Qwen TextCNN and BERT models for enhanced multilabel news classification in mobile apps
Guardado en:
| Publicado en: | Scientific Reports (Nature Publisher Group) vol. 15, no. 1 (2025), p. 43787-43809 |
|---|---|
| Autor principal: | |
| Otros Autores: | , , |
| Publicado: |
Nature Publishing Group
|
| Materias: | |
| Acceso en línea: | Citation/Abstract Full Text Full Text - PDF |
| Etiquetas: |
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
MARC
| LEADER | 00000nab a2200000uu 4500 | ||
|---|---|---|---|
| 001 | 3283667401 | ||
| 003 | UK-CbPIL | ||
| 022 | |a 2045-2322 | ||
| 024 | 7 | |a 10.1038/s41598-025-27497-6 |2 doi | |
| 035 | |a 3283667401 | ||
| 045 | 2 | |b d20250101 |b d20251231 | |
| 084 | |a 274855 |2 nlm | ||
| 100 | 1 | |a Yuan, Dawei |u School of Computer Science, Guangdong University of Science and Technology, 523083, Dongguan, China (ROR: https://ror.org/054fysp39) (GRID: grid.472284.f); Beijing Bitauto Information Technology Co., Ltd, 100102, Beijing, China | |
| 245 | 1 | |a Qwen TextCNN and BERT models for enhanced multilabel news classification in mobile apps | |
| 260 | |b Nature Publishing Group |c 2025 | ||
| 513 | |a Journal Article | ||
| 520 | 3 | |a Mobile news classification systems face significant challenges due to their large scale and complexity. In this paper, we perform a comprehensive comparative study between traditional classification models, such as TextCNN and BERT based models and Large Language Models (LLMs), for the purpose of multi-label news categorization in mobile apps about the Chinese mobile news application. We evaluated the performance of conventional techniques, including a BERT model, along with Qwen models that have been tuned with instruction and fine-tuned using the LoRA technique, to optimize their effectiveness while preserving classification accuracy. Our experimental results show that BERT models perform best for multi-label classification with balanced datasets, while textCNN performs better for binary classification tasks. Our results also reveal that the LSTM and MLP classifiers consistently achieve the highest accuracy with text instruction prompts, while random embeddings achieve competitive accuracy. Furthermore, despite the low macro F1 scores due to class imbalance, consistent relative performance confirms the validity of our analysis. Our research reveals crucial information about the classification of automotive news, highlighting the importance of weighing technical prowess against deployment constraints when choosing model architectures. | |
| 653 | |a Machine learning | ||
| 653 | |a Text categorization | ||
| 653 | |a Accuracy | ||
| 653 | |a Classification systems | ||
| 653 | |a Deep learning | ||
| 653 | |a Models | ||
| 653 | |a Recommender systems | ||
| 653 | |a Comparative studies | ||
| 653 | |a Neural networks | ||
| 653 | |a Classification | ||
| 653 | |a Batch processing | ||
| 653 | |a Large language models | ||
| 653 | |a Chinese languages | ||
| 653 | |a Resource management | ||
| 653 | |a Efficiency | ||
| 653 | |a Semantics | ||
| 653 | |a Economic | ||
| 700 | 1 | |a Liang, Guojun |u School of Information Technology, Halmstad University, 30118, Halmstad, Sweden (ROR: https://ror.org/03h0qfp10) (GRID: grid.73638.39) (ISNI: 0000 0000 9852 2034) | |
| 700 | 1 | |a Liu, Bin |u School of Computer Science and Technology, Jilin University, 130012, Changchun, China (ROR: https://ror.org/00js3aw79) (GRID: grid.64924.3d) (ISNI: 0000 0004 1760 5735) | |
| 700 | 1 | |a Liu, Suping |u School of Computer Science, Guangdong University of Science and Technology, 523083, Dongguan, China (ROR: https://ror.org/054fysp39) (GRID: grid.472284.f) | |
| 773 | 0 | |t Scientific Reports (Nature Publisher Group) |g vol. 15, no. 1 (2025), p. 43787-43809 | |
| 786 | 0 | |d ProQuest |t Science Database | |
| 856 | 4 | 1 | |3 Citation/Abstract |u https://www.proquest.com/docview/3283667401/abstract/embedded/7BTGNMKEMPT1V9Z2?source=fedsrch |
| 856 | 4 | 0 | |3 Full Text |u https://www.proquest.com/docview/3283667401/fulltext/embedded/7BTGNMKEMPT1V9Z2?source=fedsrch |
| 856 | 4 | 0 | |3 Full Text - PDF |u https://www.proquest.com/docview/3283667401/fulltextPDF/embedded/7BTGNMKEMPT1V9Z2?source=fedsrch |