.png){kind=icon}
.png){kind=icon}
Return
Turkish and English disinformation detection using deep learning and large language models: Introducing the Dogrulamac dataset
.png){kind=icon}
PRE
AI
O
T
A
S
E
DOI：10.1016/j.eswa.2026.133847.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• Introduced Dogrulamac, a new Turkish disinformation dataset for multilingual NLP. • Evaluated LSTM, BERT, conventional ML algorithms, and Gemma-2 across unified English and Turkish corpora. • Gemma-2 achieved the highest accuracy, establishing strong baselines for multilingual disinformation detection.
Keywords:
Disinformation
Fake news detection
LLM
Gemma-2
BERT
LSTM
Journal
IF:
7.5
Papers:
2.9W
Citations:
10.2W
Organization
Cited Papers