Automatic Fake News Detection for Romanian Online News
This paper proposes a supervised machine learning system to detect fake news in online sources published in Romanian. Additionally, this work presents a comparison of the obtained results by using recurrent neural networks based on long short-term memory and gated recurrent unit cells, a convolution...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-03-01
|
| Series: | Information |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2078-2489/13/3/151 |
| _version_ | 1797470700945014784 |
|---|---|
| author | Marius Cristian Buzea Stefan Trausan-Matu Traian Rebedea |
| author_facet | Marius Cristian Buzea Stefan Trausan-Matu Traian Rebedea |
| author_sort | Marius Cristian Buzea |
| collection | DOAJ |
| description | This paper proposes a supervised machine learning system to detect fake news in online sources published in Romanian. Additionally, this work presents a comparison of the obtained results by using recurrent neural networks based on long short-term memory and gated recurrent unit cells, a convolutional neural network, and a Bidirectional Encoder Representations from Transformers (BERT) model, namely RoBERT, a pre-trained Romanian BERT model. The deep learning architectures are compared with the results achieved by two classical classification algorithms: Naïve Bayes and Support Vector Machine. The proposed approach is based on a Romanian news corpus containing 25,841 true news items and 13,064 fake news items. The best result is over 98.20%, achieved by the convolutional neural network, which outperforms the standard classification methods and the BERT models. Moreover, based on irony detection and sentiment analysis systems, additional details are revealed about the irony phenomenon and sentiment analysis field which are used to tackle fake news challenges. |
| first_indexed | 2024-03-09T19:39:47Z |
| format | Article |
| id | doaj.art-c7cf59ab0b7844bf80fcd2412a79f943 |
| institution | Directory Open Access Journal |
| issn | 2078-2489 |
| language | English |
| last_indexed | 2024-03-09T19:39:47Z |
| publishDate | 2022-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Information |
| spelling | doaj.art-c7cf59ab0b7844bf80fcd2412a79f9432023-11-24T01:42:08ZengMDPI AGInformation2078-24892022-03-0113315110.3390/info13030151Automatic Fake News Detection for Romanian Online NewsMarius Cristian Buzea0Stefan Trausan-Matu1Traian Rebedea2Department of Computer Science and Engineering, University Politehnica of Bucharest, 060042 Bucharest, RomaniaDepartment of Computer Science and Engineering, University Politehnica of Bucharest, 060042 Bucharest, RomaniaDepartment of Computer Science and Engineering, University Politehnica of Bucharest, 060042 Bucharest, RomaniaThis paper proposes a supervised machine learning system to detect fake news in online sources published in Romanian. Additionally, this work presents a comparison of the obtained results by using recurrent neural networks based on long short-term memory and gated recurrent unit cells, a convolutional neural network, and a Bidirectional Encoder Representations from Transformers (BERT) model, namely RoBERT, a pre-trained Romanian BERT model. The deep learning architectures are compared with the results achieved by two classical classification algorithms: Naïve Bayes and Support Vector Machine. The proposed approach is based on a Romanian news corpus containing 25,841 true news items and 13,064 fake news items. The best result is over 98.20%, achieved by the convolutional neural network, which outperforms the standard classification methods and the BERT models. Moreover, based on irony detection and sentiment analysis systems, additional details are revealed about the irony phenomenon and sentiment analysis field which are used to tackle fake news challenges.https://www.mdpi.com/2078-2489/13/3/151fake newsconvolutional neural networkmachine learningdeep learningRoBERT |
| spellingShingle | Marius Cristian Buzea Stefan Trausan-Matu Traian Rebedea Automatic Fake News Detection for Romanian Online News Information fake news convolutional neural network machine learning deep learning RoBERT |
| title | Automatic Fake News Detection for Romanian Online News |
| title_full | Automatic Fake News Detection for Romanian Online News |
| title_fullStr | Automatic Fake News Detection for Romanian Online News |
| title_full_unstemmed | Automatic Fake News Detection for Romanian Online News |
| title_short | Automatic Fake News Detection for Romanian Online News |
| title_sort | automatic fake news detection for romanian online news |
| topic | fake news convolutional neural network machine learning deep learning RoBERT |
| url | https://www.mdpi.com/2078-2489/13/3/151 |
| work_keys_str_mv | AT mariuscristianbuzea automaticfakenewsdetectionforromanianonlinenews AT stefantrausanmatu automaticfakenewsdetectionforromanianonlinenews AT traianrebedea automaticfakenewsdetectionforromanianonlinenews |