Islam, Md Shofiqul and Kabir, Muhammad Nomani and Ngahzaifa, Ab Ghani and Kamal Zuhairi, Zamli and Nor Saradatul Akmar, Zulkifli and Rahman, Md Mustafizur and Moni, Mohammad Ali (2024) "Challenges and future in deep learning for sentiment analysis: a comprehensive review and a proposed novel hybrid approach". Artificial Intelligence Review, 57 (62). pp. 1-79. ISSN 0269-2821. (Published)
![[img]](http://umpir.ump.edu.my/style/images/fileicons/other.png) |
Pdf
Challenges and future in deep learning for sentiment analysis.pdf Restricted to Repository staff only Download (5MB) | Request a copy |
|
|
Pdf
Challenges and future in deep learning for sentiment analysis_A comprehensive review and a proposed novel hybrid approach_ABS.pdf Download (276kB) | Preview |
Abstract
Social media is used to categorise products or services, but analysing vast comments is time-consuming. Researchers use sentiment analysis via natural language processing, evaluating methods and results conventionally through literature reviews and assessments. However, our approach diverges by offering a thorough analytical perspective with critical analysis, research findings, identified gaps, limitations, challenges and future prospects specific to deep learning-based sentiment analysis in recent times. Furthermore, we provide in-depth investigation into sentiment analysis, categorizing prevalent data, pre-processing methods, text representations, learning models, and applications. We conduct a thorough evaluation of recent advances in deep learning architectures, assessing their pros and cons. Additionally, we offer a meticulous analysis of deep learning methodologies, integrating insights on applied tools, strengths, weaknesses, performance results, research gaps, and a detailed feature-based examination. Furthermore, we present in a thorough discussion of the challenges, drawbacks, and factors contributing to the successful enhancement of accuracy within the realm of sentiment analysis. A critical comparative analysis of our article clearly shows that capsule-based RNN approaches give the best results with an accuracy of 98.02% which is the CNN or RNN-based models. We implemented various advanced deep-learning models across four benchmarks to identify the top performers. Additionally, we introduced the innovative CRDC (Capsule with Deep CNN and Bi structured RNN) model, which demonstrated superior performance compared to other methods. Our proposed approach achieved remarkable accuracy across different databases: IMDB (88.15%), Toxic (98.28%), CrowdFlower (92.34%), and ER (95.48%). Hence, this method holds promise for automated sentiment analysis and potential deployment.
| Item Type: | Article |
|---|---|
| Additional Information: | Indexed by Scopus |
| Uncontrolled Keywords: | Attention; Capsule network; Classifiers; Deep learning; Neural network (NN); Sentiment analysis (SA) |
| Subjects: | Q Science > QA Mathematics > QA75 Electronic computers. Computer science Q Science > QA Mathematics > QA76 Computer software T Technology > T Technology (General) T Technology > TA Engineering (General). Civil engineering (General) T Technology > TJ Mechanical engineering and machinery |
| Faculty/Division: | Institute of Postgraduate Studies Faculty of Computing Faculty of Mechanical and Automotive Engineering Technology |
| Depositing User: | Mr Muhamad Firdaus Janih@Jaini |
| Date Deposited: | 31 Jul 2024 00:43 |
| Last Modified: | 31 Jul 2024 00:43 |
| URI: | http://umpir.ump.edu.my/id/eprint/41421 |
| Download Statistic: | View Download Statistics |
Actions (login required)
 |
View Item |