Using BERT and ZFNet/ELM optimized by improved Orca optimization algorithm for sentiment analysis
Abstract Sentiment analysis, also known as opinion mining, is a computational technique used to evaluate emotions and opinions expressed in textual data. This method is a key aspect of Natural Language Processing (NLP) that focuses on extraction of patterns and significant features from big volumes...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-04-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-025-00223-y |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Abstract Sentiment analysis, also known as opinion mining, is a computational technique used to evaluate emotions and opinions expressed in textual data. This method is a key aspect of Natural Language Processing (NLP) that focuses on extraction of patterns and significant features from big volumes of text. This article explores the critical role of sentiment analysis in understanding audience reactions to movies through user-generated reviews. In doing so, Bidirectional Encoder Representations from Transformers (BERT) was utilized, since it takes into account the context of a word based on both its preceding and following words in a sentence. Of course, some preprocessing stages were done in order to enhance the quality of data and accomplish results with high efficacy. Then, the data were inserted into ZFNet/ELM, which was optimized by Improved Orca Optimization Algorithm (IOPA). It was represented by the results that the suggested model could gain the values of 96.24, 97.41, and 96.82 for precision, recall, and F1-score, respectively. The results of the suggested model were compared with the results of other models, and it was revealed that the suggested model perform better than all of them. The high results achieved by the model proved that this model could highly recognize the polarity of reviews and classify them. |
|---|---|
| ISSN: | 2045-2322 |