User Behavior In Social Networks Research Articles

Big Data Analysis and User Behavior Prediction of Social Networks Based on Artificial Neural Network

The prediction of user behavior in social networks is of great significance for understanding user dynamics, personalized recommendation, and information dissemination. With the development of artificial intelligence (AI) technology, especially the application of artificial neural networks in big data analysis, new solutions and technical means have been provided for the analysis of user behavior in social networks. This study constructs a social network user behavior prediction model based on artificial neural networks. The article first reviews related research, establishes a research framework, and then describes in detail the functional structure of the user behavior prediction system. The key data structure design is meticulously constructed and the model is built through steps such as data preprocessing module, 3D feature frame construction module, feature mapping module, and feature prediction module. In addition, the article also constructs a group behavior theme probability prediction model based on an improved encoder-decoder model, which further enhances the understanding of group behavior of users in social networks. Through comparative experiments, the model proposed in this paper demonstrates its effectiveness in predicting individual and group user behaviors. The experimental results show that the model can accurately predict the behavior patterns of users in social networks and is superior to existing methods in terms of prediction accuracy and computational efficiency. This research shows that artificial neural networks are a powerful tool for analyzing big data in social networks and for predicting user behavior. The success of the study verifies the effectiveness of the model, provides a new technical path for future analysis of user behavior in social networks, and is expected to be widely applied in areas such as personalized recommendation and information dissemination analysis.

An improved model of the diffusion of Bass innovations for predicting changes in public opinion during the implementation of a narrative in social networks

During the writing of the article, the complex dynamics of forecasting public opinion based on the implementation of narratives in social networks were analyzed using Bass's innovation diffusion model. Recognizing the important role of narratives in the formation of collective views provides a basis for using Bass's innovation diffusion model to predict and understand changes in public attitudes during the introduction and implementation of narratives in social networks. On the basis of the above, the research task was set: improvement of the Bass innovation diffusion model for predicting changes in public opinion in social networks, which will directly contribute to the development of quality content by determined forces and means to create favorable conditions during the use of troops (forces) and in peacetime due to entering the coefficient of coverage of the target audience. During the writing of the article, theoretical methods were applied, namely, the analysis of research and publications on the topic of development in relation to the use of diffusion of innovations, which describes the process of how innovations are accepted by the population, the analysis of statistical data of public opinion, comparisons to identify development trends in the consumption of information in social networks, as well as synthesis to achieve the goal of the study. The article presents a mathematical apparatus that incorporates the Bass diffusion model into network behavior for modeling the spread of narratives and predicting changes in public opinion. For the first time, an approach to simulation modeling of the introduction and implementation of a narrative in a social network based on the Bass diffusion model was substantiated, which made it possible to investigate the consumer behavior of social network users under the influence of information and interpersonal communication in a social network. Integrating concepts from Bass's model, such as innovation adoption and imitative behavior, the proposed model aims to predict the dynamics of public attitudes in response to the spread of narratives.

Assessment of the main features of the model of dissemination of information in social networks

<span lang="EN-US">Social networks provide a fairly wide range of data that allows one way or another to evaluate the effect of the dissemination of information. This article presents the results of a study that describes methods for determining the key parameters of the model needed to analyze and predict the dissemination of information in social networks. An approach based on the analysis of statistical data on user behavior in social networks is proposed. The process of evaluating the main features of the model is described, including the mathematical methods used for data analysis and information dissemination modeling. The study aims to understand the processes of information dissemination in social networks and develop recommendations for the effective use of social networks as a communication and brand promotion tool, as well as to consider the analytical properties of the classical susceptible-infected-removed (SIR) model and evaluate its applicability to the problem of information dissemination. The results of the study can be used to create algorithms and techniques that will effectively manage the process of information dissemination in social networks.</span>

LEXICAL MEANS OF EXPRESSING VERBAL AGGRESSION IN SOCIAL NETWORKS (BASED ON THE MATERIALS OF COMMENTS ON FACEBOOK AND TWITTER ON THE PAGES OF P. POROSHENKO AND V. ZELENSKY)

The article characterizes the lexical means of realizing the conflictual communicative behavior of social network users. The network comments presented on the official pages of Ukrainian politicians - the current President of Ukraine Volodymyr Zelenskyi and the previous President of Ukraine Petro Poroshenko - in the Facebook and Twitter social networks were considered. The concept of verbal aggression is defined as a means of implementing conflictual communicative behavior. The genre specificity of comments in social networks is outlined and the peculiarities of their functioning are determined. Lexical units, which are verbal markers of aggressive behavior of commentators in social networks, were analyzed. The purpose of the study is to identify the main lexical means of implementing verbal aggression in the political discourse of social networks. The object of analysis is the conflictual communicative behavior of social network users; the subject of the study is the verbal aggression of commentators on the official pages of Ukrainian politicians. The material for analysis was comments on posts on the official pages of Ukrainian politicians Volodymyr Zelenskyi and Petro Poroshenko on Facebook and Twitter for the year 2023. In total, more than 2,000 comments were analyzed. The lexical means of expressing verbal aggression were analyzed based on the material of those comments that characterize politicians, rather than direct communicators – supporters of one of the Ukrainian presidents. It has been proven that the main means of representing verbal aggression in comments to the posts of Ukrainian politicians on Facebook and Twitter are anthroponyms, stylistically reduced vocabulary, invectives, jargonisms and reminiscences and quotes of politicians’ speeches.

Collecting and analyzing news from newspaper posts in facebook using machine learning

Many people use social networks to spend their free time. News, especially at the time of great world changes, began to gain considerable popularity. Washington Post, New York Times, Time, Reuters, Forbes are among the most famous global newspaper publications. An average analyst can spend up to 40 hours a week collecting information about competitors and researching the most popular posts. According to the conducted research, an average of 40 new posts with news per day. The data processing process can be automated using modern information tools to facilitate the routine work of analysts. To analyze the target audience and reach, it is worth considering the text of the message, the number of likes, comments and links. This information was obtained using the Selenium automated web page testing tool using the Java programming language. The time spent on collecting data in the described way from four newspaper editions amounts to approximately 12 hours. The Tensorflow library using the JavaScript programming language is applied to the collected information. Based on information about the number of shares, comments, likes, frequency of news posts, an analysis was carried out using machine learning algorithms. Based on the clustering data, we can observe such a tendency that posts with a large number of likes receive a large number of comments and vice versa. An analysis of the most active hours of users in the network based on news posts is performed. As a result, the highest activity is observed at least three times a day, namely: in the morning hours from 9:00 to 11:00, in the lunch time of the day from 12:00 to 15:00 and in the evening time period from 18:00 to 20:00. This trend is due to the work schedule of most employees during the working week. The resulting statistical information in the work can be used for other content or user behavior in social networks.

Emotion Analysis and Opinion Monitoring of Social Network Users Under Deep Convolutional Neural Network

With the development of the internet, the user behavior and emotional characteristics behind social networks have attracted scholars' attention. Meanwhile, identifying user emotion can promote the development of mobile communication technology and network intelligence industrialization. Based on this, this work explores the emotions of social network users and discusses the public comments on the speeches through the speeches of social network users. After 100 times of training, F1 of the BiLSTM algorithm can reach 97.32%, and after 100 times of training, its function loss can be reduced to 1.33%, which can reduce the impact of function loss on emotion recognition. The exploration is of great significance for analyzing the emotional behavior of social network users and provides a reference for the intelligent and systematic development of internet social model as well as the information management.

User behavior analysis based on edge evolutionary game model in social network

The application of evolutionary game method to study user behavior in social networks is a current hot issue. Most of the current evolutionary game models are proposed based on the game between nodes, which cannot accurately describe the diverse behaviors of users, and ignores the influence of network dynamics on evolutionary game. In order to solve the above problems, an edge evolution game (EEG) model is proposed in this paper. Firstly, the edge game model combines the pairwise interaction mode with the prisoner’s dilemma payoff matrix to calculate the user income. Secondly, on the basis of strategy update, the disconnect–reconnect mechanism is proposed to promote the updating of user relationship. In this mechanism, nodes perform the disconnect–reconnect based on the incomes: the betrayal neighbor with the lowest incomes is disconnected, and the neighbor of the disconnected neighbor with the highest incomes is reconnected. Finally, three kinds of networks are selected for experimental verification. The experimental results show that the cooperation clusters are formed in all three kinds of networks, which greatly promote the cooperation evolution among users.

Research on Digital Information Privacy Behavior of Social Network Users Based on Evolutionary Game

This article takes social network services as the research object and mainly conducts two aspects of research: first, based on previous research, combining the behavior characteristics of users in the social network environment related to digital information privacy, the digital information privacy of users pays attention to the influential factors of users’ digital information privacy information disclosure behavior, summarize and refine them, establish theoretical research models, and then use structural equation modelling to empirically analyze the significance of each influence path; then, based on the first part of the empirical research, the evolutionary game theory was used to analyze the interests of digital information privacy between social network users and service providers. This paper also studies the evolution of the willingness of each parameter to provide digital information to users under variable expected return conditions and uses MATLAB to analyze its evolutionary trends. It is found that the regulatory intensity coefficient, information leakage loss, and information sensitivity are both for users and websites. It has an important impact, and the loss of information leakage and information sensitivity can affect the evolution direction of users’ willingness to provide digital information and change the speed of website evolution, and the regulatory intensity coefficient is the opposite.

Behavior feature extraction method of college students’ social network in sports field based on clustering algorithm

Abstract In order to improve the integrity of the social network behavior feature extraction results for sports college students, this study proposes to be based on the clustering algorithm. This study analyzes the social network information dissemination mechanism in the field of college students’ sports, obtains the real-time social behavior data in the network environment combined with the analysis results, and processes the obtained social network behavior data from two aspects of data cleaning and de-duplication. Using clustering algorithm to determine the type of social network user behavior, setting the characteristics of social network behavior attributes, and finally through quantitative and standardized processing, get the results of college students’ sports field social network behavior characteristics extraction. The experimental results showed that the completeness of the method feature extraction results improved to 9.93%, and the average extraction time cost was 0.344 s, with high result integrity and obvious advantages in the extraction speed.

Modeling and Analysis of Opinion Dynamics in Social Networks Using Multiple-Population Mean Field Games

The dominanceof social networks has advanced immensely as many users become more dependent on these networks to be able to engage on social discussions and activities. The behavior of these users about a specific topic or issue can be extracted from their own belief or opinion as well as that of their connections. In order to derive meaningful and important behavioral information, these users can be modeled and analyzed together according to similarities in attributes such as political orientation, race, gender, and age. In this research work, the opinion dynamics of a multiple-population social network is investigated through the application of multiple-population mean field game (MPMFG) for behavior modeling and analysis. As a consequence of the proposed MPMFG model, information can be gained on the behavior of social network users belonging to different populations or groups. Specifically, the proposed MPFMG model can be utilized to estimate and predict the behavior of a social network group as well as their effect on the belief and opinion of other groups. Simulations are provided to demonstrate the belief and opinion dynamics of social network users in multiple-population settings. Moreover, theoretical and experimental results as well as comprehensive performance analysis are presented to demonstrate the effectiveness and validity of the proposed MPMFG approach in modeling and analyzing the evolution of opinions in multiple-population social networks.

Barriers to digitalization. Review of the book “Priklyucheniya tekhnologii: bar'ery tsifrovizatsii v Rossii” [The Adventures of Technologies: Barriers to Digitalization in Russia

The monograph under review presents the results of a study of barriers of various natures that arise during the implementation of several information projects - the development of unmanned vehicles, testing information programs in the IT sphere, interaction of people with a robot-operator of the help desk, behavior of social network users, and the creation of a turnstile system in transport. Another big topic of the book is the problems of the decision-making process for the development of technologies in a complex, heterogeneous socio-cultural environment, created by teams of different specialists, bearers of different managerial and technical cultures. To obtain information about the objects of research, indepth interviews, media materials, speeches of project leaders and engineers at public events were used, elements of a systematic analysis of the project progress were presented. It is emphasized that the objectively existing internal contradictions of mixed-type teams, in the presence of barriers-sets of tensions, can lead to a revision of the progress of information projects. Along with the barriers of a technological and managerial nature, some of the stress barriers are of a psychological and sociocultural nature. It is noted that the problems-barriers studied in the book can be analogs of “contradictions” in the methodology of the theory of inventive problem solving. The experience gained by the team of authors can be in demand for the implementation of digital projects of a large scale, for example, when carrying out the digital transformation of state-owned companies.

MVAESynth: a unified framework for multimodal data generation, modality restoration, and controlled generation

Synthetic data generation is used nowadays in a number of applications with privacy issues, such as training and testing of systems for analyzing the behavior of social network users or bank customers. Very often, personal data is complex and describes different aspects of a person, some of which may be missing for some records, which makes it very hard to deal with. In this paper, we present MVAESynth, a novel framework for the data-driven generation of multimodal synthetic data. It contains our implementation of a multimodal variational auto-encoder (MVAE), which is capable of generating user multimodal personal profiles (for example, social media profiles data and transactional data) and training even with missing modalities. Extensive experimental studies of MVAESynth performance were conducted demonstrating its effectiveness compared with the available solutions for the following tasks 1) training on data with missing modalities; 2) generating realistic social network profiles; 3) restoring missing profile modalities; 4) generating profiles with the specified characteristics.

Potential of the dynamic approach to data analysis

Explores the potential of a dynamic data analysis approach to study user behavior in social networks. Currently, information appears on social networks that allows differentiating user groups by their activity within the technical capabilities of a particular social network. The description of the information field of Tomsk is presented, a brief analysis is given. A dynamic approach to the study of user behavior, the structure of nodes and connections of social networks makes it possible to identify the rate of growth or decrease in the size of the network, the redistribution of connections between groups. There are four main stages in the analysis of social networks: 1) data collection; 2) selection of data for analysis; 3) selection and application of the analysis method; and 4) drawing conclusions. To obtain a complete picture of the information field of the Tomsk region, posts for 2019 were unloaded from all regional communities. All posts were classified based on training sample and specialized machine learning algorithm.

Information Propagation Formalized Representation of Micro-blog Network Based on Petri Nets

The description of user behavior in social networks is an important issue for studying social networks. Given that Petri nets can describe the resource flow problem, this study utilizes the features of Petri nets to portray the user behavior states during the message propagation of a micro-blog network and presents an information propagation formalized representation method of a micro-blog network. On this basis, this study analyzed the proposed formalized representation method in detail. We provide examples of applying formalized representation (e.g., micro-blog network addiction of users, user behavior influence, and public opinion analysis). In addition, we introduce the algorithms of formalized representation. We conduct experiments using Sina micro-blog data. Results show that the information propagation formalized representation method of micro-blog network based on Petri nets can depict user behaviors of micro-blog network intuitively and accurately. This study reveals a new perspective for information transmission of a micro-blog network and provides some tools to support public opinion monitoring and micro-blog marketing applications.

Application of clustering algorithm in social network user scenario prediction

In order to improve the ability of social network user behavior analysis and scenario pattern prediction, optimize social network construction, combine data mining and behavior analysis methods to perform social network user characteristic analysis and user scenario pattern optimization mining, and discover social network user behavior characteristics. Design multimedia content recommendation algorithms in multimedia social networks based on user behavior patterns. The current existing recommendation systems do not know how much the user likes the currently viewed content before the user scores the content or performs other operations, and the user’s preference may change at any time according to the user’s environment and the user’s identity, Usually in multimedia social networks, users have their own grading habits, or users’ ratings may be casual. Cluster-based algorithm, as an application of cluster analysis, based on clustering, the algorithm can predict the next position of the user. Because the algorithm has a “cold start”, it is suitable for new users without trajectories. You can also make predictions. In addition, the algorithm also considers the user’s feedback information, and constructs a scoring system, which can optimize the results of location prediction through iteration. The simulation results show that the accuracy of social network user scenario prediction using this method is higher, the accuracy of feature registration of social network user scenario mode is improved, and the real-time performance of algorithm processing is better.

Minimize Social Network Rumors Based on Rumor Path Tree

Social networks have become a powerful information spreading platform. How to limit rumor spread on social networks is a challenging problem. In this article, we combine information spreading mechanisms to simulate real-world social network user behavior. Based on this, we estimate the risk degree of each node during the hazard period and analyze the hazard level that other nodes are potentially affected by when a node is infected by a rumor. We use the Rumor Path Tree (RPT) to analyze the rumor spreading path. By comparing the rumors and truths propagation to a certain node, the steps taken by the rumor node to propagation are estimated. In order to identify the truth node, we construct a fractional function to calculate the effective influence nodes, and select the node with the highest score from the generated RPT pool. Based on the truth node we effectively block the spread of rumors. Finally, experimental results and comparisons on the real datasets prove that our method is effective and efficient.

Methods to identify the destructive information

The article discusses the methods that ensure the detection of destructive messages in the Internet environment. It is shown that to detect them the approaches based on the analysis of the syntactic patterns; analysis of semantic information included in the text, and correlating it with the text corpus; crowd sourcing methods; identification of the patterns of user behavior in social networks; the consideration of the additional information etc., were applied. Good results can be achieved under certain conditions: an access to traffic social networks and other online news resources, opportunities to organize or to get results from crowd sourcing, etc., when there are the restrictions on these conditions the detection of destructive messages can be performed based on indirect signs. The results of the detection of destructive news in the corpus of news reports in Russian, posted on the websites of the Republic of Kazakhstan are shown.

DEPLEST: A blockchain-based privacy-preserving distributed database toward user behaviors in social networks

Social networks record a significant amount of user behavior data every day. By analyzing this behavior data, companies or attackers use it for marketing or more questionable purposes. We propose a blockchain-based model to protect the privacy of users’ data in such big data environments. Traditional blockchain methods require too many resources for this task, so we propose a model that secures sensitive user information in a distributed blockchain and passes nonsensitive information through to the primary system in order to manage the blockchain size. Our DEPLEST algorithm performs these synchronization operations to keep local database storage and computational capacity within the limits of individual users’ devices. We also propose a consensus protocol for blockchain ledger maintenance that runs well on typical client systems and prove that this protocol has excellent Byzantine fault tolerance (BFT). Our experimental results show that DEPLEST meets the architectural and performance needs and that our consensus protocol outperforms the existing proof of work (PoW) and proof of stake (PoS) methods in this application.

Automatically identifying the function and intent of posts in underground forums

The automatic classification of posts from hacking-related online forums is of potential value for the understanding of user behaviour in social networks relating to cybercrime. We designed annotation schema to label forum posts for three properties: post type, author intent, and addressee. The post type indicates whether the text is a question, a comment, and so on. The author’s intent in writing the post could be positive, negative, moderating discussion, showing gratitude to another user, etc. The addressee of a post tends to be a general audience (e.g. other forum users) or individual users who have already contributed to a threaded discussion. We manually annotated a sample of posts and returned substantial agreement for post type and addressee, and fair agreement for author intent. We trained rule-based (logical) and machine learning (statistical) classification models to predict these labels automatically, and found that a hybrid logical–statistical model performs best for post type and author intent, whereas a purely statistical model is best for addressee. We discuss potential applications for this data, including the analysis of thread conversations in forum data and the identification of key actors within social networks.

Identifying trusted similar users using stochastic model and next-closure based knowledge model in online social networks

The social network is a medium where people of different religions, races, languages, hobbies, etc. come together and exchange information and knowledge without any social restrictions. Though they are divergent in many areas of their existence, they are all brought together by their interests. They tend to have closer communication only with those who have similar interests and trust. So identifying users of similar interest and evaluating their trustworthiness is mandatory in an online social network (OSN). As the user behavior in social network is dynamic, the stochastic process which evolves the randomness over the period is employed to compute the closeness between users in OSN. The current work proposes to identify the similar interested groups, based on the knowledge-based model through the provenance factors using formal concept analysis (FCA) and Jaccard index. The probability of closeness is derived using stochastic process reflecting the trustability of the user with respect to the different type of interaction behavior such as like, comment and chat.