Multidisciplinary classification for Indonesian scientific articles abstract using pre-trained BERT model
Scientific articles now have multidisciplinary content. These make it difficult for researchers to find out relevant information. Some submissions are irrelevant to the journal's discipline. Categorizing articles and assessing their relevance can aid researchers and journals. Existing research...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Universitas Ahmad Dahlan
2023-07-01
|
| Series: | IJAIN (International Journal of Advances in Intelligent Informatics) |
| Subjects: | |
| Online Access: | http://ijain.org/index.php/IJAIN/article/view/1051 |
| _version_ | 1827793600853835776 |
|---|---|
| author | Antonius Angga Kurniawan Sarifuddin Madenda Setia Wirawan Ruddy J. Suhatril |
| author_facet | Antonius Angga Kurniawan Sarifuddin Madenda Setia Wirawan Ruddy J. Suhatril |
| author_sort | Antonius Angga Kurniawan |
| collection | DOAJ |
| description | Scientific articles now have multidisciplinary content. These make it difficult for researchers to find out relevant information. Some submissions are irrelevant to the journal's discipline. Categorizing articles and assessing their relevance can aid researchers and journals. Existing research still focuses on single-category predictive outcomes. Therefore, this research takes a new approach by applying a multidisciplinary classification for Indonesian scientific article abstracts using a pre-trained BERT model, showing the relevance between each category in an abstract. The dataset used was 9,000 abstracts with 9 disciplinary categories. On the dataset, text preprocessing is performed. The classification model was built by combining the pre-trained BERT model with Artificial Neural Network. Fine-tuning the hyperparameters is done to determine the most optimal hyperparameter combination for the model. The hyperparameters consist of batch size, learning rate, number of epochs, and data ratio. The best hyperparameter combination is a learning rate of 1e-5, batch size 32, epochs 3, and data ratio 9:1, with a validation accuracy value of 90.8%. The confusion matrix results of the model are compared with the confusion matrix results by experts. In this case, the highest accuracy result obtained by the model is 99.56%. A software prototype used the most accurate model to classify new data, displaying the top two prediction probabilities and the dominant category. This research produces a model that can be used to solve Indonesian text classification-related problems. |
| first_indexed | 2024-03-11T18:21:47Z |
| format | Article |
| id | doaj.art-1d7137a6648841a68bf5badf12521862 |
| institution | Directory Open Access Journal |
| issn | 2442-6571 2548-3161 |
| language | English |
| last_indexed | 2024-03-11T18:21:47Z |
| publishDate | 2023-07-01 |
| publisher | Universitas Ahmad Dahlan |
| record_format | Article |
| series | IJAIN (International Journal of Advances in Intelligent Informatics) |
| spelling | doaj.art-1d7137a6648841a68bf5badf125218622023-10-15T04:42:26ZengUniversitas Ahmad DahlanIJAIN (International Journal of Advances in Intelligent Informatics)2442-65712548-31612023-07-019233134610.26555/ijain.v9i2.1051255Multidisciplinary classification for Indonesian scientific articles abstract using pre-trained BERT modelAntonius Angga Kurniawan0Sarifuddin Madenda1Setia Wirawan2Ruddy J. Suhatril3Universitas GunadarmaUniversitas GunadarmaUniversitas GunadarmaUniversitas GunadarmaScientific articles now have multidisciplinary content. These make it difficult for researchers to find out relevant information. Some submissions are irrelevant to the journal's discipline. Categorizing articles and assessing their relevance can aid researchers and journals. Existing research still focuses on single-category predictive outcomes. Therefore, this research takes a new approach by applying a multidisciplinary classification for Indonesian scientific article abstracts using a pre-trained BERT model, showing the relevance between each category in an abstract. The dataset used was 9,000 abstracts with 9 disciplinary categories. On the dataset, text preprocessing is performed. The classification model was built by combining the pre-trained BERT model with Artificial Neural Network. Fine-tuning the hyperparameters is done to determine the most optimal hyperparameter combination for the model. The hyperparameters consist of batch size, learning rate, number of epochs, and data ratio. The best hyperparameter combination is a learning rate of 1e-5, batch size 32, epochs 3, and data ratio 9:1, with a validation accuracy value of 90.8%. The confusion matrix results of the model are compared with the confusion matrix results by experts. In this case, the highest accuracy result obtained by the model is 99.56%. A software prototype used the most accurate model to classify new data, displaying the top two prediction probabilities and the dominant category. This research produces a model that can be used to solve Indonesian text classification-related problems.http://ijain.org/index.php/IJAIN/article/view/1051abstractbertclassificationhyperparameter-tuningmultidiciplinary |
| spellingShingle | Antonius Angga Kurniawan Sarifuddin Madenda Setia Wirawan Ruddy J. Suhatril Multidisciplinary classification for Indonesian scientific articles abstract using pre-trained BERT model IJAIN (International Journal of Advances in Intelligent Informatics) abstract bert classification hyperparameter-tuning multidiciplinary |
| title | Multidisciplinary classification for Indonesian scientific articles abstract using pre-trained BERT model |
| title_full | Multidisciplinary classification for Indonesian scientific articles abstract using pre-trained BERT model |
| title_fullStr | Multidisciplinary classification for Indonesian scientific articles abstract using pre-trained BERT model |
| title_full_unstemmed | Multidisciplinary classification for Indonesian scientific articles abstract using pre-trained BERT model |
| title_short | Multidisciplinary classification for Indonesian scientific articles abstract using pre-trained BERT model |
| title_sort | multidisciplinary classification for indonesian scientific articles abstract using pre trained bert model |
| topic | abstract bert classification hyperparameter-tuning multidiciplinary |
| url | http://ijain.org/index.php/IJAIN/article/view/1051 |
| work_keys_str_mv | AT antoniusanggakurniawan multidisciplinaryclassificationforindonesianscientificarticlesabstractusingpretrainedbertmodel AT sarifuddinmadenda multidisciplinaryclassificationforindonesianscientificarticlesabstractusingpretrainedbertmodel AT setiawirawan multidisciplinaryclassificationforindonesianscientificarticlesabstractusingpretrainedbertmodel AT ruddyjsuhatril multidisciplinaryclassificationforindonesianscientificarticlesabstractusingpretrainedbertmodel |