A missing value approach to social network data: “Dislike” or “Nothing”?

Nowadays, online social networks (OSNs) become a part of human life. People use the OSNs for different purposes such as working, entertainment and so on. However, existing OSNs feed too much information into an audience's social network page without recognized the audience's situation or the audience's desire. This problem, called information overload, is a weak point of current OSNs. Our ultimate goal is to change traditional feeding information used in existing OSNs to a new type of feeding information by filtering out inconsistent information with the audience's situation. Therefore, this paper aims to prepare necessary features used in filtering information to get consistent information with the audience's situation. We also study behavior of audience in several aspects by analysis characteristic of post. The result indicates that three features are essential for the audience's decision to allow a post to be displayed on the audience's social network page, which are n1 (topic of post), n0 (audience's current situation), and n2 (type of relationship between audience and creator). Furthermore, other factors such as the number of times which a post is reviewed by the audience, age and, career have an impact on the audience's decision.

Scientific problem. The paper notes that the desire of Ukrainian universities to carry out PR-activities in social media is correlated with the tendencies of PR activity of European and American universities. However, the lack of specialists in digital communications (SMM) within the staff of universities makes it possible to characterize their activity in social media as being carried out without a clear definition of goals and using limited tools. Due to the lack of strategic planning, we observe low communication efficiency of using social media. Novelty. The brand pages of Ukrainian universities in social networks are analyzed, quantitative characteristics and content topics are investigated. Recommendations are developed for improving the efficiency of communication and updating the style of content on the brand pages of universities in social networks. Research methodology. The official accounts of Ukrainian classical and technical universities in social networks (Facebook, YouTube, Twitter and Instagram) are discovered and analyzed the statistics of these pages. Based on the statistical data and the method of observation, brand pages of universities in social networks are defined in which are active and promising for the promotion of the communication strategy of universities, and which social networks have lost popularity among target audiences. In addition, the analysis of the contents of Facebook brand pages is done. The basic statistics is graphically presented in four tables, which allow comparing the PR activity of the universities in social media. Results. For the effectiveness of PR in social media, it is necessary to increase the activity of followers, to distribute different content in the information and comment on the publications. It is proved that the lack of strategic planning of communicative activity in social networks negatively affects the results of both large PR campaigns and the effectiveness of communications for informational support of university activities. The main shortcomings in creating the content of the university's PR services and the main trends in writing messages in the Facebook news are revealed. The practical significance. The detailed study of the PR-practice of the universities makes it possible to develop recommendations for increasing the effectiveness of promote brand pages in social networks.

The paper presents findings of a survey into values of different generations conducted by Academy DTEK jointly with hh.ua|grc During two months of 2019 we polled 2,182 visitors of the Ukrainian Job portal hh.ua|grc (both job seekers and employers), followers of the survey organizers’ pages in social networks (Facebook and Telegram) aged between 15 and […]

Grouping users in social networks is an important process that improves matching and recommendation activities in social networks. The data mining methods of clustering can be used in grouping the users in social networks. However, the existing general purpose clustering algorithms perform poorly on the social network data due to the special nature of users' data in social networks. One main reason is the constraints that need to be considered in grouping users in social networks. Another reason is the need of capturing large amount of information about users which imposes computational complexity to an algorithm. In this paper, we propose a scalable and effective constraint-based clustering algorithm based on a global similarity measure that takes into consideration the users' constraints and their importance in social networks. Each constraint's importance is calculated based on the occurrence of this constraint in the dataset. Performance of the algorithm is demonstrated on a dataset obtained from an online dating website using internal and external evaluation measures. Results show that the proposed algorithm is able to increases the accuracy of matching users in social networks by 10% in comparison to other algorithms.

The purpose of research was to study the existing methods of determining the degree of cohesion of two users of social network, identifying their shortcomings and developing a new method. The research identified shortcomings of existing methods and proposed a new method for assessing the degree of cohesion of social network profiles based on open data from a social network. Under the degree of cohesion of users’ profiles is understood the probability of communication (interaction) of profile owners in real life, it is calculated for two users of the social network and expressed in percent. The work of the method is demonstrated on the example of the social network “In contact”. This method includes the sequence of the following stages: the first stage is data collection about users of the social network with API and the formation of tuples of users’ profile characteristics. A tuple of characteristics of social network profiles is the data, collected for each user, stored in a structured form. The next step is the analysis of the collected information. For each characteristic of the tuple of profiles, i.e. the possible element of interaction of users in the social network, the coefficient of cohesion by the characteristic is calculated. In addition, for each feature, its informativeness is calculated, i.e. how important is this or that feature in this social network. At the final stage, the results are generated, using the formula for the probability of communication between two users, derived during the investigation. Obtained as a result of the application of the method, the probability of communication between two users can be used to optimize the activities of the operative-search services and special bodies. In addition, the received degree of cohesion of two users can be interpreted as the probability of a channel of information leakage between them. The role of the user of the method can be any private or state organization that cares about the security of corporate data and commercial secrets, the operative-search service, as well as an organization that investigates cybercrimes and information security incidents.

The role of social networks in shaping the SMM business strategy is argued. The study of the main development trends and motives for using social networks by users is conducted and it is shown that social media is an effective tool for promoting business and improving marketing communications. The main arguments in favor of various social networks expressed by users are considered. The study of the level of engagement with content among subscribers of brand pages in social networks by different industries is conducted and the potential for business promotion is determined. The main metrics used to assess the effectiveness of marketing efforts in social media are identified. A practical study of the effectiveness of using social networks using the example of sportswear brands is conducted. Recommendations are provided for improving business promotion in social media to improve subscriber engagement indicators, as well as the formation and development of a digital marketing communications system.

Nowadays, the user linkage or link prediction task is usually based on user profile or some sensitive data (i.e., name, gender, ID, life or health insurance accounts, etc.). With the enhancement of laws and regulations, the difficulty of personal sensitive data acquisition is increasing. Moreover, the abnormal users called online water army often camouflage themselves to achieve specific goals. They often register false user information such as name, gender, age, etc. To protect privacy and satisfy the needs of camouflage, users and ISPs often hide those sensitive data (i.e., user profile). In this paper, we want to link same user in multiple social networks, which is formally defined as ULASN (User Linkage across Anonymized Social Networks) problem. ULASN is very challenging to address due to (1) the lack of enough ground-truth to build models and obtain accurate prediction results, (2) the studied networks are anonymized, where no user profile or sensitive data is available, and (3) the need of scalable algorithms for user linkage task in large-scale social nateworks, and (4) users in social network are interrelated. To resolve these challenges, a noval user linkage framework based on social structures called ULA is proposed in this paper. ULA tackles these problems by considering massive, low-quality and interrelated user information. It uses few ground-truth to partition users into blocks, which reduces the size of candidates. By extending Fellegi-Sunter methods, our proposed algorithm can handle social network similarity complying to continuous distributions. A probabilistic generative model is proposed and solved by EM algorithm. Simultaneously, missing value problem can also solved when we use EM algorithm to learning parameters. Extensive experiments conducted on two real-world social networks demonstrate that ULA can perform very well in solving ULASN problem.

The purpose of the article is to highlight the online representation of Ukrainian libraries in the conditions of quarantine restrictions and martial law, to analyze the subject of the presented content. The methodological basis of the article was institutional, systemic, structural-functional and socio-communication approaches. Analysis, cognitive, synthesis, generalization and librarian methods are also applied. The scientific novelty of the study consists in arguing for the adaptation of the functioning of Ukrainian libraries in the conditions of quarantine restrictions and martial law of the library of Ukraine, when they reoriented their work to a remote form and offered online services and electronic products, actively started blogs, pages in social networks and created YouTube channels. Conclusions. On the website, blogs, pages of social networks, in a difficult period of social upheavals, the libraries of Ukraine cover both news of library life, as well as educational, entertainment, information, and local history materials. The bibliographic, factographic, and multimedia products created help to represent the cultural life of communities, creative, literary, and cultural achievements of prominent regions and present the best assets of Ukraine to the world. The epidemic, and then the full-scale war, put Ukrainian libraries in a situation where it is necessary to quickly respond to the urgent needs of society and do it mainly with the help of online services. This is what became for the majority a test of viability and stability, of professionalism and demand. During this time, most of the important and necessary resources were created, blogs, pages were launched in various social networks, YouTube channels were established, and new information technologies and products were actively introduced into library processes. Ukrainian libraries will be in demand and useful only through active development in the digital age. Keywords: libraries of Ukraine, library affair, information society, content, digitization, library website, digitization.

The article deals with the reasons of the low degree of involvement of young people in scientific activities. It is noted that the popularization of this direction helps to improve not only economic, technological and other indicators, but also the whole social life. The involvement of young people, and in particular students, in research activities plays a huge role, as implemented developments often carry an innovative approach and allow to develop several possible variations not only to solve urgent problems, but also for their further integration into other priority areas. This paper describes the reasons why there is a fairly low level of student activity in scientific, research and project activities. Studying the aspects of this problem, the above is confirmed by the sociological research in the form of a questionnaire, which allows to identify the degree of motivation among students. It is fixed that at this stage it is difficult to use the means of motivation in full on the basis of the lack of a resource that can contribute to this and bring information to the audience. It is concluded that the basic source is necessary for the actualization of a particular direction. In the age of information and technological progress communication in society, the development and promotion of various ideas and directions is achieved through the use of the media component [3]. Various ways of solution are considered and as the most optimal it was revealed that the source, which will serve as a tool for the dissemination of information about research activities, is a website on the Internet, and the means of its actualization in the appropriate target audience can be designated pages in social networks. It is also noted that the development of the above resources in the social network is the most effective, as young people devote an impressive amount of time to social networks and they are the main source of information for them. The author believes that the introduction and distribution of content about various competitions, conferences, exhibitions and competitions actualizes scientific activities.

This paper describes and evaluates privacy-friendly methods for extracting quasi-social networks from browser behavior on user-generated content sites, for the purpose of finding good audiences for brand advertising (as opposed to click maximizing, for example). Targeting social-network neighbors resonates well with advertisers, and on-line browsing behavior data counterintuitively can allow the identification of good audiences anonymously. Besides being one of the first papers to our knowledge on data mining for on-line brand advertising, this paper makes several important contributions. We introduce a framework for evaluating brand audiences, in analogy to predictive-modeling holdout evaluation. We introduce methods for extracting quasi-social networks from data on visitations to social networking pages, without collecting any information on the identities of the browsers or the content of the social-network pages. We introduce measures of brand proximity in the network, and show that audiences with high brand proximity indeed show substantially higher brand affinity. Finally, we provide evidence that the quasi-social network embeds a true social network, which along with results from social theory offers one explanation for the increase in brand affinity of the selected audiences.

The appearance of social networks has been one of the most important events in the last decade. A social network is a network of interaction and communication whose nodes are its members and its edges are the relation between them. An outstanding concept in social networks is the concept of social influence which is of great significance. Social influence is the behavioral transformation in a person, caused by his/her relationship with other people, organizations and the network. Today, the concept of social influence is used in viral marketing. The aim of viral marketing is to find a small subset of influential users in the social networks for marketing a product. The aim of this paper is to offer an algorithm in order to choose expert and influential users in social networks. This algorithm uses leader discovery method in social networks for choosing expert and influential users. This method chooses those users as the expert and influential leaders of the social networks, who are influential among the other members and also those users that have enough specialty and knowledge about the marketing product. Consequently, the process of selecting expert and influential users for the algorithm would be quick and also the selected leaders are influential and expert enough to do marketing and advertising in the social network.

The paper analyses the linguistic means used to denote the military of the Ukrainian army within the discourse of the Russia-Ukraine armed conflict. The military conflict that has been ongoing since 2014 has affected the linguistic picture of Ukrainian society. In the media space, a complex of linguistic means is formed, reflecting the armed and information confrontation. A special role is played by linguistic units that objectify the positive image of a warrior of his own army. The purpose of the paper is to model the structure of the lexical-semantic group “WARRIORS” in the discourse of the Russia-Ukraine information war. For this purpose, the texts of Ukrainian information portals and pages in social networks are analysed, as a result of which 90 lexemes and collocations to denote the military of the Ukrainian army are recorded. As a result of the analysis, the structure of the lexico-semantic group “WARRIORS” as a component of the “DEFENDER” microfield within the lexical-semantic field “WAR” is modelled. A semantic-cognitive analysis of the DEFENDER and WARRIOR concepts in the discourse of information war is carried out. The results of the analysis show that the linguistic designation of the defender in the modern Ukrainian media discourse coincides with the traditional picture of the world of speakers, according to which the warrior of his own army is endowed with exclusively positive qualities. Within the lexical-semantic group “WARRIORS” two types of microgroups are distinguished: for designations of general concepts and specialized designations – with approximately the same set of constituents – 46 and 44 units, respectively. In each of these types, 10 lexical-semantic microgroups are allocated. It is established that in the analysed media space both ready-made nominative units and morphological innovations are used to denote the defender. The use of paraphrases and metaphorical collocations is common. The influence of socially important events on the choice of language units for the designation of the military is also recorded.

Objectively assessing the contribution of outreach activities and the popularization of scientific achievements in the development of modern society, the Institute of Biomedical Problems has been actively working in this direction for many years. Effective interaction of the Institute with Russian and foreign mass media is being implemented. Much attention is paid to maintaining Internet resources and pages in social networks. Publication activity (preparation and printing of informational articles, booklets, books, etc.) makes it possible to acquaint a wide range of readers with the achievements of space biology and medicine. A significant amount of work is carried out on the organization of exhibitions (both innovative technologies and museum and educational). The Institute pays much attention to the formation of educational content and lecture activities. An important area is the development of cooperation with public organizations in the field of cosmonautics. The Institute widely uses not only traditional and customary methods in this work, but also develops and applies new approaches, technological and methodological techniques.

Identification of influential users by neighbors in online social networks

Using multimodalities, the field of biometric is receiving widespread acceptance for efficient communication between users in social network. Hence, suitable designing of authentication and access control is highly required to perform analysis of system in social network domain. In this work, a Proximal Spatial Vector and Affinity Coefficient (PSV-AC) framework is designed with the objective of ensuring authentic communication between users in social network using face and fingerprint. Initially, multimodal user biometric features with proximal feature pixel stored in spatial vector are gene encoded to obtain biometric identity keys. User authenticity is authorized by decoding gene encoded biometric features using biometric identity keys. User Affinity Coefficient is calculated via antecedent instances shared between different social users. The social network user’s affinity coefficient is ordered in a matrix. Matrix ranking is then performed to identify whether authentic user social communication happened in network. Experiments have been carried out using BioSecure datasets to measure the performance in terms of number of social users, social network authentication time, access control time, multimodal biometric feature template size, and true positive rate.