Social Network Datasets Research Articles

Integrating Multiple Linear Regression and Infectious Disease Models for Predicting Information Dissemination in Social Networks

Social network is the mainstream medium of current information dissemination, and it is particularly important to accurately predict its propagation law. In this paper, we introduce a social network propagation model integrating multiple linear regression and infectious disease model. Firstly, we proposed the features that affect social network communication from three dimensions. Then, we predicted the node influence via multiple linear regression. Lastly, we used the node influence as the state transition of the infectious disease model to predict the trend of information dissemination in social networks. The experimental results on a real social network dataset showed that the prediction results of the model are consistent with the actual information dissemination trends.

MRLBot: Multi-Dimensional Representation Learning for Social Media Bot Detection

Social media bots pose potential threats to the online environment, and the continuously evolving anti-detection technologies require bot detection methods to be more reliable and general. Current detection methods encounter challenges, including limited generalization ability, susceptibility to evasion in traditional feature engineering, and insufficient exploration of user relationships. To tackle these challenges, this paper proposes MRLBot, a social media bot detection framework based on unsupervised representation learning. We design a behavior representation learning model that utilizes Transformer and a CNN encoder–decoder to simultaneously extract global and local features from behavioral information. Furthermore, a network representation learning model is proposed that introduces intra- and outer-community-oriented random walks to learn structural features and community connections from the relationship graph. Finally, the behavioral representation and relationship representation learning models are combined to generate fused representations for bot detection. The experimental results of four publicly available social network datasets demonstrate that the proposed method has certain advantages over state-of-the-art detection methods in this field.

Variable neighborhood search for weighted total domination problem and its application in social network information spreading

The weighted total domination problem (WTDP) is a practical extension of the well-known total domination problem. The most efficient literature approaches to tackle this problem are based on branch and cut or genetic algorithm. In this work, we propose a different strategy to solve WTDP that relies on the popular variable neighborhood search (VNS) metaheuristic. VNS is equipped with a carefully designed fitness function that allows for evaluation of both feasible and infeasible solutions, which further allows for a thorough search of the promising regions of the solution space. The method also utilizes two effective first-improvement local search procedures. The effectiveness of VNS is demonstrated on a wide range of benchmark sets compared to all three competing methods from the literature. For small-to-middle-sized instances (up to 100 nodes), VNS can obtain solutions that match the quality of optimal solutions in almost all cases (134 out of 135). For middle-to-large-sized instances, VNS can outperform all comparison algorithms in terms of solution quality, which is verified by statistical hypothesis tests. Another key aspect of this paper is presenting a potential application of the WTDP for boosting information spreading across social networks. Experiments confirmed that information spreading is accelerated when informed nodes (spreaders) are set to be solutions of the WTDP obtained by VNS. Although our method has been successfully applied to samples of real social networks of up to approximately 81 thousand nodes and 1.34 million edges, further research might enhance the method to be used on various (unsampled) social network datasets.

A LOCALLY AND GLOBALLY TUNED METAHEURISTIC OPTIMIZATION FOR OVERLAPPING COMMUNITY DETECTION

Many people use online social networks to share their opinions and information in this digital age. The number of people engaged and their dynamic nature pose a major challenge for social network analysis (SNA). Community detection is one of the most critical and fascinating issues in social network analysis. Researchers frequently employ node features and topological structures to recognize important and meaningful performance in order to locate non-overlapping communities. We introduce a locally and globally tuned multi-objective biogeography-based optimization (LGMBBO) technique in this research for detecting overlapping communities based on the number of connections and node similarity. Four real- world online social network datasets were used in the experiment to assess the quality of both overlapping and non-overlapping partitions. As a result, the model generates a set of solutions that have the best topological structure of a network with node properties. The suggested model will increase their productivity and enhance their abilities to identify significant and pertinent communities.

Ethnic diversity fosters the social integration of refugee students

Forced migration has become a global megatrend, and many refugees are school aged. As social integration is key to their wellbeing and success, it is pivotal to determine factors that promote the social integration of refugee youth within schools. Here, using a large, nationally representative social network dataset from Germany, we examine the relationships of refugee adolescents with their peers (304 classrooms, 6,390 adolescents and 487 refugees). We find that refugee adolescents have fewer friends and are more often rejected as desk mates than their classmates. Crucially, however, they are less rejected in more diverse classrooms. This results from two basic processes: (1) more opportunities to meet other ethnic minority peers, who are more accepting of refugees in general and (2) higher acceptance of refugee adolescents by ethnic majority peers in more diverse settings. Our results can help promote the social adjustment of young refugees in school and mitigate the negative consequences of prejudice.

Quantum-PSO based unsupervised clustering of users in social networks using attributes.

Unsupervised cluster detection in social network analysis involves grouping social actors into distinct groups, each distinct from the others. Users in the clusters are semantically very similar to those in the same cluster and dissimilar to those in different clusters. Social network clustering reveals a wide range of useful information about users and has many applications in daily life. Various approaches are developed to find social network users' clusters, using only links or attributes and links. This work proposes a method for detecting social network users' clusters based solely on their attributes. In this case, users' attributes are considered categorical values. The most popular clustering algorithm used for categorical data is the K-mode algorithm. However, it may suffer from local optimum due to its random initialization of centroids. To overcome this issue, this manuscript proposes a methodology named the Quantum PSO approach based on user similarity maximization. In the proposed approach, firstly, dimensionality reduction is conducted by performing the relevant attribute set selection followed by redundant attribute removal. Secondly, the QPSO technique is used to maximize the similarity score between users to get clusters. Three different similarity measures are used separately to perform the dimensionality reduction and similarity maximization processes. Experiments are conducted on two popular social network datasets; ego-Twitter, and ego-Facebook. The results show that the proposed approach performs better clustering results in terms of three different performance metrics than K-Mode and K-Mean algorithms.

HAkAu: hybrid algorithm for effective k-automorphism anonymization of social networks

Online social network datasets contain a large amount of various information about their users. Preserving users’ privacy while publishing or sharing datasets with third parties has become a challenging problem. The k-automorphism is the anonymization method that protects the social network dataset against any passive structural attack. It provides a higher level of protection than other k-anonymity methods, including k-degree or k-neighborhood techniques. In this paper, we propose a hybrid algorithm that effectively modifies the social network to the k-automorphism one. The proposed algorithm is based on the structure of the previously published k-automorphism KM algorithm. However, it solves the NP-hard subtask of finding isomorphic graph extensions with a genetic algorithm and employs the GraMi algorithm for finding frequent subgraphs. In the design of the genetic algorithm, we introduce the novel chromosome representation in which the length of the chromosome is independent of the size of the input network, and each individual in each generation leads to the k-automorphism solution. Moreover, we present a heuristic method for selecting the set of vertex disjoint subgraphs. To test the algorithm, we run experiments on a set of real social networks and use the SecGraph tool to evaluate our results in terms of protection against deanonymization attacks and preserving data utility. It makes our experimental results comparable with any future research.

Triadic influence as a proxy for compatibility in social relationships

Networks of social interactions are the substrate upon which civilizations are built. Often, we create new bonds with people that we like or feel that our relationships are damaged through the intervention of third parties. Despite their importance and the huge impact that these processes have in our lives, quantitative scientific understanding of them is still in its infancy, mainly due to the difficulty of collecting large datasets of social networks including individual attributes. In this work, we present a thorough study of real social networks of 13 schools, with more than 3,000 students and 60,000 declared positive and negative relationships, including tests for personal traits of all the students. We introduce a metric-the "triadic influence"-that measures the influence of nearest neighbors in the relationships of their contacts. We use neural networks to predict the sign of the relationships in these social networks, extracting the probability that two students are friends or enemies depending on their personal attributes or the triadic influence. We alternatively use a high-dimensional embedding of the network structure to also predict the relationships. Remarkably, using the triadic influence (a simple one-dimensional metric) achieves the best accuracy, and adding the personal traits of the students does not improve the results, suggesting that the triadic influence acts as a proxy for the social compatibility of students. We postulate that the probabilities extracted from the neural networks-functions of the triadic influence and the personalities of the students-control the evolution of real social networks, opening an avenue for the quantitative study of these systems.

Improving the spatial–temporal aware attention network with dynamic trajectory graph learning for next Point-Of-Interest recommendation

Next Point-Of-Interest (POI) recommendation aim to predict users’ next visits by mining their movement patterns. Existing works attempt to extract spatial–temporal relationships from historical check-ins; however, the following critical factors have not been adequately considered: (1) structured features implied in trajectory that reflect individual visit tendency; (2) collaborative signals from other users and (3) dynamic user preference. To this end, we jointly take into full consideration the graph-structured information as well as sequential effects of user trajectory sequences and propose the Trajectory Graph enhanced Spatial–Temporal aware Attention Network (TGSTAN). Given the general preference among users and the shifts of individual interests over time, we present a novel trajectory-aware dynamic graph convolution network module (TDGCN) to facilitate the capturing of local spatial correlations. Specifically, TDGCN dynamically adjusts the normalized adjacency matrix of the trajectory graph by element-wise multiplication with self-attentive POI representations. The local trajectory graph is generated from the same training batch to reflect real-time and collaborative signals, while also following causality. Moreover, we explicitly integrate spatial–temporal interval information with bilinear interpolation to comprehensively attach relative proximity to attention mechanism when capturing long-term dependence. Extensive experiments on three real-world Location-Based Social Networks datasets (Foursquare_TKY, Weeplaces and Gowalla_CA) demonstrate that the proposed TGSTAN consistently outperforms the existing state-of-the-art baselines with an average of 8.18%, 6.59%, and 9.60% improvement on the three datasets, respectively.

Reinforcement-Learning-Based Dynamic Opinion Maximization Framework in Signed Social Networks

Dynamic opinion maximization (DOM) is a significant optimization issue, whose target is to select some nodes in the network and prorogate the opinions of network nodes, and produce the optimum node opinions. Until now, the node opinions of related researches are unchanged and seldom focus on social relationships. In the real scenario, the dynamic process of network nodes over time and user preference have existed. Therefore, this article proposes the <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">${Q}$ </tex-math></inline-formula> -learning-based DOM (QDOM) framework in signed social networks to solve the OM problem, which is made up of two phases: 1) the activated dynamic opinion model and 2) the <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">${Q}$ </tex-math></inline-formula> -learning-based seeding process. We propose the activated dynamic opinion model based on stateless <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">${Q}$ </tex-math></inline-formula> -learning theory to derive the opinion propagation process. Moreover, we design the <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">${Q}$ </tex-math></inline-formula> -learning-based seeding algorithm to obtain the seed nodes. The experimental results on the four signed social network data sets demonstrate that the proposed framework outperforms the state-of-the-art approaches on positive opinions, the ratio of positive opinions, and activated nodes.

Random Walk Sampling in Social Networks Involving Private Nodes

Analysis of social networks with limited data access is challenging for third parties. To address this challenge, a number of studies have developed algorithms that estimate properties of social networks via a simple random walk. However, most existing algorithms do not assume private nodes that do not publish their neighbors’ data when they are queried in empirical social networks. Here we propose a practical framework for estimating properties via random walk-based sampling in social networks involving private nodes. First, we develop a sampling algorithm by extending a simple random walk to the case of social networks involving private nodes. Then, we propose estimators with reduced biases induced by private nodes for the network size, average degree, and density of the node label. Our results show that the proposed estimators reduce biases induced by private nodes in the existing estimators by up to 92.6% on social network datasets involving private nodes.

Event-Based Probabilistic Embedding for POI Recommendation

Location-based social networks (LBSNs) have collected massive geo-tagged information, enabling the derivation of user preference for point of interests (POIs) in support of personalized recommendation. The existing embedding techniques deal with multiple factors by embedding a separate model for each factor. As a result, the interaction amongst various factors cannot be captured properly. In addition, we notice that the effectiveness of personalized recommendation is closely related to the current time and location. It is obvious that users would check into a POI which fits their interests, even if the current location is far away from the POI or the time is inappropriate. Therefore, it is necessary to recommend the right POI according to the time and geographic location of the user. In other words, it is necessary to predict the most likely visiting event, including users, POI, event time, and event location. In this paper, we propose a probabilistic embedding model called Topic And Region Embedding (TARE), which embeds events by simulating the users’ decision-making process. The results of TARE not only take various factors and their interaction into consideration but also consider the time and geographic location of events. Extensive experiments on three location-based social network datasets show that TARE achieves better performance in recommendation accuracy than existing state-of-the-art methods.

Minority-Weighted Graph Neural Network for Imbalanced Node Classification in Social Networks of Internet of People

Social networks are an essential component of the Internet of People (IoP) and play an important role in stimulating interactive communication among people. Graph convolutional networks provide methods for social network analysis with its impressive performance in semi-supervised node classification. However, the existing methods are based on the assumption of balanced data distribution and ignore the imbalanced problem of social networks. In order to extract the valuable information from imbalanced data for decision making, a novel method named minority-weighted graph neural network (mGNN) is presented in this article. It extends imbalanced classification ideas in the traditional machine learning field to graph-structured data to improve the classification performance of graph neural networks. In a node feature aggregation stage, the node membership values among nodes are calculated for minority nodes’ feature aggregation enhancement. In an oversampling stage, the cost-sensitive learning is used to improve edge prediction results of synthetic minority nodes, and further raise their importance. In addition, a Gumbel distribution is adopted as an activation function. The proposed mGNN is evaluated on six social network data sets. Experimental results show that it yields promising results for imbalanced node classification.

Dynamic Opinion Maximization Framework With Hybrid Method in Social Networks

Dynamic Opinion Maximization (DOM) is an optimization issue, which determines some influential network nodes (i.e., seed nodes) to propagate specific opinions towards a certain object (e.g., one individual) using a dynamic opinion model, and achieve the optimal opinion propagation. In this paper, we study the DOM and construct an effective hybrid framework to address the problem. Firstly, we explicate the DOM problem and design the objective function of the DOM. Then, based on the activation status with the linear threshold model and the dynamic opinion process with the weighted Hegselmann-Krause model, we devise the activated opinion model to estimate the activation status and dynamic opinion process of activated nodes effectively. We propose an effective hybrid framework to select the seed nodes, which includes community detection, the determination of candidate seed nodes, and the seeding algorithm with discrete particle swarm optimization. In particular, to better generate the seed nodes and promote their propagation, we design the selection algorithm of candidate seed nodes and replacement strategy. Experimental results show the superiority of the proposed hybrid framework on the average opinions and the number of activated nodes than the baseline algorithms. Our method gains 17.89% more average opinions than EPN, 14.57% than RIS, 20.19% than CIDM, 2.58% than ATOM, and 7.22% than CELF on the eight social network datasets. Moreover, our method gains 28.17% more activated nodes than EPN, 25.31% than RIS, 36.34% than CIDM, 16.82% than ATOM, and 19.68% than CELF on average.

AF-GCN: Completing various graph tasks efficiently via adaptive quadratic frequency response function in graph spectral domain

Graph neural network is a breakthrough in applying deep learning to non-Euclidean space. It is widely used for tasks such as social network analysis, molecular function inference, drug repositioning and protein modeling, achieving outstanding performance on relational models. Despite the great success of graph neural networks, most of them cannot be generalized to various scenarios. This is because graph information needs variation for different tasks and fixed models limit the flexibility of feature extraction. To address this challenge, we design a graph filter that can be adaptively adjusted according to graph tasks. This filter combines the multi-view strategy with the learnable quadratic frequency response function, using the crests of the quadratic functions to adaptively emphasize the required information. We further design the graph convolutional network model base on this adaptive filter, named AF-GCN. Extensive experiments are performed with 13 SOTA models on 12 different real-world datasets, including homogeneous and heterogeneous datasets in the node classification task, biological datasets, and social network datasets in the graph classification task. AF-GCN achieves state-of-the-art results in various scenarios. In addition, AF-GCN has high interpretability in the graph spatial domain. The development process from Graph Convolutional Networks (GCN) to AF-GCN has historical similarities with the development of Convolution Neural Networks (CNN).

Social Media Based Deep Auto-Encoder Model for Clinical Recommendation

One of the most actively studied topics in modern medicine is the use of deep learning and patient clinical data to make medication and ADR recommendations. However, the clinical community still has some work to do in order to build a model that hybridises the recommendation system. As a social media learning based deep auto-encoder model for clinical recommendation, this research proposes a hybrid model that combines deep self-decoder with Top n similar co-patient information to produce a joint optimisation function (SAeCR). Implicit clinical information can be extracted using the network representation learning technique. Three experiments were conducted on two real-world social network data sets to assess the efficacy of the SAeCR model. As demonstrated by the experiments, the suggested model outperforms the other classification method on a larger and sparser data set. In addition, social network data can help doctors determine the nature of a patient's relationship with a co-patient. The SAeCR model is more effective since it incorporates insights from network representation learning and social theory.

Plausible Heterogeneous Graph $k$-Anonymization for Social Networks

The inefficient utilization of ubiquitous graph data with combinatorial structures necessitates graph embedding methods, aiming at learning a continuous vector space for the graph which is amenable to be adopted in traditional machine learning algorithms in favor of vector representations. Graph embedding methods build an important bridge between social network analysis and data analytics as social networks naturally generate an unprecedented volume of graph data continuously. Publishing social network data not only bring benefit for public health, disaster response, commercial promotion, and many other applications, but also give birth to threats that jeopardize each individual's privacy and security. Unfortunately, most existing works in publishing social graph embedding data only focus on preserving social graph structure with less attention paid to the privacy issues inherited from social networks. To be specific, attackers can infer the presence of a sensitive relationship between two individuals by training a predictive model with the exposed social network embedding. In this paper, we propose a novel link-privacy preserved graph embedding framework using adversarial learning, which can reduce adversary's prediction accuracy on sensitive links while persevering sufficient non-sensitive information such as graph topology and node attributes in graph embedding. Extensive experiments are conducted to evaluate the proposed framework using ground truth social network datasets.

A content-location-aware personalized POI recommendation model

Aiming at the data sparsity problem of user-POI matrix in point of interest (POI) recommendation, the more and more studies have explored the contextual factors such as geographical location, content information and social relations to deal with the above-mentioned problem. However, the current research lacks comprehensive analysis and utilization of the relations of these contextual factors. Therefore, we propose a content-location-aware topic model (CLATM) to simulate the user check-in behavior in the decision-making process from the dual-perspective of content and location by using the probability generation method. CLATM consists of two core modules: content topic modeling and location topic modeling. The user check-in content depends on the content topic and location topic. The content topic and location topic jointly determine the user check-in location to a certain extent. The geographic location depends on the location topic and obeys Gaussian distribution. The CLATM model not only properly integrates the important contextual factors such as content, location and geography, but also makes full use of the latent relations between these factors to alleviate the data sparsity effectively. The performance of CLATM model is evaluated on two real location-based social network (LBSN) datasets, Foursquare and Yelp. The experimental results show that the model is superior to the baselines in recall and normalize discounted cumulative gain (NDCG), with the maximum increase of about 141.09% and 94.44% in recall@20 and NDCG@20, respectively. It can be concluded that comprehensive use of the relations of contextual factors can effectively improve the POI recommendation performance.

GAC: A deep reinforcement learning model toward user incentivization in unknown social networks

In recent years, many applications have deployed incentive mechanisms to promote users’ attention and engagement. Most incentive mechanisms determine specific incentive values based on users’ attributes (e.g., preferences), while such information is unavailable in many real-world applications. Meanwhile, due to budget restrictions, realizing successful incentivization for all users can be challenging to complete. In this light, we consider leveraging social influence to maximize the incentivization result. We can directly incentivize influential users to affect more users, so the cost of incentivizing these users can be decreased. However, identifying influential users in a social network requires complete information about influence strength among users, which is impractical to acquire in real-world situations. In this research, we propose an end-to-end reinforcement learning-based framework, called Geometric Actor–Critic (GAC), to tackle the abovementioned problem. The proposed approach can realize effective incentive allocation without having prior knowledge about users’ attributes. Three real-world social network datasets have been adopted in the experiments to evaluate the performance of GAC. The experimental results indicate that GAC can learn and apply effective incentive allocation policies in unknown social networks and outperform existing incentive allocation approaches.

Destination Image Analysis with User-Generated Content: A Computer Vision and Machine Learning Approach

This study proposes an approach to identify the elements that shape the destination image in the minds of potential tourists who peruse social network posts, based on Instagram images of Foça, a touristic district of İzmir, Turkey, in summer 2019. The elements in shared images that contributed to the development of Foça’s destination image were identified with computer vision, while word embedding and machine learning were used for element categorization and clustering, respectively. The study demonstrates the proportion of the elements in the photographs shared by Instagram users in 27 categories and subsequently, without any human intervention, constructs a representation of the elements the destination image was most dependent upon. Categorization showed that the categories that were the most representative of the destination image of Foça were sea and landforms, celestial, arts, events, urban, boating and water sports and constructional, respectively. The majority of destination image research with social network data sets relies on observation, interpretation or survey results. These studies are time-consuming and labour-intensive due to the large size of social network data. However, in this study, social network data can be analysed faster and efficiently with artificial intelligence and machine learning compared to conventional methods. Furthermore, the innovative methodology developed in the study contributes to the current tourism literature by proposing a decision support system for making computer-assisted tourism marketing decisions.