Low-Resource Language Processing Using Improved Deep Learning with Hunter–Prey Optimization Algorithm
Low-resource language (LRL) processing refers to the development of natural language processing (NLP) techniques and tools for languages with limited linguistic resources and data. These languages often lack well-annotated datasets and pre-training methods, making traditional approaches less effecti...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-10-01
|
| Series: | Mathematics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2227-7390/11/21/4493 |
| _version_ | 1797631606618324992 |
|---|---|
| author | Fahd N. Al-Wesabi Hala J. Alshahrani Azza Elneil Osman Elmouez Samir Abd Elhameed |
| author_facet | Fahd N. Al-Wesabi Hala J. Alshahrani Azza Elneil Osman Elmouez Samir Abd Elhameed |
| author_sort | Fahd N. Al-Wesabi |
| collection | DOAJ |
| description | Low-resource language (LRL) processing refers to the development of natural language processing (NLP) techniques and tools for languages with limited linguistic resources and data. These languages often lack well-annotated datasets and pre-training methods, making traditional approaches less effective. Sentiment analysis (SA), which involves identifying the emotional tone or sentiment expressed in text, poses unique challenges for LRLs due to the scarcity of labelled sentiment data and linguistic intricacies. NLP tasks like SA, powered by machine learning (ML) techniques, can generalize effectively when trained on suitable datasets. Recent advancements in computational power and parallelized graphical processing units have significantly increased the popularity of deep learning (DL) approaches built on artificial neural network (ANN) architectures. With this in mind, this manuscript describes the design of an LRL Processing technique that makes use of Improved Deep Learning with Hunter–Prey Optimization (LRLP-IDLHPO). The LRLP-IDLHPO technique enables the detection and classification of different kinds of sentiments present in LRL data. To accomplish this, the presented LRLP-IDLHPO technique initially pre-processes these data to improve their usability. Subsequently, the LRLP-IDLHPO approach applies the SentiBERT approach for word embedding purposes. For the sentiment classification process, the Element-Wise–Attention GRU network (EWAG-GRU) algorithm is used, which is an enhanced version of the recurrent neural network. The EWAG-GRU model is capable of processing temporal features and includes an attention strategy. Finally, the performance of the EWAG-GRU model can be boosted by adding the HPO algorithm for use in the hyperparameter tuning process. A widespread simulation analysis was performed to validate the superior results derived from using the LRLP-IDLHPO approach. The extensive results indicate the significant superiority of the performance of the LRLP-IDLHPO technique compared to the state-of-the-art approaches described in the literature. |
| first_indexed | 2024-03-11T11:25:51Z |
| format | Article |
| id | doaj.art-f298f2369bc34632ab043366502e7df5 |
| institution | Directory Open Access Journal |
| issn | 2227-7390 |
| language | English |
| last_indexed | 2024-03-11T11:25:51Z |
| publishDate | 2023-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Mathematics |
| spelling | doaj.art-f298f2369bc34632ab043366502e7df52023-11-10T15:08:04ZengMDPI AGMathematics2227-73902023-10-011121449310.3390/math11214493Low-Resource Language Processing Using Improved Deep Learning with Hunter–Prey Optimization AlgorithmFahd N. Al-Wesabi0Hala J. Alshahrani1Azza Elneil Osman2Elmouez Samir Abd Elhameed3Department of Computer Science, College of Science & Art at Mahayil, King Khalid University, Abha 62529, Saudi ArabiaDepartment of Applied Linguistics, College of Languages, Princess Nourah Bint Abdulrahman University, P.O. Box 84428, Riyadh 11671, Saudi ArabiaDepartment of Computer and Self Development, Preparatory Year Deanship, Prince Sattam Bin Abdulaziz University, Al-Kharj 16278, Saudi ArabiaDepartment of Computer Science, College of Post-Graduated Studies, Sudan University of Science and Technology, Khartoum 11111, SudanLow-resource language (LRL) processing refers to the development of natural language processing (NLP) techniques and tools for languages with limited linguistic resources and data. These languages often lack well-annotated datasets and pre-training methods, making traditional approaches less effective. Sentiment analysis (SA), which involves identifying the emotional tone or sentiment expressed in text, poses unique challenges for LRLs due to the scarcity of labelled sentiment data and linguistic intricacies. NLP tasks like SA, powered by machine learning (ML) techniques, can generalize effectively when trained on suitable datasets. Recent advancements in computational power and parallelized graphical processing units have significantly increased the popularity of deep learning (DL) approaches built on artificial neural network (ANN) architectures. With this in mind, this manuscript describes the design of an LRL Processing technique that makes use of Improved Deep Learning with Hunter–Prey Optimization (LRLP-IDLHPO). The LRLP-IDLHPO technique enables the detection and classification of different kinds of sentiments present in LRL data. To accomplish this, the presented LRLP-IDLHPO technique initially pre-processes these data to improve their usability. Subsequently, the LRLP-IDLHPO approach applies the SentiBERT approach for word embedding purposes. For the sentiment classification process, the Element-Wise–Attention GRU network (EWAG-GRU) algorithm is used, which is an enhanced version of the recurrent neural network. The EWAG-GRU model is capable of processing temporal features and includes an attention strategy. Finally, the performance of the EWAG-GRU model can be boosted by adding the HPO algorithm for use in the hyperparameter tuning process. A widespread simulation analysis was performed to validate the superior results derived from using the LRLP-IDLHPO approach. The extensive results indicate the significant superiority of the performance of the LRLP-IDLHPO technique compared to the state-of-the-art approaches described in the literature.https://www.mdpi.com/2227-7390/11/21/4493low-resource languagesnatural language processingdeep learningsentiment analysishunter–prey optimizer |
| spellingShingle | Fahd N. Al-Wesabi Hala J. Alshahrani Azza Elneil Osman Elmouez Samir Abd Elhameed Low-Resource Language Processing Using Improved Deep Learning with Hunter–Prey Optimization Algorithm Mathematics low-resource languages natural language processing deep learning sentiment analysis hunter–prey optimizer |
| title | Low-Resource Language Processing Using Improved Deep Learning with Hunter–Prey Optimization Algorithm |
| title_full | Low-Resource Language Processing Using Improved Deep Learning with Hunter–Prey Optimization Algorithm |
| title_fullStr | Low-Resource Language Processing Using Improved Deep Learning with Hunter–Prey Optimization Algorithm |
| title_full_unstemmed | Low-Resource Language Processing Using Improved Deep Learning with Hunter–Prey Optimization Algorithm |
| title_short | Low-Resource Language Processing Using Improved Deep Learning with Hunter–Prey Optimization Algorithm |
| title_sort | low resource language processing using improved deep learning with hunter prey optimization algorithm |
| topic | low-resource languages natural language processing deep learning sentiment analysis hunter–prey optimizer |
| url | https://www.mdpi.com/2227-7390/11/21/4493 |
| work_keys_str_mv | AT fahdnalwesabi lowresourcelanguageprocessingusingimproveddeeplearningwithhunterpreyoptimizationalgorithm AT halajalshahrani lowresourcelanguageprocessingusingimproveddeeplearningwithhunterpreyoptimizationalgorithm AT azzaelneilosman lowresourcelanguageprocessingusingimproveddeeplearningwithhunterpreyoptimizationalgorithm AT elmouezsamirabdelhameed lowresourcelanguageprocessingusingimproveddeeplearningwithhunterpreyoptimizationalgorithm |