Powered by OpenAIRE graph
Found an issue? Give us feedback
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/ ZENODOarrow_drop_down
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
ZENODO
Article
Data sources: ZENODO
addClaim

IJTIMOIY TARMOQLARDAGI XAVFLI YOZISHMALARNI AVTOMATIK ANIQLASH: K-MEANS KLASTERLASH VA 0.7 THRESHOLD ASOSIDAGI EKSPERIMENTAL TAHLIL

Authors: Babomurodov Ozod Jurayevich; Qo'yliyeva Feruzaxon Alisher qizi;

IJTIMOIY TARMOQLARDAGI XAVFLI YOZISHMALARNI AVTOMATIK ANIQLASH: K-MEANS KLASTERLASH VA 0.7 THRESHOLD ASOSIDAGI EKSPERIMENTAL TAHLIL

Abstract

Ushbu maqolada ijtimoiy tarmoqlarda foydalanuvchilar tomonidan yoziladigan qisqa matnlar xavfliligini aniqlash jarayoni K-Means algoritmi va yuqori chegaraviy qiymat — x ≥ 0.7 asosida baholash orqali o‘rganiladi. Tadqiqot doirasida 1000, 5000, 10 000 va 20 000 ta yozishmadan iborat to‘rt xil datasetda eksperimentlar o‘tkazildi. Natijalar shuni ko‘rsatdiki, yuqori threshold qo‘llanganda xavfli deb belgilangan xabarlar soni ancha kamayadi, biroq aniqlik sezilarli ravishda oshadi. Ayniqsa, yirik datasetlarda model xavfsiz va xavfli kontentni ancha to‘g‘ri ajratadi. Maqola ijtimoiy tarmoqlarda xavfli ma’lumotlarni erta aniqlash tizimlarini ishlab chiqishda amaliy ahamiyatga ega.

Powered by OpenAIRE graph
Found an issue? Give us feedback