Journals / Muş Alparslan Üniversitesi Fen Bilimleri Dergisi / 2026 / Cilt: 14 Sayı: 1

Analyzing News and Detecting Fake News Using Artificial Intelligence Methods

Yapay Zekâ Yöntemleriyle Haber Analizinin ve Sahte Haber Tespitinin Gerçekleştirilmesi

Sercan Yalçın(ADIYAMAN ÜNİVERSİTESİ, MÜHENDİSLİK FAKÜLTESİ, BİLGİSAYAR MÜHENDİSLİĞİ BÖLÜMÜ)0000-0003-1420-2490
Pages
152–161
Publication Date
2026-06-27
🏛️Bibliographic metadata and full text access for this article are provided via DergiPark.
DergiPark Record ↗
✨

AI Summary & Key Takeaways

AI Insight
⚡ TL;DR(Too Long; Didn't Read)

Accuracy rates of 90% and higher were achieved in news classification tasks, demonstrating the proposed model's ability to accurately distinguish between real and fake news.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:This research develops a robust and accurate AI-powered system capable of analyzing news articles and detecting fake news.
📊
Key Findings & Data:Model performance was evaluated using Python language and libraries, employing relevant metrics such as accuracy, precision, recall, and F1 score.
💡
Conclusion & Impact:Accuracy rates of 90% and higher were achieved in news classification tasks, demonstrating the proposed model's ability to accurately distinguish between real and fake news.
🔬Design:Modeling & Simulation
📍Scope:Comprehensive Sample
⚙️Variables:Derin öğrenme · Kodlayıcılar ve kodçözücüler · Sahte haber tespiti

Abstract

This research develops a robust and accurate AI-powered system capable of analyzing news articles and detecting fake news. The proposed study utilizes a hybrid approach based on advanced deep learning techniques, employing both Long Short Term Memory (LSTM) and Transformer-based models, to develop this system. A comprehensive dataset of news articles, including both "real" and "fake" news, was collected from BBC and Anadolu Agency news channels and pre-processed to ensure data quality and consistency. Furthermore, a web interface was developed using the Flask web framework, guaranteeing usability and adaptability. Model performance was evaluated using Python language and libraries, employing relevant metrics such as accuracy, precision, recall, and F1 score. Accuracy rates of 90% and higher were achieved in news classification tasks, demonstrating the proposed model's ability to accurately distinguish between real and fake news.

Özet

Bu araştırmada, haber makalelerini analiz edebilen ve sahte haberleri tespit edebilen sağlam ve doğru bir yapay zekâ destekli sistem geliştirilmiştir. Önerilen çalışmada bu sistemi geliştirebilmek için Uzun Kısa Süreli Bellek ve Transformer tabanlı model olmak üzere gelişmiş derin öğrenme tekniklerine dayalı hibrit bir yöntem önerilmiştir. Bu çalışmada, hem “gerçek” hem de “sahte” haberler dâhil olmak üzere kapsamlı bir haber makaleleri BBC, Anadolu Ajansı haber kanallarından veri kümesi toplanmış ve veri kalitesini ve tutarlılığını sağlamak için bu veriler ön işleme tabi tutulmuştur. Bu çalışmada ayrıca, kullanışlılığını ve uyarlanabilirliğini garanti altına alan Flask web framework'ü kullanılarak bir web arayüzü geliştirilmiştir. Modellerin performansı, doğruluk, kesinlik, geri çağırma ve F1 puanı gibi ilgili ölçütler kullanılarak Python dili ve kütüphaneleri kullanılarak değerlendirilmiştir. Haber sınıflandırma görevlerinde %90 ve daha yüksek bir doğruluk oranına ulaşılmış ve önerilen model gerçek ve sahte haberleri doğru bir şekilde ayırt etme yeteneği göstermiştir.

🔖

Cite This Article

Değirmenciler, M. F., Yalçın, S., Yıldırım, M. (2026). Analyzing News and Detecting Fake News Using Artificial Intelligence Methods. Muş Alparslan Üniversitesi Fen Bilimleri Dergisi, Cilt: 14 Sayı: 1, 152–161. https://doi.org/10.18586/msufbd.1903167

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (23)

  1. Tajrian T., Tasnim T., Sadia N., Mim T.S., Ansar S., Rahman A.S.M.F. Machine Learning and Hybrid Based Fake News Detection on Social Media, 11th International Conference on Information and Communication Technology (ICoICT), 1-6, 2023.
  2. Kozik R., Choraś M., Karas M., Kozik J. Fake news detection using transformer models, IEEE Access, 11:1 1234-1245, 2023.
  3. Ahmed H., Traore I., Saad S. Detection of Online Fake News Using N-Gram Analysis and Machine Learning, International Conference on Intelligent, Secure, and Dependable Systems in Distributed and Cloud Computing, 127-138, 2024.
  4. Ayetiran E.F., Adesina A.O., Agbele K.K. Deep learning for fake news detection: a review, Journal of Big Data, 11:1 1-35, 2024.
  5. Manzoor S.I., Singla J., Sharma N. Fake News Detection Using Machine Learning: A Systematic Review, IEEE Access, 8:1 1-15, 2020.
  6. Qi P., Cao J., Yang T., Guo J., Li J. Mining Adversarial Patterns for Multi-Domain Fake News Detection, IEEE Access, 9:1 1-12, 2021.
  7. Alghamdi A., Al-Ghamdi A.S., Al-Mulla A. Fake News Detection Using Deep Learning: A Survey, IEEE Access, 10:1 1-20, 2022.
  8. Hu L., Wei S., Zhao Z., Wu B. Deep Learning for Fake News Detection: A Comprehensive Survey, IEEE Access, 10:1 1-25, 2022.
  9. Ozbay F.A., Alatas B. Fake news detection within digital media using machine learning models, IEEE Conference, 1-8, 2020.
  10. Mertoğlu M., Yanık S., Aydın G. A New Approach for Fake News Detection Using Linguistic Features and Word Embeddings, IEEE Access, 9:1 1-14, 2021.
  11. Buzea M.C., Trausan-Matu S., Rebedea T. Fake News Detection in Romanian Using Machine Learning and Deep Learning, IEEE Access, 10:1 1-18, 2022.
  12. Kishwar S., Zafar B. A Comprehensive Dataset and AI Models for Fake News Detection in Pakistan, IEEE Access, 11:1 1-16, 2023.
  13. Genç A., Surer E. ClickbaitTR: A Dataset and Analysis for Turkish Clickbait Detection, IEEE Access, 11:1 1-15, 2023.
  14. Güler S., Gündüz H. SOSYALAN: A New Dataset for Turkish Fake News Detection on Social Media, IEEE Access, 11:1 1-14, 2023.
  15. Ağduk M., Karasoy O., Öztürk M. Multi-language News Classification Using Machine Learning, IEEE Access, 11:1 1-12, 2023.
  16. Koru S., Uluyol C. TR_FaRe_News: A Turkish Fake News Dataset and Deep Learning Models, IEEE Access, 12:1 1-16, 2024.
  17. Alguttar A., Al-Azzam N., Al-Zubi M. The Impact of Preprocessing Techniques on Fake News Detection, IEEE Access, 12:1 1-15, 2024.
  18. Yalçin S., Herdem M.S. Prediction and Analysis of Weather Parameters with Global Horizontal Solar Irradiance Using LSTM-CNN Based Deep Learning Technique, Bilecik Şeyh Edebali Üniversitesi Fen Bilimleri Dergisi, 9:1 350-365, 2022.
  19. Yalçın S., Eşit M., Çoban Ö. A new deep learning method for meteorological drought estimation based-on standard precipitation evapotranspiration index, Engineering Applications of Artificial Intelligence, 124:1 106550, 2023.
  20. Alnabrisi M., Saad S. Transformer-Based Models for Fake News Detection: A Review, IEEE Access, 12:1 1-18, 2024.
  21. Praseed A., Rodrigues J., Thilagam P.S. Hindi fake news detection using transformer ensembles, Engineering Applications of Artificial Intelligence, 119:1 105731, 2023.
  22. Choudhary A., Arora A. Linguistic Feature Based Fake News Detection Using Transformer Models, IEEE Access, 12:1 1-15, 2024.
  23. Balderas X., Ning B., He K. EfficientTransformer: A Dynamic Anomaly Detection Model for Industrial Control Networks, IEEE Access, 13:1 37931-37945, 2025.