|
THE SYSTEM OF METRICS FOR ASSESSING AND PREDICTING THE INTERACTION OF A SOCIAL NETWORK USERS
|
|
|
N.Sergeev;A. Samoylov; S.Gushansky; I.Polovko
|
|
|
||
|
|
|
|
1314-2704
|
|
|
||
|
English
|
|
|
20
|
|
|
2.1
|
|
|
|
|
|
||
|
Analysis of social networks is one of the promising areas of research. In addition to the
development of a mathematical apparatus that allows processing the extracted data, it is of interest to identify new characteristics of user interaction. In the case of researching social networks, one of the important problems is the definition of a digital portrait of a user based on the consolidation and preliminary processing of open data from his profiles. To solve this problem, the authors previously proposed a model for representing the interaction of actors and a group of actors, which makes it possible to identify the fact and nature of the interaction based on implicit and indirect features. Such indirect features may include comments, activity in groups, joint appearance in photographs and check-in in certain places. However, historical interaction in itself is not of particular value. Interest lies in predicting user interactions and modeling the distribution of information from key people (influencers). The solution to this problem is of a significant social nature, associated with security and the early detection of negative events and phenomena. The article proposes a system of metrics based on implicit characteristics extracted from open data of social networks. A forecast model is described that allows one of the parameters to be determined: the radius of coverage, the speed of information dissemination, including when there is more than one influencer with different points of view. |
|
|
conference
|
|
|
||
|
||
|
20th International Multidisciplinary Scientific GeoConference SGEM 2020
|
|
|
20th International Multidisciplinary Scientific GeoConference SGEM 2020, 18 - 24 August, 2020
|
|
|
Proceedings Paper
|
|
|
STEF92 Technology
|
|
|
International Multidisciplinary Scientific GeoConference-SGEM
|
|
|
SWS Scholarly Society; Acad Sci Czech Republ; Latvian Acad Sci; Polish Acad Sci; Russian Acad Sci; Serbian Acad Sci & Arts; Natl Acad Sci Ukraine; Natl Acad Sci Armenia; Sci Council Japan; European Acad Sci, Arts & Letters; Acad Fine Arts Zagreb Croatia; C
|
|
|
389-394
|
|
|
18 - 24 August, 2020
|
|
|
website
|
|
|
cdrom
|
|
|
7011
|
|
|
user; social network; forecasting; logistic regression
|
|