RoBERTaEns: Deep Bidirectional Encoder Ensemble Model for Fact Verification
The application of the bidirectional encoder model to detect fake news has been widely applied because of its ability to provide factual verification with good results. Good fact verification requires the most optimal model and has the best evaluation to make news readers trust the reliable and accu...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-03-01
|
| Series: | Big Data and Cognitive Computing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2504-2289/6/2/33 |
| _version_ | 1797489987097198592 |
|---|---|
| author | Muchammad Naseer Jauzak Hussaini Windiatmaja Muhamad Asvial Riri Fitri Sari |
| author_facet | Muchammad Naseer Jauzak Hussaini Windiatmaja Muhamad Asvial Riri Fitri Sari |
| author_sort | Muchammad Naseer |
| collection | DOAJ |
| description | The application of the bidirectional encoder model to detect fake news has been widely applied because of its ability to provide factual verification with good results. Good fact verification requires the most optimal model and has the best evaluation to make news readers trust the reliable and accurate verification results. In this study, we evaluated the application of a homogeneous ensemble (HE) on RoBERTa to improve the accuracy of a model. We improve the HE method using a bagging ensemble from three types of RoBERTa models. Then, each prediction is combined to build a new model called RoBERTaEns. The FEVER dataset is used to train and test our model. The experimental results showed that the proposed method, RoBERTaEns, obtained a higher accuracy value with an F1-Score of 84.2% compared to the other RoBERTa models. In addition, RoBERTaEns has a smaller margin of error compared to the other models. Thus, it proves that the application of the HE functions increases the accuracy of a model and produces better values in handling various types of fact input in each fold. |
| first_indexed | 2024-03-10T00:24:32Z |
| format | Article |
| id | doaj.art-2e4a2746f79549529f096fccdc701c44 |
| institution | Directory Open Access Journal |
| issn | 2504-2289 |
| language | English |
| last_indexed | 2024-03-10T00:24:32Z |
| publishDate | 2022-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Big Data and Cognitive Computing |
| spelling | doaj.art-2e4a2746f79549529f096fccdc701c442023-11-23T15:35:57ZengMDPI AGBig Data and Cognitive Computing2504-22892022-03-01623310.3390/bdcc6020033RoBERTaEns: Deep Bidirectional Encoder Ensemble Model for Fact VerificationMuchammad Naseer0Jauzak Hussaini Windiatmaja1Muhamad Asvial2Riri Fitri Sari3Department of Electrical Engineering, Faculty of Engineering, Universitas Indonesia, Depok 16424, IndonesiaDepartment of Electrical Engineering, Faculty of Engineering, Universitas Indonesia, Depok 16424, IndonesiaDepartment of Electrical Engineering, Faculty of Engineering, Universitas Indonesia, Depok 16424, IndonesiaDepartment of Electrical Engineering, Faculty of Engineering, Universitas Indonesia, Depok 16424, IndonesiaThe application of the bidirectional encoder model to detect fake news has been widely applied because of its ability to provide factual verification with good results. Good fact verification requires the most optimal model and has the best evaluation to make news readers trust the reliable and accurate verification results. In this study, we evaluated the application of a homogeneous ensemble (HE) on RoBERTa to improve the accuracy of a model. We improve the HE method using a bagging ensemble from three types of RoBERTa models. Then, each prediction is combined to build a new model called RoBERTaEns. The FEVER dataset is used to train and test our model. The experimental results showed that the proposed method, RoBERTaEns, obtained a higher accuracy value with an F1-Score of 84.2% compared to the other RoBERTa models. In addition, RoBERTaEns has a smaller margin of error compared to the other models. Thus, it proves that the application of the HE functions increases the accuracy of a model and produces better values in handling various types of fact input in each fold.https://www.mdpi.com/2504-2289/6/2/33fact verificationfake newsFEVER datasethomogeneous ensembleRoBERTaRoBERTaEns |
| spellingShingle | Muchammad Naseer Jauzak Hussaini Windiatmaja Muhamad Asvial Riri Fitri Sari RoBERTaEns: Deep Bidirectional Encoder Ensemble Model for Fact Verification Big Data and Cognitive Computing fact verification fake news FEVER dataset homogeneous ensemble RoBERTa RoBERTaEns |
| title | RoBERTaEns: Deep Bidirectional Encoder Ensemble Model for Fact Verification |
| title_full | RoBERTaEns: Deep Bidirectional Encoder Ensemble Model for Fact Verification |
| title_fullStr | RoBERTaEns: Deep Bidirectional Encoder Ensemble Model for Fact Verification |
| title_full_unstemmed | RoBERTaEns: Deep Bidirectional Encoder Ensemble Model for Fact Verification |
| title_short | RoBERTaEns: Deep Bidirectional Encoder Ensemble Model for Fact Verification |
| title_sort | robertaens deep bidirectional encoder ensemble model for fact verification |
| topic | fact verification fake news FEVER dataset homogeneous ensemble RoBERTa RoBERTaEns |
| url | https://www.mdpi.com/2504-2289/6/2/33 |
| work_keys_str_mv | AT muchammadnaseer robertaensdeepbidirectionalencoderensemblemodelforfactverification AT jauzakhussainiwindiatmaja robertaensdeepbidirectionalencoderensemblemodelforfactverification AT muhamadasvial robertaensdeepbidirectionalencoderensemblemodelforfactverification AT ririfitrisari robertaensdeepbidirectionalencoderensemblemodelforfactverification |