Efficient sentiment analysis on demonetization in India with improved accuracy using ESVM (ensemble support vector machine) compared over ENB (ensemble naive bayes).
Saved in:
| Title: | Efficient sentiment analysis on demonetization in India with improved accuracy using ESVM (ensemble support vector machine) compared over ENB (ensemble naive bayes). |
|---|---|
| Authors: | Babu, M. Jeevan, Kesavan, R. |
| Source: | AIP Conference Proceedings; 2025, Vol. 3252 Issue 1, p1-7, 7p |
| Subject Terms: | SUPPORT vector machines, SENTIMENT analysis, DEEP learning, SAMPLE size (Statistics), ALGORITHMS |
| Abstract: | Using the online sentimental demonetization dataset and a variety of DL (Deep Learning) classifiers, such as Novel Ensemble Support Vector Machine, compared to Ensemble Naive Bayes, this study aims to improve the accuracy rate of sentiment examination on demonetization in India. The ESVM and ENB models were used to assess the sentimental dataset on demonetization. The proposed model was put into action using the Python computer language, and the online sentiment dataset on demonetization was utilized for research reasons. G power was used to select the sample size, with the goal of achieving 80% power in both groups. For this algorithm, a total of 20 samples were selected, with 40 individuals each sample. Calculated using G power 3.1 software, the pre-test power value was set at 0.80 with an alpha level of 0.05. We used a number of indicators to assess the suggested sentiment evaluation approach for India's demonetization. It was determined that the ENB classifier had an accuracy level of 91.12%, while the ESVM classifier had an accuracy level of 94.79%. It was determined that ESVM and ENB took exactly zero minutes and ninety-nine seconds, respectively, to process. The two models were compared using a T-test, and the results showed that ESVM and ENB were not significantly different from each other, with a P-value of 0.003 (P < 0.05) supporting this conclusion. In terms of online dataset sentiment analysis, the results show that the constructed Novel Ensemble SVM model outperformed the ENB classifier, according to the parameters of the proposed research process. [ABSTRACT FROM AUTHOR] |
| Copyright of AIP Conference Proceedings is the property of American Institute of Physics and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Database: | Complementary Index |
Nájsť tento článok vo Web of Science Be the first to leave a comment!