Abstract

We communicate, post different comments, communicating with different people in Social media. Different people of the world posted their views on COVID-19 during the pandemic. In this study we analysed the posted comments on social media. Analysis of the comment in social media is called sentiment analysis. We performed sentiment analysis on content from social media platforms, classifying it into either positive or negative categories. For this task, we proposed a different hybrid model. We used deep learning and genetic algorithm. GA algorithm and Stacked LSTM gave 95% positive sentiment. This model helps the health administrators in the world to make proper decisions to fight upcoming pandemic.

Keywords: Sentiment analysis, bidirectional LSTM, SimpleRNN, stacked LSTM, genetic algorithms (GA)

INTRODUCTION Currently, we are occupied with social networking platforms. We share our comments, opinions and emotions on social media. Different people have formed groups on social media. Like-minded people form a group called homophily [1]. Different comments and opinions are needed for social network statistical analysis. Social network perception is leading a key role for marketing or statistical analysis [2]. Diverse methods exist for sentiment analysis. The accuracy of the hybrid method is better than other models [3]. Various educational tools are available on social networking sites. These tools are used for learning purposes.

Keyworde: Sentiment analysis, bidirectional LSTM, SimpleRNN, stacked LSTM, genetic algorithms (GA)

Full Text PDF

Refrences:

1. Jana RK, Maity S, Maiti S. An Empirical Study of Sentiment and Behavioural Analysis using
Homophily Effect in Social Network. In 2022 IEEE 6th International Conference on Intelligent
Computing and Control Systems (ICICCS). 2022; 1508–1515.
2. Ahmed C, ElKorany A, ElSayed E. Prediction of customer’s perception in social networks by
integrating sentiment analysis and machine learning. J Intell Inf Syst. 2022; 60(6): 1–23.
3. Jana RK, Maity S. An Accuracy based Comparative Study on Different Techniques and challenges
for Sentiment Analysis. Pervasive Computing and Social Networking: Proceedings of ICPCSN
2022; 601–619.
4. Basu B. Analyzing the perception of social networking sites as a learning tool among university
students: Case study of a business school in India. International Journal of Educational and
Pedagogical Sciences. 2017 Jun 1; 11(7): 1697–703.
5. Katoch S, Chauhan SS, Kumar V. A review on genetic algorithm: past, present, and future.
Multimed Tools Appl. 2021; 80(4): 8091–8126.
6. Sharma M. Role and working of genetic algorithm in computer science. International Journal of
Computer Applications and Information Technology (IJCAIT). 2013; 2(1): 27–32.
7. Kaur P, Chaudhury A. A Review on the Genetic Optimization of Big Data Sentiment Analysis. Int
J Eng Res Technol. 2022; 10(04): 23–28.
8. Hasan M. Genetic algorithm and its application to big data analysis. Int J Sci Eng Res. 2014; 5(1):
1991–1996.
9. Chadha MP. Classification rules and genetic algorithm in data mining. Glob J Comput Sci Technol.
2012; 12(C15): 51–54.
10. Ephzibah EP. Cost effective approach on feature selection using genetic algorithms and LS-SVM
classifier. IJCA Special Issue on Evolutionary Computation for Optimization Techniques, ECOT.
2010; 3(1): 16–20.
11. Ferreira L, Dosciatti M, Nievola J, Paraiso EC. Using a genetic algorithm approach to study the
impact of imbalanced corpora in sentiment analysis. In The 28th International Flairs Conference.
2015 Apr; 163–168.
12. Misha Jain, Verma BK. Sentiment Analysis with Vector Feature Extraction and Classification of
Social Media Dataset. International Journal of Engineering Research in Computer Science and
Engineering (IJERCSE). 2017; 4(9): 89–95.
13. Das S, Kolya AK, Das D. Optimizing Social Media Data Using Genetic Algorithm. In
Metaheuristic Approaches to Portfolio Optimization. 2019; 126–153. IGI Global.
14. Indrayuni E, Nurhadi A. Optimizing Genetic Algorithms for Sentiment Analysis of Apple Product
Reviews Using SVM. Sinkron: jurnal dan penelitian teknik informatika. 2020; 4(2): 172–178.
15. Shrivastava K, Kumar S. A sentiment analysis system for the hindi language by integrating gated
recurrent unit with genetic algorithm. Int Arab J Inf Technol. 2020; 17(6): 954–964.
16. Ernawati S, Wati R, Nuris N, Marita LS, Yulia ER. Comparison of Naïve Bayes Algorithm with
Genetic Algorithm and Particle Swarm Optimization as Feature Selection for Sentiment Analysis
Review of Digital Learning Application. In J Phys: Conf Ser. 2020 Nov 1; 1641(1): 012040. IOP
Publishing.
17. Tao Y, He Z, Zhang Y. Analysis of public sentiment tendency in COVID-19 period based on GABiLSTM. In Proceedings of the 8th International Conference on Computing and Artificial
Intelligence. 2022 Mar 18; 193–199.
18. Anam MK. Sentiment Analysis of Online Lectures using KNearest Neighbors based on Feature
Selection. Jurnal Nasional Pendidikan Teknik Informatika (JANAPATI). 2022; 11(3): 216–225.
19. Siji George CG. Genetic Algorithm Based Hybrid Model Of Convolutional Neural Network And
Random Forest Classifier For Sentiment Classification. Turkish Journal of Computer and
Mathematics Education (TURCOMAT). 2021 Apr 11; 12(2): 3216–23.
20. Alsaleh D, Larabi-Marie-Sainte S. Arabic text classification using convolutional neural network
and genetic algorithms. IEEE Access. 2021 Jun 23; 9: 91670–85.
21. Osmani A, Bagherzadeh Mohasefi J. Weighted Joint Sentiment-Topic Model for Sentiment
Analysis Compared to ALGA: Adaptive Lexicon Learning Using Genetic Algorithm. Comput Intell
Neurosci. 2022 Jul 31; 2022(4): 1–35.
22. Merlin Md, Kumar DV. Perceptive genetic algorithm-based wolf inspired classifier for big
sentiment data analysis. J Theor Appl Inf Technol. 2022 Aug 31; 100(16): 5021–5031.
23. Wahono H, Riana D. Prediksi Calon Pendonor Darah Potensial Dengan Algoritma Naïve Bayes,
K-Nearest Neighbors dan Decision Tree C4. 5. JURIKOM (Jurnal Riset Komputer). 2020 Feb 15;
7(1): 7–14.
24. Sharma DK, Singh B, Agarwal S, Pachauri N, Alhussan AA, Abdallah HA. Sarcasm Detection over
Social Media Platforms Using Hybrid Ensemble Model with Fuzzy Logic. Electronics. 2023 Feb
13; 12(4): 937.