A novel ensemble model for detecting fake news

Nissrine Bensouda, Sanaa El Fkihi, Rdouan Faizi


Due the growing proliferation of fake news over the past couple of years, ourobjective in this paper is to propose an ensemble model for the automatic classification of article news as being either real or fake. For this purpose, we optfor a blending technique that combines three models, namely bidirectional longshort-term memory (Bi-LSTM), stochastic gradient descent classifier and ridgeclassifier. The implementation of the proposed model (i.e. BI-LSR) on realworld datasets, has shown outstanding results. In fact, it achieved an accuracyscore of 99.16%. Accordingly, this ensemble learning has proven to do performbetter than individual conventional machine learning and deep learning modelsas well as many ensemble learning approaches cited in the literature.


Bagging; Blending; Boosting; Deep learning; Ensemble learning; Fake news; Machine learning

Full Text:


DOI: http://doi.org/10.11591/ijai.v13.i1.pp1160-1171


  • There are currently no refbacks.

Creative Commons License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

IAES International Journal of Artificial Intelligence (IJ-AI)
ISSN/e-ISSN 2089-4872/2252-8938 
This journal is published by the Institute of Advanced Engineering and Science (IAES) in collaboration with Intelektual Pustaka Media Utama (IPMU).

View IJAI Stats