Integrated deep learning paradigm for document-based sentiment analysis
An integrated deep learning paradigm for the analysis of document-based sentiments is presented in this article. Generally, sentiment analysis has enormous applications in the real world, particularly in e-commerce and/or cloud computing-oriented businesses. Integrated deep learning paradigms for do...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2023-07-01
|
| Series: | Journal of King Saud University: Computer and Information Sciences |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S1319157823001325 |
| _version_ | 1827871863249829888 |
|---|---|
| author | Peter Atandoh Fengli Zhang Daniel Adu-Gyamfi Paul H. Atandoh Raphael Elimeli Nuhoho |
| author_facet | Peter Atandoh Fengli Zhang Daniel Adu-Gyamfi Paul H. Atandoh Raphael Elimeli Nuhoho |
| author_sort | Peter Atandoh |
| collection | DOAJ |
| description | An integrated deep learning paradigm for the analysis of document-based sentiments is presented in this article. Generally, sentiment analysis has enormous applications in the real world, particularly in e-commerce and/or cloud computing-oriented businesses. Integrated deep learning paradigms for document-based sentiment analysis seek to efficiently categorize the polarity of contextual sentiments into positive, negative, and neutral to aid organizations in making informed decisions. Nonetheless, the sparsity of text and disambiguation of natural languages make it relatively difficult for existing methods to provide precise identification and extraction when subjected to document-based data. As a result, this study introduces BERT-MultiLayered Convolutional Neural Network (B-MLCNN) as a computationally viable integrated deep learning paradigm. The B-MLCNN considers the overall textual review as a single document and classifies the available sentiments. First, the BERT pre-trained language model handles the feature vector representation and captures any global features. Further, the multi-layered convolutional neural network (MLCNN) with different kernel dimensions handles feature extraction. A softmax function produces classification results. The experimental setup with B-MLCNN based on IMDB movie reviews, 2002 movie reviews, 2004 movie reviews, and Amazon review datasets achieved accuracies of 95%, 88%, 95%, and 95% respectively, which promises to be efficient to deploy in practical applications. |
| first_indexed | 2024-03-12T16:16:01Z |
| format | Article |
| id | doaj.art-f45fdff0ed5747699835b8dceecf8c00 |
| institution | Directory Open Access Journal |
| issn | 1319-1578 |
| language | English |
| last_indexed | 2024-03-12T16:16:01Z |
| publishDate | 2023-07-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Journal of King Saud University: Computer and Information Sciences |
| spelling | doaj.art-f45fdff0ed5747699835b8dceecf8c002023-08-09T04:32:00ZengElsevierJournal of King Saud University: Computer and Information Sciences1319-15782023-07-01357101578Integrated deep learning paradigm for document-based sentiment analysisPeter Atandoh0Fengli Zhang1Daniel Adu-Gyamfi2Paul H. Atandoh3Raphael Elimeli Nuhoho4School of Information and Software Engineering, University of Electronic Science and Technology of China, North Jianshe Road, Chengdu 610054, Sichuan, China; Corresponding author.School of Information and Software Engineering, University of Electronic Science and Technology of China, North Jianshe Road, Chengdu 610054, Sichuan, ChinaDepartment of Cyber Security and Computer Engineering Technology, C. K. Tedam University of Technology and Applied Sciences, Navrongo, UE/R, GhanaDepartment of Mathematics, Mercer University, 1501 Mercer University Drive, Macon, GA 31207, USASchool of Computer Science and Engineering, University of Electronic Science and Technology of China, No. 2006, Xiyuan Avenue, Chengdu 610054, Sichuan, ChinaAn integrated deep learning paradigm for the analysis of document-based sentiments is presented in this article. Generally, sentiment analysis has enormous applications in the real world, particularly in e-commerce and/or cloud computing-oriented businesses. Integrated deep learning paradigms for document-based sentiment analysis seek to efficiently categorize the polarity of contextual sentiments into positive, negative, and neutral to aid organizations in making informed decisions. Nonetheless, the sparsity of text and disambiguation of natural languages make it relatively difficult for existing methods to provide precise identification and extraction when subjected to document-based data. As a result, this study introduces BERT-MultiLayered Convolutional Neural Network (B-MLCNN) as a computationally viable integrated deep learning paradigm. The B-MLCNN considers the overall textual review as a single document and classifies the available sentiments. First, the BERT pre-trained language model handles the feature vector representation and captures any global features. Further, the multi-layered convolutional neural network (MLCNN) with different kernel dimensions handles feature extraction. A softmax function produces classification results. The experimental setup with B-MLCNN based on IMDB movie reviews, 2002 movie reviews, 2004 movie reviews, and Amazon review datasets achieved accuracies of 95%, 88%, 95%, and 95% respectively, which promises to be efficient to deploy in practical applications.http://www.sciencedirect.com/science/article/pii/S1319157823001325Sentiment AnalysisDeep LearningBidirectional Encoder from TransformersConvolutional Neural Network |
| spellingShingle | Peter Atandoh Fengli Zhang Daniel Adu-Gyamfi Paul H. Atandoh Raphael Elimeli Nuhoho Integrated deep learning paradigm for document-based sentiment analysis Journal of King Saud University: Computer and Information Sciences Sentiment Analysis Deep Learning Bidirectional Encoder from Transformers Convolutional Neural Network |
| title | Integrated deep learning paradigm for document-based sentiment analysis |
| title_full | Integrated deep learning paradigm for document-based sentiment analysis |
| title_fullStr | Integrated deep learning paradigm for document-based sentiment analysis |
| title_full_unstemmed | Integrated deep learning paradigm for document-based sentiment analysis |
| title_short | Integrated deep learning paradigm for document-based sentiment analysis |
| title_sort | integrated deep learning paradigm for document based sentiment analysis |
| topic | Sentiment Analysis Deep Learning Bidirectional Encoder from Transformers Convolutional Neural Network |
| url | http://www.sciencedirect.com/science/article/pii/S1319157823001325 |
| work_keys_str_mv | AT peteratandoh integrateddeeplearningparadigmfordocumentbasedsentimentanalysis AT fenglizhang integrateddeeplearningparadigmfordocumentbasedsentimentanalysis AT danieladugyamfi integrateddeeplearningparadigmfordocumentbasedsentimentanalysis AT paulhatandoh integrateddeeplearningparadigmfordocumentbasedsentimentanalysis AT raphaelelimelinuhoho integrateddeeplearningparadigmfordocumentbasedsentimentanalysis |