Community Detection in Semantic Networks: A Multi-View Approach

Community detection is an effective approach to unveil relationships among individuals in online social networks. In the literature, quite a few algorithms have been proposed to conduct community detection by exploiting the topology of social networks and the attributes of social actors. In practice, community detection is usually conducted by third parties, such as advertisement companies and hospitals, with access to social networks for different purposes, which can easily lead to a privacy breach. In this paper, we investigate community detection in social networks aiming to protect the privacy of both the network topology and the users' attributes. We show that with additional prior knowledge, community detection can be performed by querying the information of only a fraction of instead of the entire population. In particular, we first propose a new scheme called differentially private community detection (DPCD). DPCD detects communities in social networks via a probabilistic generative model, which can be decomposed into subproblems solved by individual users. The private social relationships and attributes of each user are protected by objective perturbation with differential privacy guarantees. Then, we propose a parsimonious node affiliation recovery (NAR) algorithm, which is also differentially private, to unveil the community affiliation information of the whole population based on that of the limited number of queried individuals by solving a sparse optimization problem. Through both theoretical analysis and experimental validation using synthetic and real-world social networks, we demonstrate that the proposed DPCD scheme detects social communities under the modest privacy budget. In addition, we show the effectiveness of NAR to perform community detection by querying a limited number of individuals in social networks.

Advances in Web 2.0 technologies have led to unstructured information overload in the complex and multidimensional datasets that originate in social networks. This overload can diminish the quality of web-related services such as recommender systems in the social web and can overwhelm users with irrelevant information. Such overload indicates the need to design and develop efficient and accurate information management and retrieval systems in social networks and anticipate recommendations in the semantic context of user interest. Community detection in social networks can help identify higher-order structures that unveil insight into networks and their functional organization and reduce irrelevant information received by the user. In this study, the application of community detection in online social networks is investigated within the framework of topic discovery-based user link identification and is consequently used to uncover implicit user communities (ad hoc communities). In the proposed approach, we use a graph-based information extraction technique that provides for a personalized information retrieval (recommender) system. We hypothesize that the ad hoc communities of users sharing similar interests embedded in a folksonomy-based social network can be identified by overlapping tag clusters in the tag concept hierarchy. Our methodology incorporates the novel information extraction techniques of topic modeling for topic extraction (feature extraction), user profile modeling for user profile extraction, and community extraction from the social graph, modeled in a framework to derive relevant ad hoc user communities of social interest from folksonomy data. Our experimental results demonstrate an accuracy of 70–98 % in community detection using data obtained from CiteULike®.

With the rapid increase in popularity of online social networks, community detection in these networks has become a key aspect of research field. Overlapping community detection is an important NP-hard problem of social network analysis. Modularity-based community detection is one of the most widely used approaches for social network analysis. However, modularity-based community detection technique may fail to resolve small-size communities. Hence, we propose a novel two-step approach for overlapping community detection in social networks. In the first step, modularity density-based hybrid meta-heuristics approach is used to find the disjoint communities and the quality of these disjoint communities can be verified using Silhouette coefficient. In the second step, the quality disjoint communities with low computation cost are used to detect overlapping nodes based on Min-Max Ratio of minimum(indegree, outdegree) to the maximum(indegree, outdegree) values of nodes. We tested the proposed algorithm based on 10 standard community quality metrics along with Silhouette score using seven standard datasets. Experimental results demonstrate that the proposed approach outperforms the current state-of-the-art works in terms of quality and scalability.

Parallel and distributed paradigms for community detection in social networks: A methodological review

In a rapidly changing environment, a shift toward decentralized structure for organizations seems inevitable. Semantic Web technologies combined with social network analysis make the transition of a centralized organization to a decentralized one much easier. By increasing controllability and manageability of a decentralized structure, these tools can improve functionality and performance. A framework for creation and maintenance of a semantic social network is introduced and two real world organizations have been analyzed. After selecting one organization suitable for decentralization, network datasets were generated from its structure. Generated datasets have been used as the input of the framework to create a semantic social network for the corresponding organization. Social network analysis was then performed on both semantic and non semantic social networks. Gain of performance was observed in many areas such as decision making, flexibility, reliability and throughput. Semantic social network also enables other functionalities along ease of decentralization such as gain of knowledge about dynamic structure of the organization. These functionalities are also discussed.

Semantic social network (SSN) is an extension of the current social network wherein meaningful data is added with each piece of information, known as metadata. This metadata is processed by machines to make decisions based on intelligent algorithms. SSN gives a virtual social circle where individuals can share information, ideas, news and stay connected with their friends and family. The semantic social information can be used to measure various behavioral traits of SSN individuals using metrics. There are several metrics developed to calculate the individual’s traits of the semantic social network. However, few metrics may produce wrong results in the absence of time consideration during their calculations. In this article, we have proposed a novel technique to improve the accuracy of activity factor metric calculation and another metric to calculate peak active time for an activity. The extracted results from our novel SSN metrics can help authorities to make better decisions in providing offers, rewards, suggestions, and badges for the SSN members as per their needs and interests.

The semantic social network is a kind of network that contains enormous nodes and complex semantic information, and the traditional community detection algorithms could not give the ideal cogent communities instead. To solve the issue of detecting semantic social network, we present a clustering community detection algorithm based on the PSO‐LDA model. As the semantic model is LDA model, we use the Gibbs sampling method that can make quantitative parameters map from semantic information to semantic space. Then, we present a PSO strategy with the semantic relation to solve the overlapping community detection. Finally, we establish semantic modularity (SimQ) for evaluating the detected semantic communities. The validity and feasibility of the PSO‐LDA model and the semantic modularity are verified by experimental analysis.

A cascade information diffusion based label propagation algorithm for community detection in dynamic social networks

Community detection in social networks is a promising research area. However, network exploration with multiple types of relationships remains an underexplored yet crucial domain. To address the challenge of community detection in multiplex networks, we propose SFCSA, a smart flattening-based Cuckoo Search Algorithm, designed to address the complexities of such networks effectively. SFCSA unfolds in three integral steps. Firstly, we employ DeepWalk and node2vec algorithms to extract node embeddings, which are merged to construct the multiplex network node embeddings, minimizing information loss. Secondly, a flattened network is built by merging the network layers and adopting the Pearson correlation coefficient as a weight to capture node similarity. Thirdly, we employ a community detection approach that unveils the community structure through a cuckoo search algorithm applied to the multiplex node embeddings to extract the best set of cluster centres by maximizing the modularity function. Experimental evaluations across synthetic and real-world multiplex networks attest to the efficiency and effectiveness of our approach, outperforming state-of-the-art algorithms.

A spreading activation-based label propagation algorithm for overlapping community detection in dynamic social networks

A trending issue in the network system that aids in learning and understanding the overall network structure is the community detection in the social network. Actually, they are the dividing wall which divides the node of the network into several subgroups. While dividing, the nodes within the subgroups will get connected densely but, their connections will be sparser between the subgroups. The ultimate objective of the community detection method is to divide the network into dense regions of the graph. But, in general, those regions will correlate with close related entities which can be then said that it is belonging to a community. It is defined based on the principle that the pair of nodes will be connected only if they belong to the same community and if they don’t share the communities, they are less likely to be connected. The vital problems across various research fields like the detection of minute and scattered communities have been necessitated with the ever growing variety of the social networks. The problem of community detection over the time has been recognized with the literature survey and the proposal methodology of set theorem to find the communities detection where the group belongs to activities. In addition to this, several basic concepts are stated in an exhaustive way where the research fields arise from social networks.

A synthesis of semantic social network and attraction theory for innovating community-based e-service

We demonstrate SSNetViz that is developed for integrating, visualizing and querying heterogeneous semantic social networks obtained from multiple information sources. A semantic social network refers to a social network graph with multi-typed nodes and links. We demonstrate various innovative features of SSNetViz with social networks from three information sources covering a similar set of entities and relationships in terrorism domain.

Revealing the community structure in social networks witnessed a determined effort. In this respect, a different category of social network can be handled, such as, dynamic social networks, social networks with node attributes, etc. In this article, we introduce a new method to solve this thriving issue in the social network with node attributes. This latter can be represented by a bipartite graph, which consists of a two sets of nodes and edges connecting these nodes. The tendency of people with similar node attributes leads to the hidden information of clusters or communities. A wealthy number of community-detection algorithms have been proposed for bipartite graphs and applied to several domains in the literature. To palliate some of the highlighted shortcomings, we introduce a new approach, called Fast-Bi Community Detection (FBCD), that aims to an efficient community detection in social networks. The main idea of this approach is to explore the set of maximum matching in the bipartite graph in order to reduce the complexity of our algorithm. The carried out experiments show the high quality of the obtained communities versus those by the pioneering ones of the literature.

Community detection or formation of clustering is a well defined problem of pattern recognition where interaction pattern of the members is measured. The detection of well defined communities are based on the fact that interaction within the community will be maximum whereas the interaction with the other communities will be minimum. Though several numbers of good community detection algorithms are present for well defined clustering, time complexity of these algorithm is quiet high and thus cannot be treated as the good measures of detection of community where number of nodes in the network is too large. In this paper, we are proposing a novel algorithm of community detection based on hierarchical ego based algorithm. In a network, ego is defined as the highest node degree centrality node and this node is treated as the cluster center of the community in our algorithm. The nodes closely connected with the ego node formed the community and from the remaining network the same process is iterated for community detection. For the result, dataset is extracted using Node-XL from a Twitter account, R based Hadoop network is used for the analysis of the network. For the visualization of the network I-graph is used.