CHUQUR O‘RGANISH ARXITEKTURALARI ASOSIDA O‘ZBEK TILIDAGI SOXTA XABARLARNI ANIQLASH ALGORITMINI ISHLAB CHIQISH
DOI:
https://doi.org/10.5281/zenodo.22257604Abstract
Ushbu maqolada o‘zbek tilidagi soxta xabarlarni avtomatik aniqlash uchun chuqur o‘rganish arxitekturalariga
asoslangan yondashuv ishlab chiqilgan. Taklif etilgan sxema matnni dastlabki qayta ishlash va normallashtirish,
tokenizatsiya va vektorlashtirish, CNN, LSTM/BiLSTM hamda transformer (mBERT/UzBERT) modellari yordamida xususiyatlarni
ajratish, ularni birlashtirish va Dense + Softmax qatlami asosida binar tasniflash bosqichlarini o‘z ichiga oladi.
O‘zbek tilining agglutinativ tuzilishi, lotin va kirill yozuvlarining parallel qo‘llanishi, apostrof variantlari, kod almashinuvi
hamda ijtimoiy tarmoqlarga xos noformal yozuvlar model yaratishdagi asosiy murakkabliklar sifatida ko‘rib chiqilgan.
Mavjud yondashuvlarning o‘qitish ma’lumotlaridagi tarafkashlik, kontekstni yetarli darajada anglamaslik, masshtablilik
va tushuntiriluvchanlik bilan bog‘liq cheklovlari tahlil qilingan. Katta va xilma-xil ma’lumotlar to‘plamlaridan foydalanish,
transformer va gibrid modellarni takomillashtirish, sentiment va stilometrik tahlilni qo‘llash, real vaqt rejimida yangilanishlarni
ta’minlash, shuningdek, manba ishonchliligi va foydalanuvchi xatti-harakatlarini hisobga olish bo‘yicha takliflar ishlab
chiqilgan.
Keywords
soxta xabarlar, o‘zbek tili, chuqur o‘rganish, CNN, LSTM, BiLSTM, transformer, mBERT, UzBERT, tabiiy tilni qayta ishlash, binar tasniflash.References
Kaliyar R.K., Goswami A., Narang P. FakeBERT: Fake News Detection in Social Media with a BERT-Based Deep
Learning Approach // Multimedia Tools and Applications. – 2021. – Vol. 80. – P. 11765–11788.
Uzoqov L.M., Muhammadiyeva D.K. Automatic Dataset Augmentation Techniques for Fake News Detection Models //
Universum: Технические науки. – Москва, 2025. – Вып. 7(136). – Ч. 3. – С. 40–44.
Jwa H., Oh D., Park K., Kang J.M., Lim H. exBAKE: Automatic Fake News Detection Model Based on Bidirectional
Encoder Representations from Transformers (BERT) // Applied Sciences. – 2019. – Vol. 9, № 19. – Article 4062.
Farokhian M., Rafe V., Veisi H. Fake News Detection Using Parallel BERT Deep Neural Networks // arXiv preprint
arXiv:2204.04793. – 2022.
Uzoqov L.M. O‘zbek tilidagi axborotlar bilan ishlashda uchraydigan lingvistik muammolar // “Raqamli infratuzilmani
joriy etish: muammo va innovatsion yechimlar” mavzusidagi Respublika ilmiy-amaliy anjuman materiallari. – Toshkent,
– B. 240–243.
Essa E., Alkhairy I., Shaban K. Fake News Detection Based on a Hybrid BERT and LightGBM Model // IEEE Access.
– 2023. – Vol. 11. – P. 43730–43745.
Goldani M.H., Safabakhsh R., Momtazi S. Convolutional Neural Network with Margin Loss for Fake News Detection //
Information Processing & Management. – 2021. – Vol. 58, № 1.
Dun Y., Tu K., Chen C., Hou C., Yuan X. KAN: Knowledge-Aware Attention Network for Fake News Detection //
Proceedings of the AAAI Conference on Artificial Intelligence. – 2021. – Vol. 35, № 1. – P. 81–89.
Mayank M., Sharma S., Sharma R. DEAP-FAKED: Knowledge Graph Based Approach for Fake News Detection //
arXiv preprint arXiv:2107.10648. – 2021.
Koloski B., Perdih T.S., Robnik-Šikonja M., Pollak S., Škrlj B. Knowledge Graph Informed Fake News Classification via
Heterogeneous Representation Ensembles // Neurocomputing. – 2022. – Vol. 496. – P. 208–226.
Phan H.T., Nguyen N.T., Hwang D. Fake News Detection: A Survey of Graph Neural Network Methods // Expert
Systems with Applications. – 2023. – Vol. 223.
Gong S., Sinnott R.O., Qi J., Paris C. Fake News Detection Through Graph-Based Neural Networks: A Survey // arXiv
preprint arXiv:2307.12639. – 2023.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 MUHANDISLIK VA IQTISODIYOT
This work is licensed under a Creative Commons Attribution 4.0 International License.
