Online Social Network Post Classification: A Multiclass approach

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

This paper presents the results of automating the process of social network posts’ two-level hierarchical (ensemble) classification. The research aims to build a second-level model that allows to classify three main classes into subclasses using methods of multi-class classification (SVM, naive Bayesian classifier, random forest and multilayer perceptron). This work’s theoretical and practical significance is determined by the fact that the resulting model will partially automate the process of assessing the severity of users’ psychological characteristics on their text posts in social networks, as well as create the potential to refine the estimates of the protection of users from social engineering attacks, and the development of recommendation systems offering measures to improve users’ protection. The novelty of the work comes from the complementing of the previously developed two-level classification of social network posts with a second-level model based on known multiclass classification’s methods.

Original languageEnglish
Title of host publicationProceedings of the 5th International Scientific Conference “Intelligent Information Technologies for Industry”, IITI 2021
EditorsSergey Kovalev, Valery Tarassov, Vaclav Snasel, Andrey Sukhanov
PublisherSpringer Nature
Pages207-215
Number of pages9
ISBN (Print)9783030871772
DOIs
StatePublished - 2022
Event5th International Scientific Conference on Intelligent Information Technologies for Industry, IITI 2021 - Sochi, Russian Federation
Duration: 30 Sep 20214 Oct 2021

Publication series

NameLecture Notes in Networks and Systems
Volume330 LNNS
ISSN (Print)2367-3370
ISSN (Electronic)2367-3389

Conference

Conference5th International Scientific Conference on Intelligent Information Technologies for Industry, IITI 2021
Country/TerritoryRussian Federation
CitySochi
Period30/09/214/10/21

Scopus subject areas

  • Control and Systems Engineering
  • Signal Processing
  • Computer Networks and Communications

Keywords

  • Artificial intelligence
  • Data science
  • Information security
  • Multiclass text classification
  • Social engineering attacks
  • Social graph
  • Social media

Fingerprint

Dive into the research topics of 'Online Social Network Post Classification: A Multiclass approach'. Together they form a unique fingerprint.

Cite this