Machine learning methods for forecasting of social network users’ reaction

Popova, Elizaveta; Leonenko, Vasiliy N.

doi:10.17586/2226-1494-2020-20-1-118-124

Cited by 6 publications

(1 citation statement)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In turn, the so-called dynamic approach to the study of social networks is characterized by a large number of different nuances. Based on the materials of the publication [16], within the framework of the dynamic approach it is possible to distinguish the so-called "mechanistic" and statistical directions of research realization. Thus, "mechanistic" research is characterized by the identification of a set of cause-andeffect relations or the determination of the direction of vectors of the main information flows, as well as attempts to explain the evolution of the structure of social networks, etc.…”

Section: Literature Reviewmentioning

confidence: 99%

Modeling of Information Processes in Social Networks

2021

View full text Add to dashboard Cite

In order to model information dissemination in social networks, a special methodology of sampling statistical data formation has been implemented. The probability distribution laws of various characteristics of personal and group accounts in four social networks are investigated. Stochastic aspects of interrelations between these indicators were analyzed. The classification of groups of social network users is proposed, and their characteristic features and main empirical regularities of mutual transitions are marked. Regression models of forecasting changes in the number of users of the selected groups have been obtained.

show abstract

Section: Literature Reviewmentioning

confidence: 99%