Sentiment Analysis in Portuguese Restaurant Reviews: Application of Transformer Models in Edge Computing
This study focuses on improving sentiment analysis in restaurant reviews by leveraging transfer learning and transformer-based pre-trained models. This work evaluates the suitability of pre-trained deep learning models for analyzing Natural Language Processing tasks in Portuguese. It also explores t...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-01-01
|
| Series: | Electronics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-9292/13/3/589 |
| _version_ | 1797318847260262400 |
|---|---|
| author | Alexandre Branco Daniel Parada Marcos Silva Fábio Mendonça Sheikh Shanawaz Mostafa Fernando Morgado-Dias |
| author_facet | Alexandre Branco Daniel Parada Marcos Silva Fábio Mendonça Sheikh Shanawaz Mostafa Fernando Morgado-Dias |
| author_sort | Alexandre Branco |
| collection | DOAJ |
| description | This study focuses on improving sentiment analysis in restaurant reviews by leveraging transfer learning and transformer-based pre-trained models. This work evaluates the suitability of pre-trained deep learning models for analyzing Natural Language Processing tasks in Portuguese. It also explores the viability of utilizing edge devices for Natural Language Processing tasks, considering their computational limitations and resource constraints. Specifically, we employ bidirectional encoder representations from transformers and robustly optimized BERT approach, two state-of-the-art models, to build a sentiment review classifier. The classifier’s performance is evaluated using accuracy and area under the receiver operating characteristic curve as the primary metrics. Our results demonstrate that the classifier developed using ensemble techniques outperforms the baseline model (from 0.80 to 0.84) in accurately classifying restaurant review sentiments when three classes are considered (negative, neutral, and positive), reaching an accuracy and area under the receiver operating characteristic curve higher than 0.8 when examining a Zomato restaurant review dataset, provided for this work. This study seeks to create a model for the precise classification of Portuguese reviews into positive, negative, or neutral categories. The flexibility of deploying our model on affordable hardware platforms suggests its potential to enable real-time solutions. The deployment of the model on edge computing platforms improves accessibility in resource-constrained environments. |
| first_indexed | 2024-03-08T03:58:20Z |
| format | Article |
| id | doaj.art-16af3be195de4ad9be7d828cf7801f72 |
| institution | Directory Open Access Journal |
| issn | 2079-9292 |
| language | English |
| last_indexed | 2024-03-08T03:58:20Z |
| publishDate | 2024-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Electronics |
| spelling | doaj.art-16af3be195de4ad9be7d828cf7801f722024-02-09T15:10:45ZengMDPI AGElectronics2079-92922024-01-0113358910.3390/electronics13030589Sentiment Analysis in Portuguese Restaurant Reviews: Application of Transformer Models in Edge ComputingAlexandre Branco0Daniel Parada1Marcos Silva2Fábio Mendonça3Sheikh Shanawaz Mostafa4Fernando Morgado-Dias5Faculty of Exact Sciences and Engineering, University of Madeira, 9000-082 Funchal, PortugalFaculty of Exact Sciences and Engineering, University of Madeira, 9000-082 Funchal, PortugalFaculty of Exact Sciences and Engineering, University of Madeira, 9000-082 Funchal, PortugalFaculty of Exact Sciences and Engineering, University of Madeira, 9000-082 Funchal, PortugalInteractive Technologies Institute (ITI/LARSyS and ARDITI), 9020-105 Funchal, PortugalFaculty of Exact Sciences and Engineering, University of Madeira, 9000-082 Funchal, PortugalThis study focuses on improving sentiment analysis in restaurant reviews by leveraging transfer learning and transformer-based pre-trained models. This work evaluates the suitability of pre-trained deep learning models for analyzing Natural Language Processing tasks in Portuguese. It also explores the viability of utilizing edge devices for Natural Language Processing tasks, considering their computational limitations and resource constraints. Specifically, we employ bidirectional encoder representations from transformers and robustly optimized BERT approach, two state-of-the-art models, to build a sentiment review classifier. The classifier’s performance is evaluated using accuracy and area under the receiver operating characteristic curve as the primary metrics. Our results demonstrate that the classifier developed using ensemble techniques outperforms the baseline model (from 0.80 to 0.84) in accurately classifying restaurant review sentiments when three classes are considered (negative, neutral, and positive), reaching an accuracy and area under the receiver operating characteristic curve higher than 0.8 when examining a Zomato restaurant review dataset, provided for this work. This study seeks to create a model for the precise classification of Portuguese reviews into positive, negative, or neutral categories. The flexibility of deploying our model on affordable hardware platforms suggests its potential to enable real-time solutions. The deployment of the model on edge computing platforms improves accessibility in resource-constrained environments.https://www.mdpi.com/2079-9292/13/3/589sentiment analysisnatural language processingPortuguese languageedge computingBERTtransformers |
| spellingShingle | Alexandre Branco Daniel Parada Marcos Silva Fábio Mendonça Sheikh Shanawaz Mostafa Fernando Morgado-Dias Sentiment Analysis in Portuguese Restaurant Reviews: Application of Transformer Models in Edge Computing Electronics sentiment analysis natural language processing Portuguese language edge computing BERT transformers |
| title | Sentiment Analysis in Portuguese Restaurant Reviews: Application of Transformer Models in Edge Computing |
| title_full | Sentiment Analysis in Portuguese Restaurant Reviews: Application of Transformer Models in Edge Computing |
| title_fullStr | Sentiment Analysis in Portuguese Restaurant Reviews: Application of Transformer Models in Edge Computing |
| title_full_unstemmed | Sentiment Analysis in Portuguese Restaurant Reviews: Application of Transformer Models in Edge Computing |
| title_short | Sentiment Analysis in Portuguese Restaurant Reviews: Application of Transformer Models in Edge Computing |
| title_sort | sentiment analysis in portuguese restaurant reviews application of transformer models in edge computing |
| topic | sentiment analysis natural language processing Portuguese language edge computing BERT transformers |
| url | https://www.mdpi.com/2079-9292/13/3/589 |
| work_keys_str_mv | AT alexandrebranco sentimentanalysisinportugueserestaurantreviewsapplicationoftransformermodelsinedgecomputing AT danielparada sentimentanalysisinportugueserestaurantreviewsapplicationoftransformermodelsinedgecomputing AT marcossilva sentimentanalysisinportugueserestaurantreviewsapplicationoftransformermodelsinedgecomputing AT fabiomendonca sentimentanalysisinportugueserestaurantreviewsapplicationoftransformermodelsinedgecomputing AT sheikhshanawazmostafa sentimentanalysisinportugueserestaurantreviewsapplicationoftransformermodelsinedgecomputing AT fernandomorgadodias sentimentanalysisinportugueserestaurantreviewsapplicationoftransformermodelsinedgecomputing |