An Improved Grey Wolf Optimization Algorithm for Enhancing Two-Pass Opinion Mining Classifier using Patient Reviews
DOI:
https://doi.org/10.61841/b8ef6195Keywords:
Opinion mining, drugs review, prediction, Two Pass Classifier, neural Network, SVM, modified Grey wolf optimization, modified TF-IDF, Patient users, PharmacyAbstract
The Sentiment analysis on various product reviews is a fascinating area of natural language processing and web text mining. Our Objective is to analyze the effect of an artificial neural network based method for drug based opinion classification. In the research that has done so far on sentiment analysis, ANNs have been considered rarely. In this work feed forward neural network architecture has been studied for sentiment classification. When back-propagation learning algorithms are used to train neural networks, they are typically slow and higher learning rates are needed. The selection of an appropriate learning rate is a complex issue. Proper learning rate is necessary to overcome the problem connected with back-propagation algorithms. More effort need to be put forth in the training of a neural network due to its nonlinear nature .Also identifying the unknown best set of main controlling parameters (weights) is a task where a quicker learning rate will cause unsteady learning. At the same time, a slower learning rate causes a disproportionately longer training time. It is quite demanding to discover an easy method for decide on the learning rate. Forgetting the optimal solution, Usually flawless weight connections are not formed by the back-propagation learning algorithm In this study, a Grey Wolf Optimizer algorithm was revised. For optimizing the weight of a neural network, this modified version was applied to the two pass opinion classifier.. When NN is weight optimized by IGWO, our Two Pass classifier is found to perform better and yields higher accuracy in classification. Accordingly, in my previous research, an efficient two-pass classifier system for patient opinion mining to analyze drugs satisfaction is proposed. Then, the selected features are given to optimal two-pass classifier. The two-pass classifier is a combination of support vector machine (SVM) and neural network (NN). Here, the weight value of (SVM-NN) classifier is optimally chosen with the help of improved gray wolf optimization (IGWO) algorithm. Finally, in the classification stage, we attain an opinion of corresponding drugs. The performance of proposed methodology is evaluated in terms of precision, recall and F-measure.
Downloads
References
1. B. Liu, Sentiment analysis and opinion mining, Synthesis Lectures on Human Language Technologies 5, 1–167: 2012.
2. B. O’Connor, R. Balasubramanyan, B. Routledge, N. Smith, From tweets to polls: Linking text sentiment to public opinion time series, in: Proceedings of the 4th International AAAI Conference on Web and Social Media, pp. 122–129, 2010.
3. N. Chambers, V. Bowen, E. Genco, X. Tian, E. Young, G. Harihara, E. Yang, Identifying political sentiment between nation states with social media, in: Proceedings of the Conference on Empirical Methods in Natural Language Processing, pp. 65–75, 2015.
4. C. Nopp, A. Hanbury, Detecting risks in the banking system by sentiment analysis, in: Proceedings of the Conference on Empirical Methods in Natural Language Processing, pp. 591–600, 2015.
5. E. Cambria, B. White, Jumping nlp curves: A review of natural language processing research [review article], IEEE Computational Intelligence Magazine 9, 48–57, 2014.
6. B. Khaleghi, A. Khamis, F. O. Karray, S. N. Razavi, Multisensor data fusion: A review of the state-of-the-art, Information Fusion 14, 28–44, 2013.
7. Kang, Mangi, JaelimAhn, and Kichun Lee. "Opinion mining using ensemble text hidden Markov models for text classification." Expert Systems with Applications 94: 218-227, 2018.
8. S. Manochandarand and M. Punniyamoorthy, "Scaling Feature Selection Method for Enhancing the Classification Performance of Support Vector Machines in Text Mining", journal of Computers & Industrial Engineering, 2018
9. RachanaNaik and Abhishek Raghuvanshi2, "Hybrid news recommendation system using tf-idf and associative calculus", International Journal of Scientific Development and Research, vol.2, no.3, 2017
10. Harnani Mat Zin, Norwati Mustapha, Masrah Azrifah Azmi Murad and Nurfadhlina Bt Mohd Sharef, "Term Weighting Scheme Effect in Sentiment Analysis of Online Movie Reviews", Journal of Computational and Theoretical Nanoscience, vol. 24, no. 2, pp.933-937, 2018
11. Plaza-del-Arco, Flor Miriam, M. Teresa Martín-Valdivia, Salud María Jiménez, M. Dolores Molina-González, and Eugenio Martínez-Cámara. "COPOS: corpus of patient opinions in spanish. application of sentiment analysis techniques." Procesamiento del Lenguaje Natural 57 (2016): 83-90.
12. Cambria, Erik, Thomas Mazzocco, and Amir Hussain. "Application of multi-dimensional scaling and artificial neural networks for biologically inspired opinion mining." Biologically Inspired Cognitive Architectures 4 (2013): 41-53.
13. Gopalakrishnan, Vinodhini, and Chandrasekaran Ramaswamy. "Patient opinion mining to analyze drugs satisfaction using supervised learning." Journal of applied research and technology 15, no. 4 (2017): 311-319.
14. Sabuj, Mir Shahriar, Zakia Afrin, and KM Azharul Hasan. "Opinion mining using support vector machine with web based diverse data." In International Conference on Pattern Recognition and Machine Intelligence,
pp. 673-678. Springer, Cham, 2017.
15. Go, Alec, Richa Bhayani, and Lei Huang. "Twitter sentiment classification using distant supervision." CS224N Project Report, Stanford 1, no. 12 (2009): 2009.
16. Vassiliou, Charalampos, Dimitris Stamoulis, Drakoulis Martakos, and Sotiris Athanassopoulos. "A recommender system framework combining neural networks & collaborative filtering." In Proceedings of the 5th WSEAS international conference on Instrumentation, measurement, circuits and systems, pp. 285-290. World Scientific and Engineering Academy and Society (WSEAS), 2006.
17. Das, Bijoyan, and Sarit Chakraborty. "An Improved Text Sentiment Classification Model Using TF-IDF and Next Word Negation." arXiv preprint arXiv:1806.06407 (2018).
18. HUSH D.R., HORNE B.G. Progress in supervised neural networks. IEEE Signal Processing Magazine. 1993, 10(1), pp. 8−39, doi: 10.1109/79.180705.
19. ZHANG N. An online gradient method with momentum for two-layer feed forward neural networks. Applied Mathematics and Computation. 2009, 212(2), pp. 488−498, doi: 10.1016/ j.amc.2009.02.038.
20. NG S.C., CHEUNG C.C., LEUNG S.H., LUK A. Fast convergence for back propagation network with magnified gradient function. IEEE Joint Conference on Neural Networks, Portland, OR, USA. 2003, 3, pp. 1903−1908, doi: 10.1109/ijcnn.2003.1223698.
21. Mosavi MR, Khishe M, Ghamgosar A. Classification of sonar data set using neural network trained by Gray Wolf Optimization. Neural Network World. 2016 Jul 1; 26(4):393.
22. Gidado, Abubakar, Korawinwich Boonpisuttinant, Suthamas Kanjanawongwanich, and . "Anti-cancer and Anti-Oxidative Activities of Nigerian Traditional Medicinal Plants/Recipes." Journal of Complementary Medicine Research 10 (2019), 200-211. doi:10.5455/jcmr.20190731050619
23. Patil, V., Patil, H., Shah, K., Vasani, J., Shetty, P.Diastolic dysfunction in asymptomatic type 2 diabetes mellitus with normal systolic function(2011) Journal of Cardiovascular Disease Research, 2 (4), pp. 213-222. DOI: 10.4103/0975-3583.89805
Downloads
Published
Issue
Section
License
This work is licensed under a Creative Commons Attribution 4.0 International License.
You are free to:
- Share — copy and redistribute the material in any medium or format for any purpose, even commercially.
- Adapt — remix, transform, and build upon the material for any purpose, even commercially.
- The licensor cannot revoke these freedoms as long as you follow the license terms.
Under the following terms:
- Attribution — You must give appropriate credit , provide a link to the license, and indicate if changes were made . You may do so in any reasonable manner, but not in any way that suggests the licensor endorses you or your use.
- No additional restrictions — You may not apply legal terms or technological measures that legally restrict others from doing anything the license permits.
Notices:
You do not have to comply with the license for elements of the material in the public domain or where your use is permitted by an applicable exception or limitation .
No warranties are given. The license may not give you all of the permissions necessary for your intended use. For example, other rights such as publicity, privacy, or moral rights may limit how you use the material.
