Sosyal Medyada Duygu Analizi: COVID-19 Sürecinde 5G Algısı

Year 2022, Volume: 15 Issue: 1, 55 - 68, 30.06.2022

Elçin Timur Çakmak , Ayşe Oğuzlar

https://doi.org/10.37093/ijsi.928685

Abstract

Bu çalışmada toplum için fırsatlar yaratacak yeni yetenekler getirmesi beklenen beşinci nesil hücresel ağlar (5G) ile COVID-19 aşısının dünya genelinde insanlar üzerinde oluşturduğu algının Duygu Analizi yöntemi ile ölçülmesi hedeflenmektedir. Bu amaçla, yaygın olarak kullanılan bir sosyal medya aracı olan Twitter’dan Ekim – Aralık 2020 tarihleri arasında 25642 adet tweet çekilmiş ve Python yazılımı aracılığı ile hesaplamalar yapılmıştır. Buna göre dünya genelinde Twitter üzerinden fikrini beyan eden kişilerin %36,4’ünün 5G ile COVID-19 aşısı hakkında pozitif algıya sahip olduğu görülmüştür. Tweet atan kişilerin %35,6’sının ise konuyla ilgili olarak pozitif ya da negatif görüşe sahip olmadığı ve %28’inin de negatif görüş bildirdiği sonucuna varılmıştır. Tüm tweetler için genel duygu skoru ortalaması 0,15 olarak bulunmuştur. Çalışmada ayrıca verilere makine öğrenmesi yöntemlerinden Sınıflandırma ve Regresyon Ağaçları (CART), Naïve Bayes (NB), k-En Yakın Komşuluk (KNN) ve Rastgele Orman (RF) algoritmaları uygulanmıştır. Elde edilen bulgulara göre sınıflandırmada en iyi sonuçları 0,7852 kesinlik (P) ve 0,7445 doğruluk (A) değerleri ile NB; 0,8209 duyarlılık (R) değeri ile KNN ve 0,7866 F-ölçütü (F) değeri ile RF algoritmaları vermiştir.

Keywords

5G, COVID-19, Duygu Analizi, Makine Öğrenmesi, Sınıflandırma Algoritmaları

Sentiment Analysis on Social Media: The 5G Perception During COVID-19 Process

Abstract

This study is aimed at measuring the perception created by the COVID-19 vaccines on people around the world using Sentiment Analysis – taking into account the fifth generation (5G) cellular networks, which are expected to bring new capabilities that will create opportunities for society. For this purpose, 25642 tweets were taken from Twitter between October and December 2020 and analyzed using Python software. Accordingly, 36.4% of people worldwide who expressed their opinions on Twitter have a positive perception of 5G and the COVID-19 vaccine, also 35.6% of the tweeters do not have a positive or negative view (neutral) has been observed. However, it was observed that 28% of the people expressed negative opinions. The overall sentiment score is 0.15. Also, in this study, Classification and Regression Trees (CART), Naïve Bayes (NB), k-Nearest Neighbour (KNN), and Random Forest (RF) algorithms were applied. According to the findings, the best results were obtained by NB with 0,7852 precision (P) and 0,7445 accuracy (A) values, KNN with 0,8209 recall (R) value, and RF with 0,7866 F-measure (F) value.

Keywords

5G, COVID-19, Sentiment Analysis, Machine Learning, Classification Algorithms

References

• Adwan, O. Y., Al-Tawil, M., Huneiti, A., Shahin, R., Zayed, A. A., & Al-Dibsi, R. (2020). Twitter sentiment analysis approaches: A survey. International Journal of Emerging Technologies in Learning (IJET), 15(15), 79−93. https://doi.org/10.3991/ijet.v15i15.14467
• Almunirawi, K. M., & Maghari, A. Y. A. (2016). A comparative study on serial decision tree classification algorithms in text mining. International Journal of Intelligent Computing Research (IJICR), 7(4), 754−760.
• Anvar Shathik, J. & Krishna Prasad, K. (2020). A literature review on application of sentiment analysis using machine learning techniques. International Journal of Applied Engineering and Management Letters (IJAEML), 4(2), 41−77. http://doi.org/10.5281/zenodo.3977576
• Bahja, M., & Safdar, G. A. (2020). Unlink the link between COVID-19 and 5G networks: An NLP and SNA based approach. IEEE Access: Practical Innovations, Open Solutions, 8, 209127-209137. https://doi.org/10.1109/ACCESS. 2020.3039168
• Bužić, D. (2019). Sentiment analysis of text documents. In V. Strahonja & V. Kirinić (Eds.), Proceedings of the Central European conference on information and intelligent systems (pp. 215−221). University of Zagreb.
• Chomboon, K., Chujai, P., Teerarassamee, P., Kerdprasop, K., Kerdprasop, N. (2015). An empirical study of distance metrics for k-nearest neighbor algorithm. In Proceedings of the 3rd international conference on industrial application engineering (pp. 280−285). The Institute of Industrial Applications Engineers, Japan. Doi: https://doi.org/10.12792/iciae2015.051
• Cutler, A., Cutler, D. R., & Stevens, J. R. (2012). Random Forests. In C. Zhang & Y. Ma (Ed.), Ensemble Machine Learning: Methods and Applications (pp. 157−175). Springer US. https://doi.org/10.1007/978-1-4419-9326-7_5
• Go, A., Huang, L., & Bhayani, R. (2009, June 6). Twitter sentiment analysis [Final project report CS224N]. The Stanford NLP Group. https://www-nlp.stanford.edu/courses/cs224n/2009/fp/3.pdf
• Ha, H., Han, H., Mun, S., Bae, S., Lee, J., & Lee, K. (2019). An improved study of multilevel semantic network visualization for analyzing sentiment word of movie review data. Applied Sciences, 9(12), 8−31. https://doi.org/10.3390/app9122419
• Kass, G. V. (1980). An exploratory technique for investigating large quantities of categorical data. Applied Statistics, 29(2), 119−127. https://doi.org/10.2307/2986296
• Kim, H., & Jeong, Y.-S. (2019). Sentiment classification using convolutional neural networks. Applied Sciences, 9(11), 2347. https://doi.org/10.3390/app9112347
• Kulkarni, A., Chong, D., & Batarseh, F. A. (2020). 5—Foundations of data imbalance and solutions for a data democracy. In F. A. Batarseh & R. Yang (Ed.), Data democracy: At the nexus of artificial intelligence, software development, and knowledge engineering (pp. 83−106). Academic Press. https://doi.org/10.1016/B978-0-12-818366-3.00005-8
• Kumar, T.S.S., Devi, N.T.D., Krishnendhu, T.K., Neethu, K.E., Radhakrishnan, S. C. (2020). Review of sentiment analysis: A multilingual approach. International Journal of Advanced Research in Computer and Communication Engineering, 9(1), 53−58.
• Loh, W.Y., & Shih, Y.S. (1997). Split selection methods for classification trees. Statistica Sinica, 7(4), 815−840.
• Mehta, P., & Pandya, S. (2020). A review on sentiment analysis methodologies, practices and applications. International Journal of Scientific & Technology Research, 9(2), 601−609. http://www.ijstr.org/final-print/feb2020/A-Review-On-Sentiment-Analysis-Methodologies-Practices-And-Applications.pdf
• Oğuzlar, A., & Kızılkaya, Y. M. (2019). Metin madenciliğinde duygu analizi - R uygulamalı. Dora Yayınevi.
• Patel, S. (2017, May 18). Chapter 5: Random Forest Classifier. Machine Learning 101. https://medium.com/machine-learning-101/chapter-5-random-forest-classifier-56dc7425c3e1
• Piksina, O., & Vernholmen, P. (2020). Coronavirus-Related Sentiment and Stock Prices Measuring Sentiment Effects on Swedish Stock Indices (Degree Project). Real Estate and Finance, Institutionen För Fastigheter Och Byggande, Stockholm, Sweden. https://www.diva-portal.org/smash/get/diva2:1442317/FULLTEXT01.pdf
• Poria, S., Hazarika, D., Majumder, N., & Mihalcea, R. (2020). Beneath the tip of the iceberg: Current challenges and new directions in sentiment analysis research (arXiv:2005.00357). arXiv. https://doi.org/10.48550/arXiv.2005.00357
• Qualcomm (t.y.). Everything you need to know about 5G. Qualcomm Technologies, Inc. Retrieved March 25, 2021, from https://www.qualcomm.com/5g/what-is-5g
• Rajput, N. K., Grover, B. A., & Rathi, V. K. (2020). Word frequency and sentiment analysis of Twitter messages during coronavirus pandemic (arXiv:2004.03925). arXiv. https://doi.org/10.48550/arXiv.2004.03925
• Reality Check Team. (2019, July 15). Does 5G pose health risks? BBC News. https://www.bbc.com/news/world-europe-48616174
• Rokach, L., & Maimon, O. (2005). Decision trees. In O. Maimon & L. Rokach (Ed.), Data mining and knowledge discovery handbook (pp. 165−192). Springer US. https://doi.org/10.1007/0-387-25465-X_9
• Sayad, S. (t.y.). Decision tree-classification. An introduction to data science. Retriewed April 3, 2021, from https://www.saedsayad.com/decision_tree.htm
• Singh, A. (2015). Twitter sentiment analysis (Report No. CS365A: 12056). https://cse.iitk.ac.in/users/cs365/2015/ _submissions/ajaysi/report.pdf
• Sokolova, M., Japkowicz, N., & Szpakowicz, S. (2006). Beyond accuracy, F-score and ROC: A family of discriminant measures for performance evaluation. Proceedings of the 19th Australian joint conference on Artificial Intelligence: Advances in artificial intelligence, 1015−1021. https://doi.org/10.1007/11941439_114
• Tian, L., Lai, C., & Moore, J. (2018). Polarity and intensity: The two aspects of sentiment analysis. In Proceedings of Grand Challenge and Workshop on Human Multimodal Language (Challenge-HML) (pp. 40−47). Association for Computational Linguistics (ACL). https://doi.org/10.18653/v1/W18-3306
• Timur Çakmak, E., & Oğuzlar, A. (2020). 2020 ABD başkanlık seçimleri üzerine sosyal medya duygu analizi. İçinde 20. Uluslararası ekonometri, yöneylem araştırması ve istatistik sempozyumu tam metin kitapçığı (ss. 19–27). Ankara Hacı Bayram Veli Üniversitesi.
• Visa, S., Ramsay, B., Ralescu, A., & van der Knaap, E. (2011). Confusion matrix-based feature selection. In S. Visa, A. Inoue, & A. Ralescu (Ed.), Proceedings of the 22nd Midwest Artificial Intelligence and Cognitive Science Conference (pp. 120−127). Cincinnati.
• Wilson, S. L., & Wiysonge, C. (2020). Social media and vaccine hesitancy. BMJ Global Health, 5(10), e004206. https://doi.org/10.1136/bmjgh-2020-004206