Links In Social Networks Research Articles

An approach for predicting missing links in social network using node attribute and path information

An approach for predicting missing links in social network using node attribute and path information

Common Growth Patterns for Regional Social Networks: A Point Process Approach

In this paper, we study macroscopic growth dynamics of social network link formation. Rather than focusing on one particular dataset, we find invariant behavior in regional social networks that are geographically concentrated. Empirical findings suggest that the startup phase of a regional network can be modeled by a self-exciting point process. After the startup phase ends, the growth of the links can be modeled by a non-homogeneous Poisson process with a constant rate across the day but varying rates from day to day, plus a nightly inactive period when local users are expected to be asleep. Conclusions are drawn based on analyzing four different datasets, three of which are regional and a non-regional one is included for contrast.

New Insights and Methods For Predicting Face-To-Face Contacts

The prediction of new links in social networks is a challeng- ing task. In this paper, we focus on predicting links in net- works of face-to-face spatial proximity by using information from online social networks, such as co-authorship networks in DBLP, and a number of node level attributes. First, we analyze influence factors for the link prediction task. Then, we propose a novel method that combines information from different networks and node level attributes for the pre- diction task: We introduce an unsupervised link prediction method based on rooted random walks, and show that it out- performs state-of-the-art unsupervised link prediction meth- ods. We present an evaluation using three real-world datasets. Furthermore, we discuss the impact of our results and of the insights we glean in the field of link prediction and human contact behavior.

A Social Network Link Prediction Method Based on Stacked Generalization

Abstract Traditional link prediction methods of social network are vulnerable to the influence of network structure and have poor generalization, and only on a small number of networks and evaluation indicators. To improve the stability and accuracy of link prediction, this paper assembles 15 similarity indexes, introduces the idea of stacking into the link prediction of complex networks, and presents a link prediction method (Logistic-regression LightGBM Stacking Link Prediction, LLSLP). Firstly, social network link prediction is regarded as a binary classification problem. Secondly, the hyper parameters of the basic model are determined by using cross-validation and grid searching; thirdly, Logistic-regression and LightGBM are integrated by stacked generalization; Finally, take 10 different networks as practical examples. The feasibility and effectiveness of the proposed method are verified by comparing 7 evaluation indicators. The experimental results show that: the proposed method is not only more than 98.71% higher than the traditional CN (Common Neighbor) and other models are 10.52% higher on average. In addition, compared with the traditional 15 link prediction algorithms, $F1- score$ value and $MCC$ (Matthews Correlation Coefficient) value is increased by 3.2% ~ 9.7% and 5.9% ~ 14% respectively. The proposed method has good accuracy and generalization. It can also be applied to recommendation system.

Learning-based link prediction analysis for Facebook100 network

In social network science, Facebook is one of the most interesting and widely used social networks and media platforms. Its data has significantly contributed to the evolution of social network research and link prediction techniques, which are important tools in link mining and analysis. This paper gives the first comprehensive analysis of link prediction on the Facebook100 network. We stu- dy performance and evaluate multiple machine learning algorithms on different feature sets. To derive the features, we use network embeddings and topology-based techniques such as node2vec and vectors of similarity metrics. In addition, we also employ node- -based features, which are available for the Facebook100 network, though rarely found in other datasets. The adopted approaches are discussed and results are clearly presented. Lastly, we compare and review the applied models, where overall performance and classification rates are presented.

Learning-based link prediction analysis for Facebook100 network

In social network science, Facebook is one of the most interesting and widely used social networks and media platforms. Its data has significantly contributed to the evolution of social network research and link prediction techniques, which are important tools in link mining and analysis. This paper gives the first comprehensive analysis of link prediction on the Facebook100 network. We stu- dy performance and evaluate multiple machine learning algorithms on different feature sets. To derive the features, we use network embeddings and topology-based techniques such as node2vec and vectors of similarity metrics. In addition, we also employ node- -based features, which are available for the Facebook100 network, though rarely found in other datasets. The adopted approaches are discussed and results are clearly presented. Lastly, we compare and review the applied models, where overall performance and classification rates are presented.

SOIDP: Predicting Interlayer Links in Multiplex Networks

Many link prediction algorithms regarding single-layer social networks have been proposed, and however, how to predict interlayer links in multiplex social networks is still in the initial stage. In fact, the prediction of interlayer links in multiplex networks is of great significance, which is closely related to network security, product recommendation, social network mining, and so forth. Given that many social networks are sparse and the number of the first-order common matched neighbors (CMNs) is very few, it is not sufficient to implement link prediction only based on the first-order CMNs. Moreover, many social networks have scale-free property, leading to the roles of CMNs in link prediction which are significantly different. In doing so, we propose a second-order iterative degree penalty (SOIDP) algorithm to predict interlayer links in multiplex networks, in which the information of the first- and second-order CMNs is integrally considered, as well as a degree penalty mechanism is introduced to give larger weight to the CMNs with fewer connections. In particular, to solve the problem of cumulative error in the iterative process, we demonstrate that the interlayer links can be predicted by directly calculating the matching degree matrix without iteration. Experiments on real-world networks show that the performance of SOIDP algorithm in predicting interlayer links is always better than the baseline algorithms, and the accuracy is increased 10% at least. For synthetic networks, the improvement is also very surprising when networks are rather sparse.

A multidimensional network link prediction algorithm and its application for predicting social relationships

In the "We the Media" era, the rules for forming social users' following relationships are complex. Links generated between two social user nodes are influenced by not only the structural information of their social network nodes but also the users’ occupational environments, interests in opinions, topics, social psychology, etc. In the existing studies of link prediction in complex networks, predicting the possibility of link generation between two nodes that have not yet generated edges in a complex network is calculated mainly from the known network nodes and structural information. Such studies, in which the main predictors are the structural similarities among social nodes or user location nodes, cannot fully explore and utilize the social network node users’ public opinion characteristics. To quantitatively identify the influence of different dimensions of public opinion factors on predicting links between social user nodes, we present a study on the prediction of social network links in "We the Media" networks. Starting with the characteristics of the elements found in public opinions on “We the Media” networks, in which public opinions are multidimensional and multilayered and possess multiple attributes, we built a multidimensional network model oriented towards the topology of public opinions on “We the Media” networks. Combined with an analysis of the driving factors in the formation of user-node relationships in social networks, we designed a prediction algorithm that works on multidimensional network links. Furthermore, we conducted an empirical analysis of social relationship prediction, whose effectiveness has also been compared with baseline methods such as the Common-Neighbourhood-Driven model, the Jaccard index, and the SimRank method. We chose the area under the curve (AUC) as the indicator of link prediction and evaluation using “We the Media” public opinion data from Weibo.com. The research findings of this paper can be summarized as follows: (1) The effectiveness of the multidimensional network link prediction algorithm is significantly higher than those of the baseline methods. (2) The prediction algorithm presented in this paper works on multidimensional network links and can evaluate the effects of different dimensions of public opinion factors on the prediction of user-node links in social networks. (3) The element of occupational environment improves the accuracy much more than the element of user interest in opinions and topics when predicting user-nodes’ links, while the element of social psychology reduces the accuracy.

Context Aware Sentiment Link Prediction in Heterogeneous Social Network

People often express opinions towards others in a social network, causing sentiment links to form among users. To develop effective methods for discovering implicit sentiment links among users, the extraction and exploitation of structural semantic information from heterogeneous social networks are of great importance. We propose a novel heterogeneous social network embedding-based approach for sentiment link prediction that takes both global structural information with multi-dimensional relations and heterogeneous context information into consideration to leverage rich and intrinsic association information. Specifically, the attributed heterogeneous social network and Sentic LSTM-based sentiment link network are employed to incorporate various explicit context knowledge and implicit multi-dimensional user interaction association knowledge into representation learning and sentiment link prediction. The experimental results on a real-world dataset show that the proposed approach has advantages over the state-of-the-art baselines. The results show the effectiveness of incorporating social relations and profile context information into sentiment link prediction, especially in cold-start scenarios. The learned embedding representation that incorporates both structural information with multi-dimensional relations and context information from heterogeneous social networks can improve sentiment link prediction performance. The proposed approach is effective and feasible for detecting unobserved sentiment links from online social networks and outperforms the state-of-the-art baselines in sentiment link prediction tasks.

Discovering Hidden Topical Hubs and Authorities Across Multiple Online Social Networks

Finding influential users in online social networks (OSNs) is an important problem with many possible useful applications. Many methods have been proposed to identify influential users in OSNs. PageRank and HITs are two well known examples that determine influential users through link analysis. In recent years, new models that consider both content and social network links have been developed. The Hub and Authority Topic (HAT) model is one that extends HITS to identify topic-specific hubs and authorities by jointly learning hubs, authorities, and topical interests from users' relationship and textual content. However, many of the previous works are confined to identifying influential users within a single OSN. These models, when applied to multiple OSNs, could not learn influential users under a common set of topics nor address platform preferences. In this paper, we therefore propose the MPHAT model, an extension of HAT, to jointly model the topic-specific hub users, authority users, their topical interests and platform preferences. We evaluate MPHAT against several existing state-of-the-art methods in three tasks: (i) modeling of topics, (ii) platform choice prediction, and (iii) link recommendation. Based on our extensive experiments in multiple OSNs settings using synthetic datasets and real-world datasets from Twitter and Instagram, we show that MPHAT is comparable to state-of-the-art topic models in learning topics but outperforms the state-of-the-art models in platform prediction and link recommendation tasks. We also empirically demonstrate the ability of MPHAT to determine influential users within and across multiple OSNs.

Learning Influential Cognitive Links in Social Networks by a New Hybrid Model for Opinion Dynamics

A principled approach to modeling sociocognitive networks is fundamental to understanding the network interrelations which in turn can be used in many applications such as human behavior analysis or team performance assessment. More specifically, in the opinion domain, learning the cognitive links and making a proper model for causal relationships between individuals is necessary for both analysis and control purposes. There are several mathematical models for opinion dynamics. However, few of them have been tested to be consistent with real-world data. In this article, a new hybrid model for opinion dynamics is proposed and is put to test with subjective experiments. It is imperative that a realistic model considers two cognitive facts: 1) a person tends to stick to his/her previously shaped opinion and 2) the opinion of a person is affected by others (either reinforced in a positive way or undermined negatively). This article presents a novel mathematical formulation of the proposed opinion dynamics model and proves its stability too. The new model is also extended to support multiple dimensions. In the multidimensional approach, opinions about two or more subjects are considered separately. The rationale behind this is to describe the evolution of agents’ opinions on several topics. To study how the model performs in reality, some real-world experiments are conducted and the influence matrix is learned in each case. In addition, a method is introduced to extract the parameters of the model from the experimental data. It is shown that the new model predictions, after it is trained, chase the real behaviors of participants very well and result in less error compared with the previous models.

An edge creation history retrieval based method to predict links in social networks

Link prediction is a graph mining task that aims to foretell whether pairs of non-linked nodes will connect in the future. It has many useful applications in social networks such as friend recommendation, identification of future collaborations between authors in co-authorship networks, discovery of hidden groups of terrorists and criminals, among others. In general, the state-of-the-art link prediction methods consider topological data extracted from the current state (i.e., the most recent and available snapshot) of a network. They do not take into account information that describes how the network’s topology was at the moments when the existing edges were created. Hence, those methods take the chance to disregard information about the circumstances that may have influenced the appearance of old edges, and that could be useful to predict the creation of new ones. Thus, this study raises and evaluates the hypothesis that recovering such data may contribute to improving link prediction. This hypothesis is justified since those data enrich the description of the application’s context with examples that represent exactly the kind of event to be foreseen: the creation of new connections. To this end, this paper proposes a new link prediction method that is based on edge creation history retrieval. Results from experiments with twenty scenarios of four real co-authorship social networks presented statistical evidence that indicates the effectiveness of the proposed method and confirms the raised hypothesis.

Monetary incentives and peer referral in promoting digital network-based secondary distribution of HIV self-testing among men who have sex with men in China: study protocol for a three-arm randomized controlled trial

BackgroundHuman immunodeficiency virus (HIV) testing is a crucial strategy for HIV prevention. HIV testing rates remain low among men who have sex with men (MSM) in China. Digital network-based secondary distribution is considered as an effective model to enhance HIV self-testing (HIVST) among key populations. Digital platforms provide opportunities for testers to apply for HIVST kits by themselves, and secondary distribution allows them to apply for multiple kits to deliver to their sexual partners or members within their social network. We describe a three-arm randomized controlled trial to examine the effect of monetary incentives and peer referral in promoting digital network-based secondary distribution of HIVST among MSM in China.MethodsThree hundred MSM in China will be enrolled through a digital platform for data collection. The eligibility criteria include being biological male, 18 years of age or over, ever having had sex with another man, being able to apply for kits via the online platform, and being willing to provide personal telephone number for follow-up. Eligible participants will be randomly allocated into one of the three arms: standard secondary distribution arm, secondary distribution with monetary incentives arm, and secondary distribution with monetary incentives plus peer referral arm. Participants (defined as “index”) will distribute actual HIV self-test kits to members within their social network (defined as “alter”) or share referral links to encourage alters to apply HIV self-test kits by themselves. All index participants will be requested to complete a baseline survey and a 3-month follow-up survey. Both indexes and alters will complete a survey upon returning the results by taking a photo of the used kits with the unique identification number.DiscussionHIV testing rates remain suboptimal among MSM in China. Innovative interventions are needed to further expand the uptake of HIV testing among key populations. The findings of the trial can provide scientific evidence and experience on promoting secondary distribution of HIVST to reach key populations who have not yet been covered by existing testing services.Trial registrationThe study was registered in the Chinese Clinical Trial Registry (ChiCTR1900025433) on 26, August 2019, http://www.chictr.org.cn/showproj.aspx?proj=42001. Prospectively registered.

Personalized Prediction of Trust Links in Social Networks (Student Abstract)

In this paper we show how integrating both domain specific and generic trust indicators into a prediction of trust links between users in social networks can improve upon methods for recommending content to users and how clustering of users to deliver personalized solutions offers even greater advantages.

Information and the Acquisition of Social Network Connections

How do information interventions affect individual efforts to expand social networks? We study a randomized controlled trial of a program providing information on settling in the U.S. for new immigrants from the Philippines. Improved information leads new immigrants to acquire fewer new social network connections. Treated immigrants make 16-28 percent fewer new friends and acquaintances and are 65 percent less likely to receive support from organizations of fellow immigrants. The treatment has no effect on employment, wellbeing, or other outcomes. Consistent with a simple model, the treatment reduces social network links more in places likely to have lower costs of acquiring network links (those with more prior fellow immigrants). Information and social network links appear to be substitutes in this context: better-informed immigrants invest less in expanding their social networks upon arrival. Our results suggest that endogenous reductions in acquisition of social network connections can reduce the effectiveness of information interventions. Institutional subscribers to the NBER working paper series, and residents of developing countries may download this paper without additional charge at www.nber.org.

Sociality and tattoo skin disease among bottlenose dolphins in Shark Bay, Australia

AbstractSocial behavior is an important driver of infection dynamics, though identifying the social interactions that foster infectious disease transmission is challenging. Here we examine how social behavior impacts disease transmission in Indo-Pacific bottlenose dolphins (Tursiops aduncus) using an easily identifiable skin disease and social network data. We analyzed tattoo skin disease (TSD) lesions based on photographs collected as part of a 34-year longitudinal study in relation to the sociality of T. aduncus using three metrics (degree, time spent socializing, and time in groups) and network structure, using the k-test. We show that calves with TSD in the second year of life associated more with TSD-positive individuals in the first year of life compared with calves that did not have TSD. Additionally, the network k-test showed that the social network links are epidemiologically relevant for transmission. However, degree, time spent in groups, and time spent socializing were not significantly different between infected and uninfected groups. Our findings indicate that association with infected individuals is predictive of an individual’s risk for TSD and that the social association network can serve as a proxy for studying the epidemiology of skin diseases in bottlenose dolphins.

A Correlative Scrutiny for Improving the Career Guidance Links in Social Network

Social Network analysis techniques have shown the ability to meet educators and influence career development guidance. Career education mentoring plays an important role in the career supporting which are the interest, the strength, and the aspirations of the students. In this paper, we proposed a career development framework enhances the node influence propagation and effective interaction between nodes is taken as a strong link, from the node influence propagation we divide it into two categories such as: (1) career predictions to persuade prospective graduates to pursue the desired career path, with career prospects considered by them as a learning opportunity. (2) Social network analysis and persuasive techniques are used to motivate within a social networking framework where there is a tendency to adopt desired professional behaviors. The process begins with the discovery of behavioral features to create a cognitive profile and to identify individual disabilities. We compare a clustering algorithm that predicts the accuracy values and pattern of creations to a social network for achieving collaborative cognition.

Cultural communication in double-layer coupling social network based on association rules in big data

In the big data set around the world, cultural communication in a single-layer social network cannot handle data in a two-tier social network. Combined with the characteristics of cultural communication, a two-layer coupled social network model for predicting cultural information dissemination is proposed. According to the law of big data set in the process of cultural communication, the ethical review and theoretical construction of cultural network communication was carried out. Combining the online two-layer coupling network and the CRF word segmentation algorithm, the known link relationship is obtained, and the feature attributes of the network are extracted. This paper mainly completed the construction of online social network link prediction. Starting from the topological structure of two-layer coupled social network, based on the association rules to analyze the data generated by information dissemination between two-layer coupled network nodes, a two-layer coupled network information propagation law model is proposed. The prediction and construction of the cultural information communication link in the online social network is completed, the process of data opening and sharing is accelerated, and the privacy and copyright issues in the process of cultural communication are solved. The influence of immune node and node self-healing time on the cultural information dissemination process of two-layer coupled social network is discussed. By comparing the information dissemination in social networks and the information dissemination in two-layer coupled social networks, the control of certain lyric cultures can be effectively prevented. The experimental results show that it has reference value.

Acquisition method of users’ browsing behavior preference based on the fusion of social network link and theme model

Acquisition method of users’ browsing behavior preference based on the fusion of social network link and theme model

Using network motifs to characterize temporal network evolution leading to diffusion inhibition

Network motifs are patterns of over-represented node interactions in a network which have been previously used as building blocks to understand various aspects of the social networks. In this paper, we use motif patterns to characterize the information diffusion process in social networks. We study the lifecycle of information cascades to understand what leads to saturation of growth in terms of cascade reshares, thereby resulting in expiration, an event we call “diffusion inhibition”. In an attempt to understand what causes inhibition, we use motifs to dissect the network obtained from information cascades coupled with traces of historical diffusion or social network links. Our main results follow from experiments on a dataset of cascades from the Weibo platform and the Flixster movie ratings. We observe the temporal counts of 5-node undirected motifs from the cascade temporal networks leading to the inhibition stage. Empirical evidences from the analysis lead us to conclude the following about stages preceding inhibition: (1) individuals tend to adopt information more from users they have known in the past through social networks or previous interactions thereby creating patterns containing triads more frequently than acyclic patterns with linear chains and (2) users need multiple exposures or rounds of social reinforcement for them to adopt an information and as a result information starts spreading slowly thereby leading to the death of the cascade. Following these observations, we use motif-based features to predict the edge cardinality of the network exhibited at the time of inhibition. We test features of motif patterns using regression models for both individual patterns and their combination and we find that motifs as features are better predictors of the future network organization than individual node centralities.