Modelling the Behavior Classification of Social News Aggregations Users *[0000-0001-7548-5856] [0000-0003-1461-791X] Solomia Fedushko , Olha Trach , [0000-0002-9114-1911] Yaryna Turchyn , Zoryana Kunch [0000-0002-8924-7274] , Ulyana Yarka [0000-0003-1920-1980] Lviv Polytechnic National University, Lviv, Ukraine solomiia.s.fedushko@lpnu.ua, olya@trach.com.ua, turchyn.j@gmail.com, uliana.b.yarka@lpnu.ua, zorjana.kunch@gmail.com Abstract. This paper deals with actual fuzzy logic approach for modelling the behavior classification of social news aggregations users. The peculiarities of the structure of informational content of communities on the basis of social news aggregations are explored. A formal model of social news aggregation model has been developed, which includes user of the social news aggregation on the basis of fuzzy measures of its characteristics. The method of behavioral classification of users and methods for structuring sections and discussions of social news aggregations are developed. The methods for determining the main characteristics of the users of the social news aggregation: activeness, creative- ness, attractiveness, reactiveness, loyalty, is developed. Method for defining characteristics and classification of social news aggregations users is presented. Keywords: classification, social network, modelling, social news aggregation, fuzzy logic, behavior classification, web, user. 1 Introduction Each user of social news aggregations makes a contribution to the development of a social news aggregation. Contribution of the user can be determined objectively (based on the study of its behavior, information content, which is created and classifi- cation) and subjective (based on the assessments of other user of social news aggrega- tions and expert evaluations). The indicator of user usefulness allows ranking the users of social news aggregations, using received information for further administra- tive measures. For example, the most useful users need to be involved in moderation of the social news aggregation, to stimulate the material, while users with negative usefulness need to remove from social news aggregations. Ranking the users in the contribution and determining the core of social news aggre- gation user allows the administrator at any time to establish the users, who bring the social news aggregation the maximum benefit. This information is necessary and critically useful for managing the social news ag- gregation, since the social news aggregation is different from the usual site, which the administrator must take into account the views and interests of the users. And in order to make social news aggregation-based solutions is needed to listen to users, who have a great authority and make the main contribution to its development. The development of methods for behavioral classification of users of social news aggregation based on the presentation of information content as a tree is an urgent task. 2 The Method of User Behavioral Classification The user of the social news aggregation a person who visits the social news aggrega- tion site, reads or publishes its content in the form of discussions and messages on the social news aggregation is considered. The model of the user of the social news aggregation is assigned in the following form: Logini ,Passwordi ,Statusi ,Emaili , SNAU i  MemNamei ,LastVisiti ,PersonalDatai where SNAUi is a user of social news aggregations; Logini is pseudo of user; Pass- wordi is password of user; Statusi is the role of a user in the community; Emaili is e- mail; Memnamei is the name of the user; LastVisiti is date of the last visit to social news aggregation; PersonalDatai is personal data of the user. 2.1 Development of Methods for the Calculating Characteristics of Social News Aggregation Users In the course of the research it was established that the users of the social news aggre- gations (1) to a greater or lesser extent have the following characteristics in Figure 1. Fig. 1. Scheme of characteristics of social news aggregation users. Based on these characteristics, we define the rules for classifying users in social news aggregations. For presentation the characteristics of the users in the social news aggregation we will use a set of unclear plurals of the listed characteristics of the community users in rela- tion to the entire social news aggregation are determined based on the analysis of the behavior of users within the community: ─ activeness is determined by the amount of information content they create; ─ creativeness is determined the quality of information content and how other users of community react to it; ─ attractiveness is determined the quantity of users who react to the created content; ─ reactiveness is a way of participating in discussions; ─ loyalty is a reaction to the information content of other users. 2.2 Development of Methods for Calculating the Values of Linguistic Variables and Measures of Belonging For each of the proposed characteristics of the users, we introduce the corresponding linguistic variables: Activeness, Creativeness, Attractiveness, Reactiveness, and Loy- alty. The linguistic variable is given by the quartet < 𝛽, 𝑇, 𝑋, 𝑀 > where 𝛽 is the name of the linguistic variable; T is a plural of values of a linguistic variable, which is the names of fuzzy variables; T  " low"," medium"," high" X is area of definition of fuzzy variables describing the linguistic variable 𝑋 = [0; 𝑐𝑎𝑟𝑑(𝑃𝑜𝑠𝑡)]; M is a set of measures of fuzzy variables, which are values of a linguistic variable.  A2 1 A1 A3 0,5 x 1 1 2  2  3  1 4  2  Pнизька Pсередня Pнизька Pсередня Pсередня Pвисока Pсередня Pвисока card(Post) Fig. 2. The function of belonging to fuzzy plurals: A1 –"low", A2 – "medium", A3 –"high". (1)  2  1 2 3 4 1  2 Plow , Plow , Pmedium , Pmedium , Pmedium , Pmedium , Phigh , Phigh are the param- eters that are proportional to card(Post) and given by an expert or administrator of the forum, and moreover              Pmedium  Plow  Pmedium  Pmedium  Phigh  Pmedium  Phigh 1. 1 1 2 2 3 1 4 2 Plow All the P parameters that are used later in the membership functions are determined by experts for each feature of the social news aggregation. We will write down the functions of membership for all characteristics (1) – (30) of the users of the social news aggregation. The activeness of creating discussions:  1,if 0  ActivenessThread  SNAU i   Patlow 1   2  Patlow  ActivenessThread  SNAU i  low Th     2 1 , (1)  Pat low  Pat low  if Patlow  ActivenessThread  SNAU i   Patlow 1  2  ActivenessThread  SNAU i   Patmedium  1  2  1 ,  Patmedium  Patmedium   if Patmedium  ActivenessThread  SNAU i   Patmedium  1 2  2 medium Th   1,if Patmedium  ActivenessThread  SNAU i   Patmedium 3 (2)  Pat  medium  ActivenessThread  SNAU i  3 3 ,  Patmedium  Patmedium   3  if Patmedium  ActivenessThread  SNAU i   Patmedium 4   ActivenessThread  SNAU i   Pathigh 1   2 1 ,  Pat high  Pat high  high Th   if Pathigh 1  ActivenessThread  SNAU i   Pathigh  2 (3)   1, if Pat  2   Activeness  high Thread  SNAU i   1 where ActivenessThread  SNAUi  is activeness of creating posts j-th user. The activeness of creating polls:  1, if 0  ActivenessPoll  SNAU i   Papllow 1   2  Papllow  ActivenessPoll  SNAU i  low  Pl     2 1 ,  Papl low  Papllow (4)  if Papllow  ActivenessPost  SNAU i   Papllow  1 2  ActivenessPoll  SNAU i   Paplmedium 1  2  1 ,  Paplmedium  Paplmedium   if Paplmedium  ActivenessPoll  SNAU i   Paplmedium  1  2  2 medium  Pl   1, if Paplmedium  ActivenessPoll  SNAU i   Paplmedium 3 (5)   Paplmedium  ActivenessPoll  SNAU i  , 4  3 Paplmedium 3  Paplmedium   3  if Paplmedium  ActivenessPoll  SNAU i   Paplmedium 4   ActivenessPoll  SNAU i   Paplhigh 1   2 1 ,  Paplhigh  Paplhigh  high  Pl    if Paplhigh  1  ActivenessPoll  SNAU i   Paplhigh  2 (6)    1, if Papl  2   Activeness  high Poll  SNAU i   1 where ActivenessPoll  SNAUi  is the activity of creating polls i-th user. The activeness of creating posts:  1, if 0  ActivenessPost  SNAU i   Papslow  1  2  Papslow  ActivenessPost  SNAU i  low  Ps     2  1 , (7)  Paps low  Papslow   if Papslow  ActivenessPost  SNAU i   Papslow  1 2  ActivenessPost  SNAU i   Papsmedium  1  2  1 ,  Papsmedium  Papsmedium   if Papsmedium  ActivenessPost  SNAU i   Papsmedium  1 2  (8) 2 medium  Ps   1, if Papsmedium  ActivenessPost  SNAU i   Papsmedium 3   Papsmedium  ActivenessPost  SNAU i  , 4  Papsmedium3  3  Papsmedium   3  if Papsmedium  ActivenessPost  SNAU i   Papsmedium 4   ActivenessPost  SNAU i   Papshigh  1  2  1 ,  Papshigh  Papshigh  high  Ps   if Papshigh  1  ActivenessPost  SNAU i   Papshigh 2 (9)    1, if Paps  2   Activeness  high Post  SNAU i   1 where ActivenessPost  SNAUi  is the activity of the i-th user in the creation of posts. Activeness of participation in polls:  1, if 0  ActivenessVote  SNAU i   Pvtlow  1   Pvt    ActivenessVote  SNAU i  2 low Vt    low  2  1 , (10)  Pvt low  Plow  if Pvtlow  ActivenessVote  SNAU i   Pvtlow  1  2  ActivenessVote  SNAU i   Pvtmedium  1   2  1 ,  Pvtmedium  Pvtmedium   if Pvtmedium  ActivenessVote  SNAU i   Pvtmedium  1  2  2  medium Vt   1, if Pvtmedium  ActivenessVote  SNAU i   Pvtmedium 3 (11)   Pvtmedium  ActivenessVote  SNAU i  , 4  3 Pvtmedium  3  Pvtmedium  3  if Pvtmedium  ActivenessVote  SNAU i   Pvtmedium 4    ActivenessVote  SNAU i   Pvthigh 1   2 1 ,  Pvthigh  Pvthigh  high Vt   if Pvthigh 1  ActivenessVote  SNAU i   Pvthigh  2 (12)    1, if Pvt  2   Activeness  high Vote  SNAU i   1 where ActivenessVote  SNAUi  is active participation in the voting. The activeness of evaluating the actions of other users:  1, if 0  ActivityFeedback  SNAU i   Pfblow  1  2  Pfblow  ActivityFeedback  SNAU i  low  Fb     2  1 , (13)  Pfblow  Pfblow  if Pfblow  ActivityFeedback  SNAU i   Pfblow  1 2  ActivenessFeedback  SNAU i   Pfbmedium  1      ,  Pfbmedium 2 1  Pfbmedium   if Pfbmedium  ActivenessFeedback  SNAU i   Pfbmedium  1 2 (14)  2 medium  Fb   1, if Pfbmedium  ActivenessFeedback  SNAU i   Pfbmedium 3   Pfbmedium  ActivenessFeedback  SNAU i  , 4  Pfbm edium 3  3  Pfbmedium  3  if Pfbmedium  ActivenessFeedback  SNAU i   Pfbmedium 4   ActivenessFeedback  SNAU i   Pfbhigh 1   2  1 ,  Pfbhigh  Pfbhigh  high  Fb   if Phigh  1  ActivenessFeedback  meSNAU i mberi   Pfbhigh 2 (15)    1, if Pfbhigh 2  ActivenessFeedback  SNAU i   1  where ActivenessFeedback  SNAUi  is the activeness of evaluating actions by the i- th user. Total activeness: Calculated based on these types of activeness: 1, якщо 0  ActivenessTotal  SNAU i   Ptlow 1   2  Ptlow  ActivenessTotal  SNAU i  low Total    2 1 , (16)  Ptlow  Ptlow   if Ptlow  ActivenessTotal  SNAU i   Ptlow  1 2  ActivenessTotal  SNAU i   Ptmedium  1   2 1 ,  Ptmedium  Ptmedium   if Ptmedium  ActivenessTotal  SNAU i   Ptmedium  1 2  (17) 2 medium Total   1, if Patmedium  ActivenessTotal  SNAU i   Patmedium 3   Patmedium  ActivenessThread  SNAU i  , 4  3 Patmedium 3  Patmed  ium  if Patmedium  ActivenessTotal  SNAU i   Patmedium  3 4   ActivenessTotal  SNAU i   Pthigh 1   2 1 ,  Pthigh  Pthigh  high Total   if Pthigh 1  ActivenessTotal  SNAU i   Pthigh 2 (18)    1, if Pt  2   Activeness  high Total  SNAU i   1 where ActivenessTotal  SNAUi  is total activeness of the i-th user. Creativeness of the user: 1, if 0  Creativeness  SNAU i   Pcrlow 1  2  Pcrlow  Creativeness  SNAU i  low  Cr    2  1 , (19)  Pcrlow  Pcrlow   if Pcrlow  Creativeness  SNAU i   Pcrlow 1  2  Creativeness  SNAU i   Pcrmedium  1  2  1 ,  Pcrmedium  Pcrmedium   if Pcrmedium  Creativeness  SNAU i   Pcrmedium  1  2  medium  Cr   1,  2  Creativeness  SNAU i   Pcrmedium  3 (20) if Pcrmedium   4 Pcrmedium  Creativeness  SNAU i  ,   3 Pcrmedium 3  Pcrmedium  ium  Creativeness  SNAU i   Pcrmedium   3 4 Pcrmed   Creativeness  SNAU i   Pcrhigh 1  2  1 ,  Pcrhigh  Pcrhigh  high  Cr   if Pcrhigh 1  Creativeness  SNAU i   Pcrhigh  2 (21)    1, if Pcr  2   Creativeness SNAU  1  high  i where Creativeness SNAU i  is creativeness of the user. Аtractiveness of the user:  1, if 0  Attractiveness  SNAU i   Pattrlow 1  2  Pattrlow  Attractiveness  SNAU i  low  Attr   1  2 1 , (22)  Pattrlow  Pattrlow   if Pattrlow  Attractiveness  SNAU i   Pattrlow  1 2  Attractiveness  SNAU i   Pattrmedium  1   2  1 ,  Pattrmedium  Pattrmedium   if Pattrmedium  Attractiveness  SNAU i   Pattrmedium  1 2  (23)  2  medium  Attr   11, if Pattrmedium  Attractiveness  SNAU i   Pattrmedium  3   Pattrmedium  Attractiveness  SNAU i  , 4  Pattrmedium  3  3  Pattrmedium   3  if Pattrmedium  Attractiveness  SNAU i   Pattrmedium 4    Attractiveness  SNAU i   Pattrhigh 1   2 1 ,  Pattrhigh  Pattrhigh  high  Attr   1 if Pattrhigh 1  Attractiveness  SNAU i   Pattrhigh  2 (24)    1, if Pattr  2   Attractiveness SNAU  1  high  i where Attractiveness SNAU i   is attractiveness of the user. Reactiveness of the user.:  1, if 0  Reactiveness  SNAU i   Prlow 1  2  Prlow  Reactiveness  SNAU i  low  R   1  2  1 , (25)  Prlow  Prlow   if Prlow  Reactiveness  SNAU i   Prlow  1  2  Reactiveness  SNAU i   Prmedium 1   2  1 ,  Prmedium  Prmedium   if Prmedium  Reactiveness  SNAU i   Prmedium  1  2 (26)  2 medium  R   1, if Prmedium  Reactiveness  SNAU i   Prmedium 3   Prmedium  Reactiveness  SNAU i  , 4  3 Prmedium 3  Prmedium   3  if Prmedium  Reactiveness  SNAU i   Prmedium 4    Reactiveness  SNAU i   Prhigh  1   2 1 ,  Prhigh  Prhigh  high  R   if Prhigh  1  Reactiveness  SNAU i   Prhigh  2 (27)    1, if Pr  2   Reactiveness SNAU  1  high  i where R e activeness  SNAU i  is reactiveness of the user. Loyalty of the user: 1, if 0  Loyalty  SNAU i   Pllow  1  2  Pl  Loyalty  SNAU i  low  L    low 2  1 , (28)  Pllow  Pllow   if Pllow  Loyalty  SNAU i   Pllow 1  2  Loyalty  SNAU i   Plmedium 1  2  1 ,  Plmedium  Plmedium   if Plmedium  Loyalty  SNAU i   Plmedium  1  2  (29) 2 medium  L   1, if Plmedium  Loyalty  SNAU i   Plmedium 3   Plmedium  Loyalty  SNAU i  , 4  3 Plmedium  3  Plmedium   3  if Plmedium  Loyalty  SNAU i   Plmedium 4   Loyalty  SNAU i   Plhigh 1   2 1 ,  Plhigh  Plhigh  high  L   if Plhigh  1  Loyalty  SNAU i   Plhigh 2 (30)    1, if Pl  2   Loyalty SNAU  1  high  i where Loyalty  SNAU i  is loyalty of the user. 3 Building Rules for Classifying Users of Social News Aggregation The classification rules for each class of users of the social news aggregation are for- mulated based on the developed methods for calculating the characteristics of users and certain classes of social news aggregation users. The classes of the social news aggregation are proposed:  Activist  Moderator  Flamer  Author  Critic  Reader. The membership of the users in one of the classes based on its characteristics (Ac- tivity, Creativity, Attraction, Reactivity, Loyalty) is represented by production rules and Table 1. Table 1. Classes users of the social news aggregation. Moderator Flamer Author Critic Reader Activist Activeness medium, medium, medium, low low high high high Creativeness medium, medium, low low low high high Attractiveness low, low, high medium medium Reactiveness low, medium, high low low medium high Loyalty medium, low high 1. If Асtiveness(SNAU)  "medium","high" and Creativeness(SNAU)  "medium","high" and Reactivenes(SNAU)  "low","medium" then Member - Аctivist; 2. If Аctiveness(SNAU)  "medium","high" and Reactivenes(SNAU)="high" and Loyatly(SNAU)  "medium","high" , then Member - Мoderator; 3. If Аctiveness(SNAU)  "medium","high" and Creativeness(SNAU)="low" and Loyatly(SNAU)="low", then Member - Babbler; 4. If Аctiveness  SNAU  ="low" and Creativeness(SNAU)  "medium","high" and Аtractiveness(SNAU)  "medium","high" and Reactiveness  SNAU  ="low",then Member - Аuthor; 5. If Creativeness  SNAU  ="low" and Rеаctiveness(SNAU)  "low","high" and Аtractiveness(SNAU)="high" and Loyatly  SNAU  ="low",then Member - Critic; 6. If Аtractiveness  SNAU  ="low" and Creativeness( SNAU )="low" and Atractiveness( SNAU )  "low","average" and Reactiveness  SNAU  ="low", then Member - Reader; 4 Determine the User's Usefulness for the Community The usefulness of a user for the social news aggregation is a complex indicator calcu- lated on the basis of its characteristics: activeness, attractiveness, creativeness, reac- tiveness and loyalty. The usefulness of user ME is calculated by the equation: ME  C1  Activeness  C2  Attractiveness  C3  Creativeness  (31) C4  Reactiveness  C5  Loyalty where C1 ,C2 , ,C5 is weight coefficients of each user's characteristics, which are determined based on the development scenario of the social news aggregation, more- over  C  1 , Ci  0 . i i Consequently, 𝑀𝐸 ∈ [0, 1]. The user's usefulness allows the administrator to evaluate the importance of the user for the community and to take this value into account when applying sanctions. 5 Conclusion In this work the models have been developed that are the basis for further research on the construction of effective site positioning methods. Formalized structure of the social news aggregation, which includes two components (information content, users) is suggested. The peculiarities of the structure of informational content of communities on the basis of social news aggregations are explored. A formal social news aggregation model has been developed, which includes the model of user of the social news aggregation on the basis of fuzzy measures of its characteristics, the model of the structure of information content and the model of the content of information content, on the basis of which developed the method of behavioral classification of users and methods for structuring sections and discussions of social news aggregations. The methods for determining the main characteristics of the users of the web commu- nity: activeness, creativeness, attractiveness, reactiveness, loyalty are developed. The classes of users of social news aggregations on the basis of social news aggrega- tions are allocated and the rules of classification of users are formulated. References 1. Jin, L., Chen, Y., Wang, T., Hui, P., Vasilakos, A.: Understanding user behavior in online social networks: a survey. Communications Magazine, 51, (9), 144-150 (2013). 2. Benevenuto, F., Rodrigues, T., Cha, M., Almeida, V.: Characterizing user behavior in online social networks. In: 9th ACM SIGCOMM conference on Internet measure- ment (IMC '09). ACM, pp. 49-62. New York, USA (2009). 3. Fernández, A., García, S., del Jesus, M. J., Herrera, F.: A study of the behaviour of linguis- tic fuzzy rule based classification systems in the framework of imbalanced data-sets. Fuzzy Sets Syst., 159 (18), 2378-2398 (2008). 4. Korzh, R., Peleshchyshyn, A., Syerov, Y., Fedushko, S.: University’s information image as a result of university web communities’ activities. Advances in Intelligent Systems and Computing. Advances in Intelligent Systems and Computing, 512, pp. 115-127. Springer, Cham (2017). DOI: 10.1007/978-3-319-45991-2_8 5. Morente-Molinera, J., et al.: Supervised learning classification methods using multigranu- lar linguistic modeling and fuzzy entropy, Transactions on Fuzzy Systems, 25(5), 1078- 1089 (2017). 6. Fedushko, S., Ustyianovych, T.: Predicting pupil’s successfulness factors using machine learning algorithms and mathematical modelling methods. Advances in Computer Science for Engineering and Education II. ICCSEEA 2019. Advances in Intelligent Systems and Computing, 938, pp. 625-636. Springer (2020). DOI 10.1007/978-3-030-16621-2_58 7. Olson, D. L., Delen, D: Advanced Data Mining Techniques. NY, USA: Springer, 2008. 8. Lee, H.-M., et al.: An efficient fuzzy classifier with feature selection based on fuzzy entro- py, Trans. Syst. Man Cybern. B Cybern., 31 (3), 426-432 (2001). 9. Wendy, N., Misha, P.: Moving behavioral theories into the 21st century: technological ad- vancements for improving quality of life. IEEE pulse. 4(5), 25-28 (2013). 10. Syerov, Y., Fedushko, S., Loboda, Z.: Determination of development scenarios of the edu- cational web forum. In: 11th International Scientific and Technical Conference “Computer Sciences and Information Technologies” CSIT-2016, 73-76 (2016). DOI: 10.1109/STC- CSIT.2016.7589872. 11. Liu, J., Weitzman, E., Chunara, R.: Assessing Behavioral Stages From Social Media Da- ta. In: Conference on Computer-Supported Cooperative Work, pp.1320-1333 (2017). 12. Bilushchak, Т., Peleshchyshyn, A., Komova, M.: Development of method of search and identification of historical information in the social environment of the Internet. In: XIth International Scientific and Technical Conference "Computer Sciences and Infor- mation Technologies" CSIT-2017, 196-199 (2017). 13. Trach O., Peleshchyshyn A.: Functional-network model of tasks performance of virtual communication life cycle directions. In: XIIth International Conference "Computer Sci- ences and Information Technologies" CSIT-2016. pp. 108-110. Lviv (2016). 14. Trach O., Vus V., Tymovchak-Maksymets O.: Typical algorithm of stage completion when creating a virtual community of a HEI. In: XIIIth International Conference on Ad- vanced Trends in Radioelectronics, Telecommunications and Computer Engineering, TCSET-2016, pp. 849-851. Lviv-Slavske (2016). 15. Dosyn, D., Lytvyn, V., Kovalevych, V., Oborska, O., Holoshchuk, R.: Knowledge discov- ery as planning development in knowledgebase framework. Modern Problems of Radio Engineering, Telecommunications and Computer Science. In: 13th International Confer- ence on on Advanced Trends in Radioelectronics, Telecommunications and Computer En- gineering, TCSET-2016, pp. 449-451. Lviv-Slavsko, Ukraine (2016). 16. Lytvyn, V., Peleshchak, I., Peleshchak, R., Holoshchuk, R.: Detection of multispectral in- put images using nonlinear artificial neural networks. In: 14th International Conference on Advanced Trends in Radioelectronics, Telecommunications and Computer Engineering, TCSET, pp. 119-122. Slavske, Ukraine (2018). 17. Artem, K., Holoshchuk, R., Kunanets, N., Shestakevysh, T., Rzheuskyi, A.: Information Support of Scientific Researches of Virtual Communities on the Platform of Cloud Ser- vices. Advances in Intelligent Systems and Computing. Advances in intelligent systems and computing III, 871, pp. 301-311 (2019). 18. Zhezhnych, P., Tarasov, D.: Methods of data processing restriction in ERP Systems. In: 13th International Scientific and Technical Conference on Computer Sciences and Infor- mation Technologies, CSIT 2018, pp. 274-277 (2018). 19. Tkachenko, R., Izonin, I.: Model and Principles for the Implementation of Neural-Like Structures based on Geometric Data Transformations. Advances in Computer Science for Engineering and Education. International Conference on Computer Science, Engineering and Education Applications, ICCSEEA 2018. Advances in Intelligent Systems and Com- puting, vol 754, 578-587. Springer, Cham (2019). doi: 10.1007/978-3-319-91008-6_58 20. Gozhyj, A., Vysotska, V., Yevseyeva, I., Kalinina, I., Gozhyj, V.: Web resources man- agement method based on intelligent technologies. Advances in Intelligent Systems and Computing, 871, 206-221 (2019). 21. Gozhyj, A., Kalinina, I., Vysotska, V., Gozhyj, V.: The method of web-resources man- agement under conditions of uncertainty based on fuzzy logic. In: 13th International Scien- tific and Technical Conference "Computer Sciences and Information Technologies" CSIT 2018, pp. 343-346 (2018). 22. Lytvyn, V., Dosyn, D., Emmerich, M., Yevseyeva, I.: Content formation method in the web systems. CEUR Workshop Proceedings, 2136, pp. 42-61 (2018). 23. Anisimova O., Vasylenko V.: Social networks as the instrument for a higher education in- stitution image creation. 1-st International Workshop Control, Optimization and Analytical Processing of Social Networks (2019). In press.