Sentiment Analysis on Twitter Data using Modified Neuro Fuzzy Algorithm
Keywords:
Twitter data, MPCA, K-fold validation, MFNA, kaggleAbstract
The utilization of Social Media (SM) has been widely adopted by individuals as a convenient and formal means of communication. Individuals engage in the act of composing or disseminating textual content, as well as appending visual media such as images and videos, on various social networking platforms such as Twitter, Facebook, and other analogous digital platforms. Sentiment analysis (SA), also known as Opinion Mining (OM), is a prevalent task in dialogue preparation that seeks to uncover the underlying sentiments expressed in texts pertaining to diverse topics. The collection of data from social media platforms can be effectively leveraged to address various objectives, including the marketplace prediction, product suggestion, and analysis of reviewer sentiment. Managing unstructured data found on social media poses a significant challenge. Deep learning algorithms are a suitable solution for addressing the challenges associated with handling this type of data. Therefore, this study aims to conduct SA on a dataset collected from Twitter. In the proposed study, the initial step involves preprocessing the input Twitter data. Following the preprocessing stage, the words are organized in a structured format utilizing HDFS (Hadoop Distributed File System). The process of Map Reducing is then applied to eliminate duplicate words and establish the structured format. The features are derived from the Proposed Modified Principal Component Analysis (MPCA) method. In the final stage, the features are classified utilizing the Modified Fuzzy Neural Algorithm (MFNA) that has been proposed. The simulation results of the proposed method demonstrate superior performance in comparison to existing methods. Ultimately, the outcome was evaluated through the utilization of the K Fold Cross Validation technique. The aforementioned procedures are implemented in twitter data set publicly available in the Kaggle. The highest level of accuracy achieved is 96.984%, which is correlated with the sentiments of three classes positive, negative and neutral.
Downloads
References
J. Tao and X. Fang, “Toward multi-label sentiment analysis: A transfer learning based approach,” Journal of Big Data, vol. 7, no. 1, pp. 1–26, 2020.
M. Alam, J. F. Wang, C. Guangpei, L. V. Yunrong and Y. Chen, “Convolutional neural network for the semantic segmentation of remote sensing images,” Mobile Networks and Applications, vol. 26, no. 1, pp. 200–215, 2021.
Erick Odhiambo Omuya, George Okeyo and Michael Kimwele, “Sentiment analysis on social media tweets using dimensionality reduction and natural language processing”, Engineering Reports. 2023;5:e12579. wileyonlinelibrary.com/journal/eng2 1 of 14
https://doi.org/10.1002/eng2.12579.
Samreen Naeem, Wali KhanMashwani, Aqib Ali, M. Irfan Uddin, MarwanMahmoud, Farrukh Jamal, and Christophe Chesneau, “Machine Learning-based USD/PKR Exchange Rate Forecasting Using Sentiment Analysis of Twitter Data”, Computers,Materials & Communication, DOI:10.32604/cmc.2021.015872, 2021, vol.67, no.3.
Abdullah Alsaeedi and Mohammad Zubair Khan, “A Study on Sentiment Analysis Techniques of Twitter Data”, International Journal of Advanced Computer Science and Applications, Vol. 10, No. 2, 2019.
Farkhund Iqbal, Jahanzeb Maqbool Hashmi, Benjamin C. M. Fung, Rabia Batool, Asad Masood Khattak, Saiqa Aleem and Patrick C. K. Hung, “A Hybrid Framework for Sentiment Analysis Using Genetic Algorithm Based Feature Reduction”, IEEE Access, February 8, 2019, Digital Object Identifier 10.1109/ACCESS.2019.2892852.
Dharmendra Dang, Amit Bhagat and Dheeraj Kumar Dixit, “Sentiment Analysis on Social Media Using Genetic Algorithm with CNN”, Computers,Materials & Continua, DOI:10.32604/cmc.2022.02043, vol.70, no.3, 2022.
A. Insaf, A. Ouahabi, A. Benzaoui and A. T. Ahmed, “Past, present, and future of face recognition: A review,” Electronics, vol. 9, no. 8, pp. 1188, 2020.
G. Aaryan, V. Dengre, H. A. Kheruwala and M. Shah, “Comprehensive review of text-mining applications in finance,” Financial Innovation, vol. 6, no. 1, pp. 1–25, 2020.
Y. X. Yang, C. Wen, K. Xie, F. Q. Wen, G. Q. Sheng et al., “Face recognition using the SR-CNN model,” Sensors, vol. 18, no. 12, pp. 4237, 2018.
Prabakaran N S, “Efficient Natural Language Processing used for Twitter data based on Sentiment Analysis”, International Journal of Science & Engineering Development Research, ISSn:2455-2631, vol-4, issue 6, pg.no-368-380, june 2019.
Prabakaran N S, Dr. S.Karthick, “ A Hybrid Deep Learning Method for Twitter Data based on Sentiment Analysis”, ICTACT, 2023. (Paper under Review).
Benjamin Jackson, Mark Johnson, Andrea Ricci, Piotr Wiśniewski, Laura Martínez. Ethical Considerations in Machine Learning Applications for Decision Science. Kuwait Journal of Machine Learning, 2(4). Retrieved from http://kuwaitjournals.com/index.php/kjml/article/view/221
Dr. S. Praveen Chakkravarthy. (2020). Smart Monitoring of the Status of Driver Using the Dashboard Vehicle Camera. International Journal of New Practices in Management and Engineering, 9(01), 01 - 07. https://doi.org/10.17762/ijnpme.v9i01.81
Dhabliya, D. (2021). Delay-tolerant sensor network (DTN) implementation in cloud computing. Paper presented at the Journal of Physics: Conference Series, , 1979(1) doi:10.1088/1742-6596/1979/1/012031 Retrieved from www.scopus.com
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
All papers should be submitted electronically. All submitted manuscripts must be original work that is not under submission at another journal or under consideration for publication in another form, such as a monograph or chapter of a book. Authors of submitted papers are obligated not to submit their paper for publication elsewhere until an editorial decision is rendered on their submission. Further, authors of accepted papers are prohibited from publishing the results in other publications that appear before the paper is published in the Journal unless they receive approval for doing so from the Editor-In-Chief.
IJISAE open access articles are licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. This license lets the audience to give appropriate credit, provide a link to the license, and indicate if changes were made and if they remix, transform, or build upon the material, they must distribute contributions under the same license as the original.