CREATION OF A DICTIONARY OF KEYWORDS FOR A CLASSIFIER OF TEXTS CONTAINING DANGEROUS CONTENT IN THE CYBERSPACE OF KAZAKHSTAN
Published:
2023-09-30Section:
Engineering and engineeringArticle language:
RussianKeywords:
natural language processing, sentiment analysis, machine learning, term frequency, text classificationAbstract
This work is part of a study on the creation of an information system for searching dangerous content in the cyberspace of Kazakhstan. The aim of the study is to create a dictionary of keywords for the work of a classifier of texts containing dangerous content, using the example of the problem of identifying the presence of a suicidal risk in the texts of suicide notes and groups of suicidal. There is no such database for the Kazakh language. As a result of this research, an experimental corpus and a list of keywords in the Kazakh language were created. Keywords have been added to the database with various morphological forms.
License
Copyright (c) 2023 Вестник ВКТУ
This work is licensed under a Creative Commons Attribution 4.0 International License.
Most read articles by the same author(s)
- Kuanysh Nursakitov, APPLICATION OF NEURAL NETWORKS FOR CYBERBULLYING DETECTION , Вестник ВКТУ: Vol. 1 No. 4 (2023): CITech