The BERT Uncased and LSTM Multiclass Classification Model for Traffic Violation Text Classification
The increasing amount of internet content makes it difficult for users to find information using the search function. This problem is overcome by classifying news based on its context to avoid material that has many interpretations. This research combines the Uncased model BiDirectional Encoder Repr...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Udayana University, Institute for Research and Community Services
2025-01-01
|
| Series: | Lontar Komputer |
| Online Access: | https://ojs.unud.ac.id/index.php/lontar/article/view/116705 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832575541985673216 |
|---|---|
| author | Komang Ayu Triana Indah I Ketut Gede Darma Putra I Made Sudarma Rukmi Sari Hartati Minho Jo |
| author_facet | Komang Ayu Triana Indah I Ketut Gede Darma Putra I Made Sudarma Rukmi Sari Hartati Minho Jo |
| author_sort | Komang Ayu Triana Indah |
| collection | DOAJ |
| description | The increasing amount of internet content makes it difficult for users to find information using the search function. This problem is overcome by classifying news based on its context to avoid material that has many interpretations. This research combines the Uncased model BiDirectional Encoder Representations from Transformer (BERT) with other models to create a text classification model. Long Short-Term Memory (LSTM) architecture trains a model to categorize news articles about traffic violations. Data was collected through the crawling method from the online media application API through unmodified and modified datasets. The BERT Uncased-LSTM model with the best hyperparameter combination scenario of batch size 16, learning rate 2e-5, and average pooling obtained Precision, Recall, and F1 values of 97.25%, 96.90%, and 98.10%, respectively. The research results show that the test value on the unmodified dataset is higher than on the modified dataset because the selection of words that have high information value in the modified dataset makes it difficult for the model to understand the context in text classification. |
| format | Article |
| id | doaj-art-b4fc12c575424ecab039b52a5706a02c |
| institution | Kabale University |
| issn | 2088-1541 2541-5832 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Udayana University, Institute for Research and Community Services |
| record_format | Article |
| series | Lontar Komputer |
| spelling | doaj-art-b4fc12c575424ecab039b52a5706a02c2025-01-31T23:56:26ZengUdayana University, Institute for Research and Community ServicesLontar Komputer2088-15412541-58322025-01-01150211212310.24843/LKJITI.2024.v15.i02.p04116705The BERT Uncased and LSTM Multiclass Classification Model for Traffic Violation Text ClassificationKomang Ayu Triana Indah0I Ketut Gede Darma Putra1I Made Sudarma2Rukmi Sari Hartati3Minho Jo4Politeknik Negeri Balinformation Technology Department Udayana UniversityInformation Technology Department Udayana UniversityElectrical Engineering Department Udayana UniversityDepartment of Computer and Information Science, Korea UniversityThe increasing amount of internet content makes it difficult for users to find information using the search function. This problem is overcome by classifying news based on its context to avoid material that has many interpretations. This research combines the Uncased model BiDirectional Encoder Representations from Transformer (BERT) with other models to create a text classification model. Long Short-Term Memory (LSTM) architecture trains a model to categorize news articles about traffic violations. Data was collected through the crawling method from the online media application API through unmodified and modified datasets. The BERT Uncased-LSTM model with the best hyperparameter combination scenario of batch size 16, learning rate 2e-5, and average pooling obtained Precision, Recall, and F1 values of 97.25%, 96.90%, and 98.10%, respectively. The research results show that the test value on the unmodified dataset is higher than on the modified dataset because the selection of words that have high information value in the modified dataset makes it difficult for the model to understand the context in text classification.https://ojs.unud.ac.id/index.php/lontar/article/view/116705 |
| spellingShingle | Komang Ayu Triana Indah I Ketut Gede Darma Putra I Made Sudarma Rukmi Sari Hartati Minho Jo The BERT Uncased and LSTM Multiclass Classification Model for Traffic Violation Text Classification Lontar Komputer |
| title | The BERT Uncased and LSTM Multiclass Classification Model for Traffic Violation Text Classification |
| title_full | The BERT Uncased and LSTM Multiclass Classification Model for Traffic Violation Text Classification |
| title_fullStr | The BERT Uncased and LSTM Multiclass Classification Model for Traffic Violation Text Classification |
| title_full_unstemmed | The BERT Uncased and LSTM Multiclass Classification Model for Traffic Violation Text Classification |
| title_short | The BERT Uncased and LSTM Multiclass Classification Model for Traffic Violation Text Classification |
| title_sort | bert uncased and lstm multiclass classification model for traffic violation text classification |
| url | https://ojs.unud.ac.id/index.php/lontar/article/view/116705 |
| work_keys_str_mv | AT komangayutrianaindah thebertuncasedandlstmmulticlassclassificationmodelfortrafficviolationtextclassification AT iketutgededarmaputra thebertuncasedandlstmmulticlassclassificationmodelfortrafficviolationtextclassification AT imadesudarma thebertuncasedandlstmmulticlassclassificationmodelfortrafficviolationtextclassification AT rukmisarihartati thebertuncasedandlstmmulticlassclassificationmodelfortrafficviolationtextclassification AT minhojo thebertuncasedandlstmmulticlassclassificationmodelfortrafficviolationtextclassification AT komangayutrianaindah bertuncasedandlstmmulticlassclassificationmodelfortrafficviolationtextclassification AT iketutgededarmaputra bertuncasedandlstmmulticlassclassificationmodelfortrafficviolationtextclassification AT imadesudarma bertuncasedandlstmmulticlassclassificationmodelfortrafficviolationtextclassification AT rukmisarihartati bertuncasedandlstmmulticlassclassificationmodelfortrafficviolationtextclassification AT minhojo bertuncasedandlstmmulticlassclassificationmodelfortrafficviolationtextclassification |