The influence maximization problem aims to select a small set of influential nodes, termed a seed set, to maximize their influence coverage in social networks. Although the methods that are based on a greedy strategy ...The influence maximization problem aims to select a small set of influential nodes, termed a seed set, to maximize their influence coverage in social networks. Although the methods that are based on a greedy strategy can obtain good accuracy, they come at the cost of enormous computational time, and are therefore not applicable to practical scenarios in large-scale networks. In addition, the centrality heuristic algorithms that are based on network topology can be completed in relatively less time. However, they tend to fail to achieve satisfactory results because of drawbacks such as overlapped influence spread. In this work, we propose a discrete two-stage metaheuristic optimization combining quantum-behaved particle swarm optimization with Lévy flight to identify a set of the most influential spreaders. According to the framework,first, the particles in the population are tasked to conduct an exploration in the global solution space to eventually converge to an acceptable solution through the crossover and replacement operations. Second, the Lévy flight mechanism is used to perform a wandering walk on the optimal candidate solution in the population to exploit the potentially unidentified influential nodes in the network. Experiments on six real-world social networks show that the proposed algorithm achieves more satisfactory results when compared to other well-known algorithms.展开更多
The public is increasingly using social media platforms such as Twitter and Facebook to express their views on a variety of topics.As a result,social media has emerged as the most effective and largest open source for...The public is increasingly using social media platforms such as Twitter and Facebook to express their views on a variety of topics.As a result,social media has emerged as the most effective and largest open source for obtaining public opinion.Single node computational methods are inefficient for sentiment analysis on such large datasets.Supercomputers or parallel or distributed proces-sing are two options for dealing with such large amounts of data.Most parallel programming frameworks,such as MPI(Message Processing Interface),are dif-ficult to use and scale in environments where supercomputers are expensive.Using the Apache Spark Parallel Model,this proposed work presents a scalable system for sentiment analysis on Twitter.A Spark-based Naive Bayes training technique is suggested for this purpose;unlike prior research,this algorithm does not need any disk access.Millions of tweets have been classified using the trained model.Experiments with various-sized clusters reveal that the suggested strategy is extremely scalable and cost-effective for larger data sets.It is nearly 12 times quicker than the Map Reduce-based model and nearly 21 times faster than the Naive Bayes Classifier in Apache Mahout.To evaluate the framework’s scalabil-ity,we gathered a large training corpus from Twitter.The accuracy of the classi-fier trained with this new dataset was more than 80%.展开更多
Influence Maximization(IM)aims to select a seed set of size k in a social network so that information can be spread most widely under a specific information propagation model through this set of nodes.However,most exi...Influence Maximization(IM)aims to select a seed set of size k in a social network so that information can be spread most widely under a specific information propagation model through this set of nodes.However,most existing studies on the IM problem focus on static social network features,while neglecting the features of temporal social networks.To bridge this gap,we focus on node features reflected by their historical interaction behavior in temporal social networks,i.e.,interaction attributes and self-similarity,and incorporate them into the influence maximization algorithm and information propagation model.Firstly,we propose a node feature-aware voting algorithm,called ISVoteRank,for seed nodes selection.Specifically,before voting,the algorithm sets the initial voting ability of nodes in a personalized manner by combining their features.During the voting process,voting weights are set based on the interaction strength between nodes,allowing nodes to vote at different extents and subsequently weakening their voting ability accordingly.The process concludes by selecting the top k nodes with the highest voting scores as seeds,avoiding the inefficiency of iterative seed selection in traditional voting-based algorithms.Secondly,we extend the Independent Cascade(IC)model and propose the Dynamic Independent Cascade(DIC)model,which aims to capture the dynamic features in the information propagation process by combining node features.Finally,experiments demonstrate that the ISVoteRank algorithm has been improved in both effectiveness and efficiency compared to baseline methods,and the influence spread through the DIC model is improved compared to the IC model.展开更多
This paper proposes a deep neural network(DNN)approach for detecting fake profiles in social networks.The DNN model is trained on a large dataset of real and fake profiles and is designed to learn complex features and...This paper proposes a deep neural network(DNN)approach for detecting fake profiles in social networks.The DNN model is trained on a large dataset of real and fake profiles and is designed to learn complex features and patterns that distinguish between the two types of profiles.In addition,the present research aims to determine the minimum set of profile data required for recognizing fake profiles on Facebook and propose the deep convolutional neural network method for fake accounts detection on social networks,which has been developed using 16 features based on content-based and profilebased features.The results demonstrated that the proposed method could detect fake profiles with an accuracy of 99.4%,equivalent to the achieved findings based on bigger data sets and more extensive profile information.The results were obtained with the minimum available profile data.In addition,in comparison with the other methods that use the same amount and kind of data,the proposed deep neural network gives an increase in accuracy of roughly 14%.The proposed model outperforms existing methods,achieving high accuracy and F1 score in identifying fake profiles.The associated findings indicate that the proposed model attained an average accuracy of 99%while considering two distinct scenarios:one with a single theme and another with a miscellaneous one.The results demonstrate the potential of DNNs in addressing the challenging problem of detecting fake profiles,which has significant implications for maintaining the authenticity and trustworthiness of online social networks.展开更多
Health professionals and mainly nurses must be kept updated on context conditions where populations they have in charge, since this is the only way to maintain communication with those vulnerable groups avoiding barri...Health professionals and mainly nurses must be kept updated on context conditions where populations they have in charge, since this is the only way to maintain communication with those vulnerable groups avoiding barriers, there are topics of difficult approach such as the use and abuse of substances in adolescents, and currently adolescents communicate through social networks. We aimed to determine the influence of social networks as a pedagogic strategy in adolescents’ health education. Method: Qualitative and descriptive study with phenomenological design. Fifteen informants from nursing career participated, and selected by convenience. Data collection was through a semi-structured interview composed of 5 questions directed to informants, regarding their experience to make an informative video about use and abuse in adolescents;questions were about their experiences, found difficulties and any other element related with the making of the video, its spread, the login and acceptance that the audiovisual material had in social networks by students and the management of information with preventive goals. All final products were incorporated to a link where group members, as well as the student community, could revise the video and make comments, maintain a chat with others, and so on, a dynamic session of presentations on questions and comments was done. An informed consent was signed. Collected qualitative data were analyzed according to De Souza Minayo. Results: Three categories emerged with nine sub-categories, Category 1: Influence of social networks on students, sub-categories: 1.1) Perception about addictions, 1.2) Expectation on attention to addictions, 1.3) As educational strategy. Category 2: Experiences of students with social networks, sub-categories: 2.1) Motivates creativity, 2.2) Rescue learned skills and add others, 2.3) Motivates empathy. Category 3: Use of social networks by nurse students, sub-categories: 3.1) Constraint in videos production, 3.2) Advantage for spread in social networks, 3.3) Favors health education. Conclusion: Social networks are accepted and used by adolescents, they represent a recommendable pedagogic strategy as a way to inform, health education and prevention of use and abuse of legal and illegal substances in vulnerable groups, it is easy to access and is a good working tool for health professionals to help in prevent of this public health issue, and to keep and reach wider coverage in health education.展开更多
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 int...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.展开更多
Influence maximization of temporal social networks(IMT)is a problem that aims to find the most influential set of nodes in the temporal network so that their information can be the most widely spread.To solve the IMT ...Influence maximization of temporal social networks(IMT)is a problem that aims to find the most influential set of nodes in the temporal network so that their information can be the most widely spread.To solve the IMT problem,we propose an influence maximization algorithm based on an improved K-shell method,namely improved K-shell in temporal social networks(KT).The algorithm takes into account the global and local structures of temporal social networks.First,to obtain the kernel value Ks of each node,in the global scope,it layers the network according to the temporal characteristic of nodes by improving the K-shell method.Then,in the local scope,the calculation method of comprehensive degree is proposed to weigh the influence of nodes.Finally,the node with the highest comprehensive degree in each core layer is selected as the seed.However,the seed selection strategy of KT can easily lose some influential nodes.Thus,by optimizing the seed selection strategy,this paper proposes an efficient heuristic algorithm called improved K-shell in temporal social networks for influence maximization(KTIM).According to the hierarchical distribution of cores,the algorithm adds nodes near the central core to the candidate seed set.It then searches for seeds in the candidate seed set according to the comprehensive degree.Experiments showthatKTIMis close to the best performing improved method for influence maximization of temporal graph(IMIT)algorithm in terms of effectiveness,but runs at least an order of magnitude faster than it.Therefore,considering the effectiveness and efficiency simultaneously in temporal social networks,the KTIM algorithm works better than other baseline algorithms.展开更多
Influence maximization,whose aim is to maximise the expected number of influenced nodes by selecting a seed set of k influential nodes from a social network,has many applications such as goods advertising and rumour s...Influence maximization,whose aim is to maximise the expected number of influenced nodes by selecting a seed set of k influential nodes from a social network,has many applications such as goods advertising and rumour suppression.Among the existing influence maximization methods,the community‐based ones can achieve a good balance between effectiveness and efficiency.However,this kind of algorithm usually utilise the network community structures by viewing each node as a non‐overlapping node.In fact,many nodes in social networks are overlapping ones,which play more important role in influence spreading.To this end,an overlapping community‐based particle swarm opti-mization algorithm named OCPSO for influence maximization in social networks,which can make full use of overlapping nodes,non‐overlapping nodes,and their interactive information is proposed.Specifically,an overlapping community detection algorithm is used to obtain the information of overlapping community structures,based on which three novel evolutionary strategies,such as initialisation,mutation,and local search are designed in OCPSO for better finding influential nodes.Experimental results in terms of influence spread and running time on nine real‐world social networks demonstrate that the proposed OCPSO is competitive and promising comparing to several state‐of‐the‐arts(e.g.CGA,CMA‐IM,CIM,CDH‐SHRINK,CNCG,and CFIN).展开更多
Recent developments on Internet and social networking have led to the growth of aggressive language and hate speech.Online provocation,abuses,and attacks are widely termed cyberbullying(CB).The massive quantity of use...Recent developments on Internet and social networking have led to the growth of aggressive language and hate speech.Online provocation,abuses,and attacks are widely termed cyberbullying(CB).The massive quantity of user generated content makes it difficult to recognize CB.Current advancements in machine learning(ML),deep learning(DL),and natural language processing(NLP)tools enable to detect and classify CB in social networks.In this view,this study introduces a spotted hyena optimizer with deep learning driven cybersecurity(SHODLCS)model for OSN.The presented SHODLCS model intends to accomplish cybersecurity from the identification of CB in the OSN.For achieving this,the SHODLCS model involves data pre-processing and TF-IDF based feature extraction.In addition,the cascaded recurrent neural network(CRNN)model is applied for the identification and classification of CB.Finally,the SHO algorithm is exploited to optimally tune the hyperparameters involved in the CRNN model and thereby results in enhanced classifier performance.The experimental validation of the SHODLCS model on the benchmark dataset portrayed the better outcomes of the SHODLCS model over the recent approaches.展开更多
It is commonly accepted that, on social networks, the opinion of the agents with a higher connectivity, i.e., a larger number of followers, results in more convincing than that of the agents with a lower number of fol...It is commonly accepted that, on social networks, the opinion of the agents with a higher connectivity, i.e., a larger number of followers, results in more convincing than that of the agents with a lower number of followers. By kinetic modeling approach, a kinetic model of opinion formation on social networks is derived, in which the distribution function depends on both the opinion and the connectivity of the agents. The opinion exchange process is governed by a Sznajd type model with three opinions, ±1, 0, and the social network is represented statistically with connectivity denoting the number of contacts of a given individual. The asymptotic mean opinion of a social network is determined in terms of the initial opinion and the connectivity of the agents.展开更多
Cyberbullying(CB)is a distressing online behavior that disturbs mental health significantly.Earlier studies have employed statistical and Machine Learning(ML)techniques for CB detection.With this motivation,the curren...Cyberbullying(CB)is a distressing online behavior that disturbs mental health significantly.Earlier studies have employed statistical and Machine Learning(ML)techniques for CB detection.With this motivation,the current paper presents an Optimal Deep Learning-based Cyberbullying Detection and Classification(ODL-CDC)technique for CB detection in social networks.The proposed ODL-CDC technique involves different processes such as pre-processing,prediction,and hyperparameter optimization.In addition,GloVe approach is employed in the generation of word embedding.Besides,the pre-processed data is fed into BidirectionalGated Recurrent Neural Network(BiGRNN)model for prediction.Moreover,hyperparameter tuning of BiGRNN model is carried out with the help of Search and Rescue Optimization(SRO)algorithm.In order to validate the improved classification performance of ODL-CDC technique,a comprehensive experimental analysis was carried out upon benchmark dataset and the results were inspected under varying aspects.A detailed comparative study portrayed the superiority of the proposed ODL-CDC technique over recent techniques,in terms of performance,with the maximum accuracy of 92.45%.展开更多
Cybersecurity encompasses various elements such as strategies,policies,processes,and techniques to accomplish availability,confidentiality,and integrity of resource processing,network,software,and data from attacks.In...Cybersecurity encompasses various elements such as strategies,policies,processes,and techniques to accomplish availability,confidentiality,and integrity of resource processing,network,software,and data from attacks.In this scenario,the rising popularity of Online Social Networks(OSN)is under threat from spammers for which effective spam bot detection approaches should be developed.Earlier studies have developed different approaches for the detection of spam bots in OSN.But those techniques primarily concentrated on hand-crafted features to capture the features of malicious users while the application of Deep Learning(DL)models needs to be explored.With this motivation,the current research article proposes a Spam Bot Detection technique using Hybrid DL model abbreviated as SBDHDL.The proposed SBD-HDL technique focuses on the detection of spam bots that exist in OSNs.The technique has different stages of operations such as pre-processing,classification,and parameter optimization.Besides,SBD-HDL technique hybridizes Graph Convolutional Network(GCN)with Recurrent Neural Network(RNN)model for spam bot classification process.In order to enhance the detection performance of GCN-RNN model,hyperparameters are tuned using Lion Optimization Algorithm(LOA).Both hybridization of GCN-RNN and LOA-based hyperparameter tuning process make the current work,a first-of-its-kind in this domain.The experimental validation of the proposed SBD-HDL technique,conducted upon benchmark dataset,established the supremacy of the technique since it was validated under different measures.展开更多
Graphs are used in various disciplines such as telecommunication,biological networks,as well as social networks.In large-scale networks,it is challenging to detect the communities by learning the distinct properties o...Graphs are used in various disciplines such as telecommunication,biological networks,as well as social networks.In large-scale networks,it is challenging to detect the communities by learning the distinct properties of the graph.As deep learning hasmade contributions in a variety of domains,we try to use deep learning techniques to mine the knowledge from large-scale graph networks.In this paper,we aim to provide a strategy for detecting communities using deep autoencoders and obtain generic neural attention to graphs.The advantages of neural attention are widely seen in the field of NLP and computer vision,which has low computational complexity for large-scale graphs.The contributions of the paper are summarized as follows.Firstly,a transformer is utilized to downsample the first-order proximities of the graph into a latent space,which can result in the structural properties and eventually assist in detecting the communities.Secondly,the fine-tuning task is conducted by tuning variant hyperparameters cautiously,which is applied to multiple social networks(Facebook and Twitch).Furthermore,the objective function(crossentropy)is tuned by L0 regularization.Lastly,the reconstructed model forms communities that present the relationship between the groups.The proposed robust model provides good generalization and is applicable to obtaining not only the community structures in social networks but also the node classification.The proposed graph-transformer shows advanced performance on the social networks with the average NMIs of 0.67±0.04,0.198±0.02,0.228±0.02,and 0.68±0.03 on Wikipedia crocodiles,Github Developers,Twitch England,and Facebook Page-Page networks,respectively.展开更多
In real-world networks,there usually exist a small set of nodes that play an important role in the structure and function of networks.Those vital nodes can influence most of other nodes in the network via a spreading ...In real-world networks,there usually exist a small set of nodes that play an important role in the structure and function of networks.Those vital nodes can influence most of other nodes in the network via a spreading process.While most of the existing works focused on vital nodes that can maximize the spreading size in the final stage,which we call final influencers,recent work proposed the idea of fast influencers,which emphasizes nodes’spreading capacity at the early stage.Despite the recent surge of efforts in identifying these two types of influencers in networks,there remained limited research on untangling the differences between the fast influencers and final influencers.In this paper,we firstly distinguish the two types of influencers:fast-only influencers and final-only influencers.The former is defined as individuals who can achieve a high spreading effect at the early stage but lose their superiority in the final stage,and the latter are those individuals that fail to exhibit a prominent spreading performance at the early stage but influence a large fraction of nodes at the final stage.Further experiments are based on eight empirical datasets,and we reveal the key differences between the two types of influencers concerning their spreading capacity and the local structures.We also analyze how network degree assortativity influences the fraction of the proposed two types of influencers.The results demonstrate that with the increase of degree assortativity,the fraction of the fast-only influencers decreases,which indicates that more fast influencers tend to keep their superiority at the final stage.Our study provides insights into the differences and evolution of different types of influencers and has important implications for various empirical applications,such as advertisement marketing and epidemic suppressing.展开更多
In this paper, we introduce an asymmetric payoff distribution mechanism into the evolutionary prisoner's dilemma game (PDG) on Newman Watts social networks, and study its effects on the evolution of cooperation. Th...In this paper, we introduce an asymmetric payoff distribution mechanism into the evolutionary prisoner's dilemma game (PDG) on Newman Watts social networks, and study its effects on the evolution of cooperation. The asymmetric payoff distribution mechanism can be adjusted by the parameter α: if α〉 0, the rich will exploit the poor to get richer; if α 〈 0, the rich are forced to offer part of their income to the poor. Numerical results show that the cooperator frequency monotonously increases with c~ and is remarkably promoted when c~ 〉 0. The effects of updating order and self-interaction are also investigated. The co-action of random updating and self-interaction can induce the highest cooperation level. Moreover, we employ the Gini coefficient to investigate the effect of asymmetric payoff distribution on the the system's wealth distribution. This work may be helpful for understanding cooperative behaviour and wealth inequality in society.展开更多
Online social media networks are gaining attention worldwide,with an increasing number of people relying on them to connect,communicate and share their daily pertinent event-related information.Event detection is now ...Online social media networks are gaining attention worldwide,with an increasing number of people relying on them to connect,communicate and share their daily pertinent event-related information.Event detection is now increasingly leveraging online social networks for highlighting events happening around the world via the Internet of People.In this paper,a novel Event Detection model based on Scoring and Word Embedding(ED-SWE)is proposed for discovering key events from a large volume of data streams of tweets and for generating an event summary using keywords and top-k tweets.The proposed ED-SWE model can distill high-quality tweets,reduce the negative impact of the advent of spam,and identify latent events in the data streams automatically.Moreover,a word embedding algorithm is used to learn a real-valued vector representation for a predefined fixed-sized vocabulary from a corpus of Twitter data.In order to further improve the performance of the Expectation-Maximization(EM)iteration algorithm,a novel initialization method based on the authority values of the tweets is also proposed in this paper to detect live events efficiently and precisely.Finally,a novel automatic identification method based on the cosine measure is used to automatically evaluate whether a given topic can form a live event.Experiments conducted on a real-world dataset demonstrate that the ED-SWE model exhibits better efficiency and accuracy than several state-of-art event detection models.展开更多
Community detection is one of the important tasks of social network analysis. It has significant practical importance for achieving cost-effective solutions for problems in the area of search engine optimization, spam...Community detection is one of the important tasks of social network analysis. It has significant practical importance for achieving cost-effective solutions for problems in the area of search engine optimization, spam detection, viral marketing, counter-terrorism, epidemic modeling, etc. In recent years, there has been an exponential growth of online social platforms such as Twitter, Facebook, Google+, Pinterest and Tumblr, as people can easily connect to each other in the Internet era overcoming geographical barriers. This has brought about new forms of social interaction, dialogue, exchange and collaboration across diverse social networks of unprecedented scales. At the same time, it presents new challenges and demands more effective, as well as scalable, graphmining techniques because the extraction of novel and useful knowledge from massive amount of graph data holds the key to the analysis of social networks in a much larger scale. In this research paper, the problem to find communities within social networks is considered. Existing community detection techniques utilize the topological structure of the social network, but a proper combination of the available attribute data, which represents the properties of the participants or actors, and the structure data of the social network graph is promising for the detection of more accurate and meaningful communities.展开更多
Currently, the collaboration in scientific communities has been studied in order to explain, among other things, the knowledge diffusion. The quality of Graduate Programmes is often associated with the scientific coll...Currently, the collaboration in scientific communities has been studied in order to explain, among other things, the knowledge diffusion. The quality of Graduate Programmes is often associated with the scientific collaboration. This paper discusses how scientific collaboration processes can be identified and characterized through social and complex networks. For this purpose, collaboration networks of bibliographic production, research projects, and committees of PhD theses and Masters’ dissertations by researchers from a graduate program in computational modeling were studied. The data were obtained from CAPES’ reports of the period from 2001 to 2009. Among the studied indices, centrality indices indicate the presence of prominent researchers who influence others and promptly interact with other researchers in the network. The indices of complex networks reveal the presence of the small-world (i.e. these networks are favorable to increase coordination between researchers) phenomenon and indicate a behavior of scale-free degree distribution (i.e. some researchers promote clustering more than others) for one of the studied networks.展开更多
Fractal and self similarity of complex networks have attracted much attention in recent years. The fractal dimension is a useful method to describe the fractal property of networks. However, the fractal features of mo...Fractal and self similarity of complex networks have attracted much attention in recent years. The fractal dimension is a useful method to describe the fractal property of networks. However, the fractal features of mobile social networks (MSNs) are inadequately investigated. In this work, a box-covering method based on the ratio of excluded mass to closeness centrality is presented to investigate the fractal feature of MSNs. Using this method, we find that some MSNs are fractal at different time intervals. Our simulation results indicate that the proposed method is available for analyzing the fractal property of MSNs.展开更多
The Internet of Things(IoT)has the potential to be applied to social networks due to innovative characteristics and sophisticated solutions that challenge traditional uses.Social network analysis(SNA)is a good example...The Internet of Things(IoT)has the potential to be applied to social networks due to innovative characteristics and sophisticated solutions that challenge traditional uses.Social network analysis(SNA)is a good example that has recently gained a lot of scientific attention.It has its roots in social and economic research,as well as the evaluation of network science,such as graph theory.Scientists in this area have subverted predefined theories,offering revolutionary ones regarding interconnected networks,and they have highlighted the mystery of six degrees of separation with confirmation of the small-world phenomenon.The motivation of this study is to understand and capture the clustering properties of large networks and social networks.We present a network growth model in this paper and build a scale-free artificial social network with controllable clustering coefficients.The random walk technique is paired with a triangle generating scheme in our proposed model.As a result,the clustering controlmechanism and preferential attachment(PA)have been realized.This research builds on the present random walk model.We took numerous measurements for validation,including degree behavior and the measure of clustering decay in terms of node degree,among other things.Finally,we conclude that our suggested random walk model is more efficient and accurate than previous state-of-the-art methods,and hence it could be a viable alternative for societal evolution.展开更多
基金Project supported by the Zhejiang Provincial Natural Science Foundation (Grant No.LQ20F020011)the Gansu Provincial Foundation for Distinguished Young Scholars (Grant No.23JRRA766)+1 种基金the National Natural Science Foundation of China (Grant No.62162040)the National Key Research and Development Program of China (Grant No.2020YFB1713600)。
文摘The influence maximization problem aims to select a small set of influential nodes, termed a seed set, to maximize their influence coverage in social networks. Although the methods that are based on a greedy strategy can obtain good accuracy, they come at the cost of enormous computational time, and are therefore not applicable to practical scenarios in large-scale networks. In addition, the centrality heuristic algorithms that are based on network topology can be completed in relatively less time. However, they tend to fail to achieve satisfactory results because of drawbacks such as overlapped influence spread. In this work, we propose a discrete two-stage metaheuristic optimization combining quantum-behaved particle swarm optimization with Lévy flight to identify a set of the most influential spreaders. According to the framework,first, the particles in the population are tasked to conduct an exploration in the global solution space to eventually converge to an acceptable solution through the crossover and replacement operations. Second, the Lévy flight mechanism is used to perform a wandering walk on the optimal candidate solution in the population to exploit the potentially unidentified influential nodes in the network. Experiments on six real-world social networks show that the proposed algorithm achieves more satisfactory results when compared to other well-known algorithms.
文摘The public is increasingly using social media platforms such as Twitter and Facebook to express their views on a variety of topics.As a result,social media has emerged as the most effective and largest open source for obtaining public opinion.Single node computational methods are inefficient for sentiment analysis on such large datasets.Supercomputers or parallel or distributed proces-sing are two options for dealing with such large amounts of data.Most parallel programming frameworks,such as MPI(Message Processing Interface),are dif-ficult to use and scale in environments where supercomputers are expensive.Using the Apache Spark Parallel Model,this proposed work presents a scalable system for sentiment analysis on Twitter.A Spark-based Naive Bayes training technique is suggested for this purpose;unlike prior research,this algorithm does not need any disk access.Millions of tweets have been classified using the trained model.Experiments with various-sized clusters reveal that the suggested strategy is extremely scalable and cost-effective for larger data sets.It is nearly 12 times quicker than the Map Reduce-based model and nearly 21 times faster than the Naive Bayes Classifier in Apache Mahout.To evaluate the framework’s scalabil-ity,we gathered a large training corpus from Twitter.The accuracy of the classi-fier trained with this new dataset was more than 80%.
基金supported by the Fundamental Research Funds for the Universities of Heilongjiang(Nos.145109217,135509234)the Youth Science and Technology Innovation Personnel Training Project of Heilongjiang(No.UNPYSCT-2020072)the Innovative Research Projects for Postgraduates of Qiqihar University(No.YJSCX2022048).
文摘Influence Maximization(IM)aims to select a seed set of size k in a social network so that information can be spread most widely under a specific information propagation model through this set of nodes.However,most existing studies on the IM problem focus on static social network features,while neglecting the features of temporal social networks.To bridge this gap,we focus on node features reflected by their historical interaction behavior in temporal social networks,i.e.,interaction attributes and self-similarity,and incorporate them into the influence maximization algorithm and information propagation model.Firstly,we propose a node feature-aware voting algorithm,called ISVoteRank,for seed nodes selection.Specifically,before voting,the algorithm sets the initial voting ability of nodes in a personalized manner by combining their features.During the voting process,voting weights are set based on the interaction strength between nodes,allowing nodes to vote at different extents and subsequently weakening their voting ability accordingly.The process concludes by selecting the top k nodes with the highest voting scores as seeds,avoiding the inefficiency of iterative seed selection in traditional voting-based algorithms.Secondly,we extend the Independent Cascade(IC)model and propose the Dynamic Independent Cascade(DIC)model,which aims to capture the dynamic features in the information propagation process by combining node features.Finally,experiments demonstrate that the ISVoteRank algorithm has been improved in both effectiveness and efficiency compared to baseline methods,and the influence spread through the DIC model is improved compared to the IC model.
文摘This paper proposes a deep neural network(DNN)approach for detecting fake profiles in social networks.The DNN model is trained on a large dataset of real and fake profiles and is designed to learn complex features and patterns that distinguish between the two types of profiles.In addition,the present research aims to determine the minimum set of profile data required for recognizing fake profiles on Facebook and propose the deep convolutional neural network method for fake accounts detection on social networks,which has been developed using 16 features based on content-based and profilebased features.The results demonstrated that the proposed method could detect fake profiles with an accuracy of 99.4%,equivalent to the achieved findings based on bigger data sets and more extensive profile information.The results were obtained with the minimum available profile data.In addition,in comparison with the other methods that use the same amount and kind of data,the proposed deep neural network gives an increase in accuracy of roughly 14%.The proposed model outperforms existing methods,achieving high accuracy and F1 score in identifying fake profiles.The associated findings indicate that the proposed model attained an average accuracy of 99%while considering two distinct scenarios:one with a single theme and another with a miscellaneous one.The results demonstrate the potential of DNNs in addressing the challenging problem of detecting fake profiles,which has significant implications for maintaining the authenticity and trustworthiness of online social networks.
文摘Health professionals and mainly nurses must be kept updated on context conditions where populations they have in charge, since this is the only way to maintain communication with those vulnerable groups avoiding barriers, there are topics of difficult approach such as the use and abuse of substances in adolescents, and currently adolescents communicate through social networks. We aimed to determine the influence of social networks as a pedagogic strategy in adolescents’ health education. Method: Qualitative and descriptive study with phenomenological design. Fifteen informants from nursing career participated, and selected by convenience. Data collection was through a semi-structured interview composed of 5 questions directed to informants, regarding their experience to make an informative video about use and abuse in adolescents;questions were about their experiences, found difficulties and any other element related with the making of the video, its spread, the login and acceptance that the audiovisual material had in social networks by students and the management of information with preventive goals. All final products were incorporated to a link where group members, as well as the student community, could revise the video and make comments, maintain a chat with others, and so on, a dynamic session of presentations on questions and comments was done. An informed consent was signed. Collected qualitative data were analyzed according to De Souza Minayo. Results: Three categories emerged with nine sub-categories, Category 1: Influence of social networks on students, sub-categories: 1.1) Perception about addictions, 1.2) Expectation on attention to addictions, 1.3) As educational strategy. Category 2: Experiences of students with social networks, sub-categories: 2.1) Motivates creativity, 2.2) Rescue learned skills and add others, 2.3) Motivates empathy. Category 3: Use of social networks by nurse students, sub-categories: 3.1) Constraint in videos production, 3.2) Advantage for spread in social networks, 3.3) Favors health education. Conclusion: Social networks are accepted and used by adolescents, they represent a recommendable pedagogic strategy as a way to inform, health education and prevention of use and abuse of legal and illegal substances in vulnerable groups, it is easy to access and is a good working tool for health professionals to help in prevent of this public health issue, and to keep and reach wider coverage in health education.
基金This work was supported by the 2021 Project of the“14th Five-Year Plan”of Shaanxi Education Science“Research on the Application of Educational Data Mining in Applied Undergraduate Teaching-Taking the Course of‘Computer Application Technology’as an Example”(SGH21Y0403)the Teaching Reform and Research Projects for Practical Teaching in 2022“Research on Practical Teaching of Applied Undergraduate Projects Based on‘Combination of Courses and Certificates”-Taking Computer Application Technology Courses as an Example”(SJJG02012)the 11th batch of Teaching Reform Research Project of Xi’an Jiaotong University City College“Project-Driven Cultivation and Research on Information Literacy of Applied Undergraduate Students in the Information Times-Taking Computer Application Technology Course Teaching as an Example”(111001).
文摘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.
基金Thiswork is supported by theYouth Science and Technology Innovation Personnel Training Project of Heilongjiang(No.UNPYSCT-2020072)the FundamentalResearch Funds for the Universities of Heilongjiang(Nos.145109217,135509234)+1 种基金the Education Science Fourteenth Five-Year Plan 2021 Project of Heilongjiang(No.GJB1421344)the Innovative Research Projects for Postgraduates of Qiqihar University(No.YJSCX2022048).
文摘Influence maximization of temporal social networks(IMT)is a problem that aims to find the most influential set of nodes in the temporal network so that their information can be the most widely spread.To solve the IMT problem,we propose an influence maximization algorithm based on an improved K-shell method,namely improved K-shell in temporal social networks(KT).The algorithm takes into account the global and local structures of temporal social networks.First,to obtain the kernel value Ks of each node,in the global scope,it layers the network according to the temporal characteristic of nodes by improving the K-shell method.Then,in the local scope,the calculation method of comprehensive degree is proposed to weigh the influence of nodes.Finally,the node with the highest comprehensive degree in each core layer is selected as the seed.However,the seed selection strategy of KT can easily lose some influential nodes.Thus,by optimizing the seed selection strategy,this paper proposes an efficient heuristic algorithm called improved K-shell in temporal social networks for influence maximization(KTIM).According to the hierarchical distribution of cores,the algorithm adds nodes near the central core to the candidate seed set.It then searches for seeds in the candidate seed set according to the comprehensive degree.Experiments showthatKTIMis close to the best performing improved method for influence maximization of temporal graph(IMIT)algorithm in terms of effectiveness,but runs at least an order of magnitude faster than it.Therefore,considering the effectiveness and efficiency simultaneously in temporal social networks,the KTIM algorithm works better than other baseline algorithms.
基金supported in part by the National Natural Science Foundation of China(61976001,62076001,61876184)the Key Projects of University Excellent Talents Support Plan of Anhui Provincial Department of Education(gxyqZD2021089)+1 种基金the University Synergy Innovation Program of Anhui Province(GXXT‐2020‐050)the Natural Science Foundation of Anhui Province(2008085QF309).
文摘Influence maximization,whose aim is to maximise the expected number of influenced nodes by selecting a seed set of k influential nodes from a social network,has many applications such as goods advertising and rumour suppression.Among the existing influence maximization methods,the community‐based ones can achieve a good balance between effectiveness and efficiency.However,this kind of algorithm usually utilise the network community structures by viewing each node as a non‐overlapping node.In fact,many nodes in social networks are overlapping ones,which play more important role in influence spreading.To this end,an overlapping community‐based particle swarm opti-mization algorithm named OCPSO for influence maximization in social networks,which can make full use of overlapping nodes,non‐overlapping nodes,and their interactive information is proposed.Specifically,an overlapping community detection algorithm is used to obtain the information of overlapping community structures,based on which three novel evolutionary strategies,such as initialisation,mutation,and local search are designed in OCPSO for better finding influential nodes.Experimental results in terms of influence spread and running time on nine real‐world social networks demonstrate that the proposed OCPSO is competitive and promising comparing to several state‐of‐the‐arts(e.g.CGA,CMA‐IM,CIM,CDH‐SHRINK,CNCG,and CFIN).
基金Princess Nourah bint Abdulrahman University Researchers Supporting Project number(PNURSP2022R140)Princess Nourah bint Abdulrahman University,Riyadh,Saudi Arabia.The authors would like to thank the Deanship of Scientific Research at Umm Al-Qura University for supporting this work by Grant Code:22UQU4310373DSR15.
文摘Recent developments on Internet and social networking have led to the growth of aggressive language and hate speech.Online provocation,abuses,and attacks are widely termed cyberbullying(CB).The massive quantity of user generated content makes it difficult to recognize CB.Current advancements in machine learning(ML),deep learning(DL),and natural language processing(NLP)tools enable to detect and classify CB in social networks.In this view,this study introduces a spotted hyena optimizer with deep learning driven cybersecurity(SHODLCS)model for OSN.The presented SHODLCS model intends to accomplish cybersecurity from the identification of CB in the OSN.For achieving this,the SHODLCS model involves data pre-processing and TF-IDF based feature extraction.In addition,the cascaded recurrent neural network(CRNN)model is applied for the identification and classification of CB.Finally,the SHO algorithm is exploited to optimally tune the hyperparameters involved in the CRNN model and thereby results in enhanced classifier performance.The experimental validation of the SHODLCS model on the benchmark dataset portrayed the better outcomes of the SHODLCS model over the recent approaches.
文摘It is commonly accepted that, on social networks, the opinion of the agents with a higher connectivity, i.e., a larger number of followers, results in more convincing than that of the agents with a lower number of followers. By kinetic modeling approach, a kinetic model of opinion formation on social networks is derived, in which the distribution function depends on both the opinion and the connectivity of the agents. The opinion exchange process is governed by a Sznajd type model with three opinions, ±1, 0, and the social network is represented statistically with connectivity denoting the number of contacts of a given individual. The asymptotic mean opinion of a social network is determined in terms of the initial opinion and the connectivity of the agents.
基金The authors extend their appreciation to the Deanship of Scientific Research at King Khalid University for funding this work under Grant Number(GPR/303/42)Princess Nourah bint Abdulrahman University Researchers Supporting Project Number(PNURSP2022R191),Princess Nourah bint Abdulrahman University,Riyadh,Saudi Arabia.
文摘Cyberbullying(CB)is a distressing online behavior that disturbs mental health significantly.Earlier studies have employed statistical and Machine Learning(ML)techniques for CB detection.With this motivation,the current paper presents an Optimal Deep Learning-based Cyberbullying Detection and Classification(ODL-CDC)technique for CB detection in social networks.The proposed ODL-CDC technique involves different processes such as pre-processing,prediction,and hyperparameter optimization.In addition,GloVe approach is employed in the generation of word embedding.Besides,the pre-processed data is fed into BidirectionalGated Recurrent Neural Network(BiGRNN)model for prediction.Moreover,hyperparameter tuning of BiGRNN model is carried out with the help of Search and Rescue Optimization(SRO)algorithm.In order to validate the improved classification performance of ODL-CDC technique,a comprehensive experimental analysis was carried out upon benchmark dataset and the results were inspected under varying aspects.A detailed comparative study portrayed the superiority of the proposed ODL-CDC technique over recent techniques,in terms of performance,with the maximum accuracy of 92.45%.
基金The authors extend their appreciation to the Deanship of Scientific Research at King Khalid University for funding this work under Grant Number(RGP 1/53/42).www.kku.edu.sa.This research was funded by the Deanship of Scientific Research at Princess Nourah bint Abdulrahman University through the Fast-Track Path of Research Funding Program。
文摘Cybersecurity encompasses various elements such as strategies,policies,processes,and techniques to accomplish availability,confidentiality,and integrity of resource processing,network,software,and data from attacks.In this scenario,the rising popularity of Online Social Networks(OSN)is under threat from spammers for which effective spam bot detection approaches should be developed.Earlier studies have developed different approaches for the detection of spam bots in OSN.But those techniques primarily concentrated on hand-crafted features to capture the features of malicious users while the application of Deep Learning(DL)models needs to be explored.With this motivation,the current research article proposes a Spam Bot Detection technique using Hybrid DL model abbreviated as SBDHDL.The proposed SBD-HDL technique focuses on the detection of spam bots that exist in OSNs.The technique has different stages of operations such as pre-processing,classification,and parameter optimization.Besides,SBD-HDL technique hybridizes Graph Convolutional Network(GCN)with Recurrent Neural Network(RNN)model for spam bot classification process.In order to enhance the detection performance of GCN-RNN model,hyperparameters are tuned using Lion Optimization Algorithm(LOA).Both hybridization of GCN-RNN and LOA-based hyperparameter tuning process make the current work,a first-of-its-kind in this domain.The experimental validation of the proposed SBD-HDL technique,conducted upon benchmark dataset,established the supremacy of the technique since it was validated under different measures.
基金The research is funded by the Researchers Supporting Project at King Saud University(Project#RSP-2021/305).
文摘Graphs are used in various disciplines such as telecommunication,biological networks,as well as social networks.In large-scale networks,it is challenging to detect the communities by learning the distinct properties of the graph.As deep learning hasmade contributions in a variety of domains,we try to use deep learning techniques to mine the knowledge from large-scale graph networks.In this paper,we aim to provide a strategy for detecting communities using deep autoencoders and obtain generic neural attention to graphs.The advantages of neural attention are widely seen in the field of NLP and computer vision,which has low computational complexity for large-scale graphs.The contributions of the paper are summarized as follows.Firstly,a transformer is utilized to downsample the first-order proximities of the graph into a latent space,which can result in the structural properties and eventually assist in detecting the communities.Secondly,the fine-tuning task is conducted by tuning variant hyperparameters cautiously,which is applied to multiple social networks(Facebook and Twitch).Furthermore,the objective function(crossentropy)is tuned by L0 regularization.Lastly,the reconstructed model forms communities that present the relationship between the groups.The proposed robust model provides good generalization and is applicable to obtaining not only the community structures in social networks but also the node classification.The proposed graph-transformer shows advanced performance on the social networks with the average NMIs of 0.67±0.04,0.198±0.02,0.228±0.02,and 0.68±0.03 on Wikipedia crocodiles,Github Developers,Twitch England,and Facebook Page-Page networks,respectively.
基金supported by the National Natural Science Foundation of China(Grant Nos.61673150 and 11622538)Special Project for the Central Guidance on Local Science and Technology Development of Sichuan Province,China(Project No.2021ZYD0029)。
文摘In real-world networks,there usually exist a small set of nodes that play an important role in the structure and function of networks.Those vital nodes can influence most of other nodes in the network via a spreading process.While most of the existing works focused on vital nodes that can maximize the spreading size in the final stage,which we call final influencers,recent work proposed the idea of fast influencers,which emphasizes nodes’spreading capacity at the early stage.Despite the recent surge of efforts in identifying these two types of influencers in networks,there remained limited research on untangling the differences between the fast influencers and final influencers.In this paper,we firstly distinguish the two types of influencers:fast-only influencers and final-only influencers.The former is defined as individuals who can achieve a high spreading effect at the early stage but lose their superiority in the final stage,and the latter are those individuals that fail to exhibit a prominent spreading performance at the early stage but influence a large fraction of nodes at the final stage.Further experiments are based on eight empirical datasets,and we reveal the key differences between the two types of influencers concerning their spreading capacity and the local structures.We also analyze how network degree assortativity influences the fraction of the proposed two types of influencers.The results demonstrate that with the increase of degree assortativity,the fraction of the fast-only influencers decreases,which indicates that more fast influencers tend to keep their superiority at the final stage.Our study provides insights into the differences and evolution of different types of influencers and has important implications for various empirical applications,such as advertisement marketing and epidemic suppressing.
基金Project supported by the Major State Basic Research Development Program of China (Grant No. 2004CB318109)Program for New Century Excellent Talents in University of China (Grant No. NCET-07-0787)the National Natural Science Foundation of China (Grant No. 70601026)
文摘In this paper, we introduce an asymmetric payoff distribution mechanism into the evolutionary prisoner's dilemma game (PDG) on Newman Watts social networks, and study its effects on the evolution of cooperation. The asymmetric payoff distribution mechanism can be adjusted by the parameter α: if α〉 0, the rich will exploit the poor to get richer; if α 〈 0, the rich are forced to offer part of their income to the poor. Numerical results show that the cooperator frequency monotonously increases with c~ and is remarkably promoted when c~ 〉 0. The effects of updating order and self-interaction are also investigated. The co-action of random updating and self-interaction can induce the highest cooperation level. Moreover, we employ the Gini coefficient to investigate the effect of asymmetric payoff distribution on the the system's wealth distribution. This work may be helpful for understanding cooperative behaviour and wealth inequality in society.
基金The work reported in this paper has been supported by UK-Jiangsu 20-20 World Class University Initiative programme.
文摘Online social media networks are gaining attention worldwide,with an increasing number of people relying on them to connect,communicate and share their daily pertinent event-related information.Event detection is now increasingly leveraging online social networks for highlighting events happening around the world via the Internet of People.In this paper,a novel Event Detection model based on Scoring and Word Embedding(ED-SWE)is proposed for discovering key events from a large volume of data streams of tweets and for generating an event summary using keywords and top-k tweets.The proposed ED-SWE model can distill high-quality tweets,reduce the negative impact of the advent of spam,and identify latent events in the data streams automatically.Moreover,a word embedding algorithm is used to learn a real-valued vector representation for a predefined fixed-sized vocabulary from a corpus of Twitter data.In order to further improve the performance of the Expectation-Maximization(EM)iteration algorithm,a novel initialization method based on the authority values of the tweets is also proposed in this paper to detect live events efficiently and precisely.Finally,a novel automatic identification method based on the cosine measure is used to automatically evaluate whether a given topic can form a live event.Experiments conducted on a real-world dataset demonstrate that the ED-SWE model exhibits better efficiency and accuracy than several state-of-art event detection models.
文摘Community detection is one of the important tasks of social network analysis. It has significant practical importance for achieving cost-effective solutions for problems in the area of search engine optimization, spam detection, viral marketing, counter-terrorism, epidemic modeling, etc. In recent years, there has been an exponential growth of online social platforms such as Twitter, Facebook, Google+, Pinterest and Tumblr, as people can easily connect to each other in the Internet era overcoming geographical barriers. This has brought about new forms of social interaction, dialogue, exchange and collaboration across diverse social networks of unprecedented scales. At the same time, it presents new challenges and demands more effective, as well as scalable, graphmining techniques because the extraction of novel and useful knowledge from massive amount of graph data holds the key to the analysis of social networks in a much larger scale. In this research paper, the problem to find communities within social networks is considered. Existing community detection techniques utilize the topological structure of the social network, but a proper combination of the available attribute data, which represents the properties of the participants or actors, and the structure data of the social network graph is promising for the detection of more accurate and meaningful communities.
基金financial support from CNPq(the Brazilian federal grant agency).
文摘Currently, the collaboration in scientific communities has been studied in order to explain, among other things, the knowledge diffusion. The quality of Graduate Programmes is often associated with the scientific collaboration. This paper discusses how scientific collaboration processes can be identified and characterized through social and complex networks. For this purpose, collaboration networks of bibliographic production, research projects, and committees of PhD theses and Masters’ dissertations by researchers from a graduate program in computational modeling were studied. The data were obtained from CAPES’ reports of the period from 2001 to 2009. Among the studied indices, centrality indices indicate the presence of prominent researchers who influence others and promptly interact with other researchers in the network. The indices of complex networks reveal the presence of the small-world (i.e. these networks are favorable to increase coordination between researchers) phenomenon and indicate a behavior of scale-free degree distribution (i.e. some researchers promote clustering more than others) for one of the studied networks.
基金Supported by the National Natural Science Foundation of China under Grant Nos 61501217,61363015,61501218 and 61262020the Natural Science Foundation of Jiangxi Province under Grant No 20142BAB206026
文摘Fractal and self similarity of complex networks have attracted much attention in recent years. The fractal dimension is a useful method to describe the fractal property of networks. However, the fractal features of mobile social networks (MSNs) are inadequately investigated. In this work, a box-covering method based on the ratio of excluded mass to closeness centrality is presented to investigate the fractal feature of MSNs. Using this method, we find that some MSNs are fractal at different time intervals. Our simulation results indicate that the proposed method is available for analyzing the fractal property of MSNs.
基金This work was supported in part by the Basic Science Research Program through the National Research Foundation of Korea(NRF)funded by the Ministry of Education under Grant NRF-2019R1A2C1006159 and Grant NRF-2021R1A6A1A03039493in part by the 2021 Yeungnam University Research Grant。
文摘The Internet of Things(IoT)has the potential to be applied to social networks due to innovative characteristics and sophisticated solutions that challenge traditional uses.Social network analysis(SNA)is a good example that has recently gained a lot of scientific attention.It has its roots in social and economic research,as well as the evaluation of network science,such as graph theory.Scientists in this area have subverted predefined theories,offering revolutionary ones regarding interconnected networks,and they have highlighted the mystery of six degrees of separation with confirmation of the small-world phenomenon.The motivation of this study is to understand and capture the clustering properties of large networks and social networks.We present a network growth model in this paper and build a scale-free artificial social network with controllable clustering coefficients.The random walk technique is paired with a triangle generating scheme in our proposed model.As a result,the clustering controlmechanism and preferential attachment(PA)have been realized.This research builds on the present random walk model.We took numerous measurements for validation,including degree behavior and the measure of clustering decay in terms of node degree,among other things.Finally,we conclude that our suggested random walk model is more efficient and accurate than previous state-of-the-art methods,and hence it could be a viable alternative for societal evolution.