Fake news detection using an ensemble learning model based on Self-Adaptive Harmony Search algorithms

•The appropriate features of news are analyzed for training models.•The ensemble learning model for fake news detection is proposed in the paper.•The weights of the ensemble learning model are optimized in the paper.•The cross-domain intractability issue is investigated in the paper. In general, the...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Expert systems with applications Ročník 159; s. 113584
Hlavní autoři: Huang, Yin-Fu, Chen, Po-Hong
Médium: Journal Article
Jazyk:angličtina
Vydáno: New York Elsevier Ltd 30.11.2020
Elsevier BV
Témata:
Accuracy
Adaptive algorithms
Deep learning
Domains
Ensemble learning
Fake news
Harmony search algorithm
Machine learning
Natural language processing
News
Search algorithms
Deep learning
Natural language processing
Fake news
Harmony search algorithm
ISSN:0957-4174, 1873-6793
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:•The appropriate features of news are analyzed for training models.•The ensemble learning model for fake news detection is proposed in the paper.•The weights of the ensemble learning model are optimized in the paper.•The cross-domain intractability issue is investigated in the paper. In general, the features of fake news are almost the same as those of real news, so it is not easy to identify them. In this paper, we propose a fake news detection system using a deep learning model. First, news articles are preprocessed and analyzed based on different training models. Then, an ensemble learning model combining four different models called embedding LSTM, depth LSTM, LIWC CNN, and N-gram CNN is proposed for fake news detection. Besides, to achieve higher accuracy in fake news detection, the optimized weights of the ensemble learning model are determined using the Self-Adaptive Harmony Search (SAHS) algorithm. In the experiments, we verify that the proposed model is superior to the state-of-the-art methods, with the highest accuracy of 99.4%. Furthermore, we also investigate the cross-domain intractability issue and achieve the highest accuracy of 72.3%. Finally, we believe there is still room for improving the ensemble learning model in addressing the cross-domain intractability issue.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0957-4174
1873-6793
DOI:10.1016/j.eswa.2020.113584