for discovering clusters in graphs with multiview vertex features. Unlike most of the aforementioned approaches, CCPMVFGC is capable of learning a shared latent space from multiview features as the cluster preference for each vertex and making use of this latent space to model the inter-relationship between pairwise vertices. CCPMVFGC uses an effective method to compute the degree of contextual correlation between pairwise vertex features and utilizes view-wise latent space representing the feature-cluster preference to model the computed correlation. Thus, the cluster preference learned by CCPMVFGC is jointly inferred by multiview features, view-wise correlations of pairwise features, and the graph topology. Accordingly, we propose a unified objective function for CCPMVFGC and develop an iterative strategy to solve the formulated optimization problem. We also provide the theoretical analysis of the proposed model, including convergence proof and computational complexity analysis. In our experiments, we extensively compare the proposed CCPMVFGC with both classical and state-of-the-art graph clustering methods on eight standard graph datasets (six multiview and two single-view datasets). The results show that CCPMVFGC achieves competitive performance on all eight datasets, which validates the effectiveness of the proposed model.

Phase transitions in normalized cut of social networks

One of the main goals of network analysis and data science is to identify community structures in a network. Community structure is a typical feature of social networks and community detection is considered to be crucial to understand the structure and function of social networks in cyberspace. The community detection problem of social networks can be viewed as a graph partitioning problem whose objective is to identify the external edges as the edge cut that separates the network as two subnetworks by recursive method. The degree-normalized adjacency matrix is more convenient than traditional Laplacian matrix in calculating eigenvalues and eigenvectors. In this work, based on random model we first prove the existence of an abrupt phase transition for community detection in terms of the degree-normalized adjacency matrix with accurate critical value. In detail, the detectability of community detection has changed from high to low when the critical value of phase transition q approaches p1p2 almost surely, where pi(i=1,2) is the intra-community edge connection probability of subnetworks Ci, respectively. Then, the validity of the theoretical results is verified by numerical experiments.

SoLoMo Cities: Socio-Spatial City Formation Detection and Evolution Tracking Approach

The tremendous growth of telecommunication devices coupled with the huge number of social media users has revealed a new kind of development that turning our cities into information-rich smart platforms. We analyse the role of LBSN check-ins using social community detection methods to extract city structured communities, which we call 'SoLoMo cities', using a modified version of Louvain algorithm, then we track these communities' evolution patterns through a pairwise consecutive matching process to detect behavioural events changing city's communities. The findings of the experiments on the Brightkite dataset can be summarised as follows: online users' check-in activities reveal a set of well-formed physical land spaces of city's communities, the concentration of online social interactions and the formation of those cities are positively correlated with a percentage of 89%. Finally, we were able to track the evolution of the discovered communities through detecting three community behaviour events: survive, grow and shrink.

Social Community Detection Scheme Based on Social-Aware in Mobile Social Networks

Currently many factors can influence community detection in mobile social networks, where node mobility is a key factor to influence the stability of community structure. In this paper, we propose a social community detection scheme for mobile social networks based on social-ware, including social attribute similarity, node interest similarity and node mobility. Compared with other community detection schemes, our proposed scheme can accurately detect the communities based on community attribute and node mobility. The experiments show the numbers of detected communities and members in the maximal size community generated by our scheme are both smaller than those of the GN and NM schemes. Additionally, since the nodes (users) both have higher mobility in mobile social networks, the efficiency of our proposed scheme relatively becomes higher. The experiments show when the values of mobility in the test data sets increase, the running time of our proposed scheme decreases when the number of edges is fixed. For example, the running time of our proposed scheme is about 17s when the maximum value of mobility is set as 0.5 and the number of edges is about 16000, and further the running time is only about 13s when the maximum value of mobility is set as 1. Therefore, our proposed scheme can more accurately and efficiently make community detection to increase the stability of mobile community structure.

Discovering and tracking query oriented active online social groups in dynamic information network

The efficient identification of social groups with common interests is a key consideration for viral marketing in online social networking platforms. Most existing studies in social groups or community detection either focus on the common attributes of the nodes (users) or rely on only the topological links of the social network graph. The temporal evolution of user activities and interests have not been thoroughly studied to identify their effects on the formation of groups. In this paper, we investigate the problem of discovering and tracking time-sensitive activity driven user groups in dynamic social networks for a given input query consisting a set of topics. The users in these groups have the tendency to be temporally similar in terms of their activities on the topics of interest. To this end, we develop two baseline solutions to discover effective social groups. The first solution uses the network structure, whereas the second one uses the topics of common interest. We further propose an index-based method to incrementally track the evolution of groups with a lower computational cost. Our main idea is based on the observation that the degree of user activeness often degrades or upgrades widely over a period of time. The temporal tendency of user activities is modelled as the freshness of recent activities by tracking the social streams with a fading time window. We conduct extensive experiments on three real data sets to demonstrate the effectiveness and efficiency of the proposed methods. We also report some interesting observations on the temporal evolution of the discovered social groups using case studies.

Social community detection and message propagation scheme based on personal willingness in social network

Personal willingness is one of the most important factors influencing the construction of social community and the message propagation in social network. Personal willingness is used to describe the subjective initiative of node (user) to communicate information with outside world. The personal willingness is greater, the corresponding user is more willing to make communication with outside world, then the user is more likely to join the corresponding community. So, personal willingness may reduce the probability of generating large-scale communities so as to improve the accuracy and reliability of community detection and increase the stability of community structure. This paper proposes a social community detection and message propagation scheme based on personal willingness in social network. In the proposed scheme, the social community detection algorithm extracts node attributes and then uses modularity degree, interest degree and personal willingness to sophisticatedly detect social communities; also, the message propagation method is based on the exponential model, which constructs feature vector by edge feature and node feature, willingness vector by personal willingness and community willingness, and related basic relationship by propagation probability and propagation delay. Based on the Weibo, YouTube and Digg data, the experiments show that our proposed scheme can ensure the stability and reliability of social community detection and add the initiative and effectiveness of message propagation among users.

Influence Propagation Model for Clique-Based Community Detection in Social Networks

Social media community detection is a fundamental challenge in social data analytics, in order to understand user relationships and improve social recommendations. Although the problem has been extensively investigated, the majority of research has been based on social networks with static structures. Our findings within large social networks, such as Twitter, show that only a few users have interactions or communications at fixed time intervals. Finding active communities that demonstrate constant interactions between its members comprises a reasonable perspective. Communities examined from this perspective will provide time-variant social relationships, which may greatly improve the applicability of social data analytics. In this paper, we address the problem of temporal interaction-biased community detection using a four-step process. First, we develop a partition approach using an objective function based on clique structure, to enhance the time efficiency of our methodology. Second, we develop an influence propagation model that gives greatest weight to active edges or to inactive edges in close proximity to active edges. Third, we develop expansion-driven algorithms to efficiently find the activity-biased densest community. Finally, we verify the effectiveness of the extended community metric and the efficiency of the algorithms using three real data sets and a case study conducted on Twitter dynamic data set.

Social Network Community Detection for DMA Creation: Criteria Analysis through Multilevel Optimization

Management of large water distribution systems can be improved by dividing their networks into so-called district metered areas (DMAs). However, such divisions must be based on appropriated technical criteria. Considering the importance of deeply understanding the relationship between DMA creation and these criteria, this work proposes a performance analysis of DMA generation that takes into account such indicators as resilience index, demand similarity, pressure uniformity, water age (and thus water quality), solution implantation costs, and electrical consumption. To cope with the complexity of the problem, suitable mathematical techniques are proposed in this paper. We use a social community detection technique to define the sectors, and then a multilevel particle swarm optimization approach is applied to find the optimal placement and operating point of the necessary devices. The results obtained by implementing the methodology in a real water supply network show its validity and the meaningful influence on the final result of, especially, elevation and pipe length.

A social community detection algorithm based on parallel grey label propagation

Community detection is one of the important methods for understanding the mechanism behind the function of social networks. The recently developed label propagation algorithm (LPA) has been gaining increasing attention because of its excellent characteristics, such as a succinct framework, linear time and space complexity, easy parallelization, etc. However, several limitations of the LPA algorithm, including random label initialization and greedy label updating, hinder its application to complex networks. A new parallel LPA is proposed in this study. First, grey relational analysis is integrated into the label updating process, which is based on vertex similarity. Second, parallel propagation steps are comprehensively studied to utilize parallel computation power efficiently. Third, randomness in label updating is significantly reduced via automatic label selection and label weight thresholding. Experiments conducted on artificial and real social networks demonstrate that the proposed algorithm is scalable and exhibits high clustering accuracy.

Fuzzy Clustering in a Complex Network Based on Content Relevance and Link Structures

Many real-world problems can be represented as complex networks with nodes representing different objects and links between nodes representing relationships between objects. As different attributes can be considered as associating with different objects, other than nontrivial link structures, complex networks also contain rich content information, and it can be a big challenge to find interesting clusters in such networks by fully exploiting the knowledge of both content and link information in them. Although some attempts have been made to tackle this clustering problem, few of them have considered the feasibility of identifying clusters in complex networks using a fuzzy-based clustering approach. We believe that, if the degree of membership to a cluster that a node belongs to can be considered, we will be able to better identify clusters in complex networks, as we may be able to identify overlapping clusters. In this paper, we, therefore, propose a fuzzy-based clustering algorithm for this task. The algorithm, which we call Fuzzy Clustering Algorithm for Complex Networks (FCAN), can discover clusters by taking into consideration both link and content information. It does so by first processing the content information by introducing a measure to quantify the relevance of contents between each pair of nodes within the network. It then proceeds to leverage the link information in the clustering process by considering a measure of cluster density. Based on these measures, FCAN identifies fuzzy clusters that are more densely connected and more highly relevant in their contents to optimize the degrees of memberships of each node belonging to different clusters. The performance of FCAN has been evaluated with several synthetic and real datasets involving those of document classification and social community detection. The results show that, in terms of accuracy, computation efficiency, and scalability, FCAN can be a very promising approach.

A Crowdsourcing Assignment Model Based on Mobile Crowd Sensing in the Internet of Things

With the powerful sensing capability of mobile smart devices, users can easily obtained the crowd sensing services with smart devices in the Internet of Things (IoT). However, credible interaction issues between mobile users are still the hard problems in the past. In this paper, we focus on how to assign the crowdsourcing sensing tasks based on the credible interaction between users. First, a novel credible crowdsourcing assignment model is proposed based on social relationship cognition and community detection. Second, the service quality factor (SQF), link reliability factor (LRF), and region heat factor (RHF) are introduced to scientifically evaluate the user crowdsourcing preferences. Then, a crowdsourcing algorithm based on analytic hierarchy process (AHP) theory is proposed. Finally, the simulation experiments prove the correctness, effectiveness, and robustness of our method.