Documents

DOI

The aim of our work is to develop a software that could detect toxicity in the Russian segment of social media. In this paper, we investigated the problem of toxic detection in messages in Russian language. We implemented a set of features using selected vector models, trained some classifiers on the dataset about fourteen thousand annotated messages and compare results. Experiments were conducted with a calculation of accuracy, precision, and recall values. F1 measure reached the value 0.91, accuracy value is 0.87.

Translated title of the contributionКлассификация токсичных сообщений в социальных сетях
Original languageEnglish
Title of host publicationScience and Global Challenges of the 21st Century - Science and Technology - Proceedings of the International Perm Forum “Science and Global Challenges of the 21st Century”
Subtitle of host publicationProceedings of the International Perm Forum “Science and Global Challenges of the 21st Century”
EditorsAlvaro Rocha, Ekaterina Isaeva
Place of PublicationCham
PublisherSpringer Nature
Pages60-65
Number of pages6
EditionSpringer
ISBN (Electronic)978-3-030-89477-1
ISBN (Print)978-3-030-89476-4
DOIs
StatePublished - 2022
EventInternational Perm Forum on Science and Global Challenges of the 21st Century, 2021 - Perm, Russian Federation
Duration: 18 Oct 202123 Oct 2021

Publication series

NameLecture Notes in Networks and Systems
Volume342 LNNS
ISSN (Print)2367-3370
ISSN (Electronic)2367-3389

Conference

ConferenceInternational Perm Forum on Science and Global Challenges of the 21st Century, 2021
Country/TerritoryRussian Federation
CityPerm
Period18/10/2123/10/21

    Research areas

  • Natural Language Processing (NLP), Social network analysis, Machine learning, Toxic detection, Feature extraction, Social media analysis

    Scopus subject areas

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

ID: 97970958