НАЦИОНАЛЬНАЯ АКАДЕМИЯ НАУК АЗЕРБАЙДЖАНА
АНАЛИЗ ТОНАЛЬНОСТИ TWITTER ДАННЫХ НА ОСНОВЕ МАШИННОГО ОБУЧЕНИЯ
Макруфа Ш. Гаджирагимова, Марзия И. Исмаилова

С наступлением эры социальных сетей и быстрым распространением приложений и форумов для микроблогов роль анализа тональности текста значительно возросла. Социальные сети являются основными источниками сбора информации о мыслях и мнениях пользователей по различным темам. Люди ежедневно часами проводят время в социальных сетях для того, чтобы поделиться своими мыслями и мнениями с другими пользователями. Одна из тем, обсуждаемых в социальных сетях, в частности в Twitter, – это пандемия COVID-19. В статье исследовано мнение пользователей Twitter из разных стран о пандемии COVID-19 на основе алгоритмов машинного обучения. Для анализа эмоциональной «окраски» (положительный, отрицательный и нейтральный) твитов о пандемии COVID-19 использованы четыре метода машинного обучения - Naive Bayes (NB), Support Vector Machine (SVM), Random Forest (RF) и Neural Network (NN). Эксперименты проведены в программной среде Python с применением библиотеки scikit-learn. В экспериментах использовался набор данных твитов, связанных с пандемией COVID-19, с веб-сайта Kaggle. Сравнительный анализ полученных результатов показал наилучшую результативность классификатора RF (стр.58-67).

Ключевые слова:Aнализ тональности, Twitter, Mикроблоги, Mашинное обучение, Naive Bayes, Neural Network
DOI : 10.25045/jpis.v13.i1.07
Литература
  • Liu, B. (2012). Sentiment analysis and opinion mining. Toronto: Morgan & Claypool Publishers. https://doi.org/10.2200/S00416ED1V01Y201204HLT016
  • Hacırəhimova, M.Ş., İsmayılova, M.İ. (2020). Sentiment analiz: problemləri və həlli yollari. İnformasiya texnologiyaları problemləri, 2, 111-123. https://doi.org/10.25045/jpit.v11.i2.11
  • Evirgen, E. (2016). Sentiment analysis of turkish tweets. Master Thesis. Turkey: Bahcesehir University. https://www.academia.edu/38504379/IJMET_10_01_094_pdf?from=cover_page
  • Alguliev, R., Aliguliyev, R., Hajirahimova, M. (2010). Multi-document summarization model based on integer linear programming. Intelligent Control and Automation, 1(2), 105-111.        https://doi.org/10.4236/ica.2010.12012
  • Kaur, C., Sharma, A. (2020). Twitter Sentiment Analysis on Coronavirus using Textblob. EasyChair Preprint, 2974, 1-10. https://easychair.org/publications/preprint/Fd5m
  • Dashtian, H., Murthy, D. (2021). CML-COVID: A large-scale covid-19 Twitter dataset with latent topics, sentiment and location information, Academia Letters, 1-9. https://doi.org/10.20935/AL314
  • Samina, A. et al. (2021). Machine Learning Approach for COVID-19 Detection on Twitter. Computers, Materials & Continua, 68(2), 2231-2247. https://doi.org/10.32604/cmc.2021.016896
  • Shofiya, C., Samina, A. (2021). Sentiment Analysis on COVID-19-Related Social Distancing in Canada Using Twitter Data. International Journal of Enviromental Research and Public Health, 18(11), 1-10. https://doi.org/10.3390/ijerph18115993
  • Abdulaziz, M. et al. (2021). Topic based Sentiment Analysis for COVID-19 Tweets. International Journal of Advanced Computer Science and Applications, 12 (1), 626-636. https://doi.org/10.14569/IJACSA.2021.0120172
  • Vohra, S. M., Teraiya, J. B. (2013). A comparative study of sentiment Analysis techniques. İnternational Journal of Information, knowledge and research in Computer engineering, 2(2), 313-317.
  • Kumar, A., Sebastian, T. M. (2012). Sentiment Analysis on Twitter. International Journal of Computer Science, 9(4), 372-378. http://www.ijcsi.org/
  • Kolchyna, O. et al. (2015). Twitter Sentiment Analysis: Lexicon Method, MachineLearning Method and Their Combination, Cornell university, 1-32. arXiv.org
  • Borele, P., Borikar, D.A. (2016). An Approach to Sentiment Analysis using Artificial Neural Network with Comparative Analysis of Different Techniques. Journal of Computer Engineering (IOSR-JCE), 18(2), 64-69.
  • Spencer, J., Uchyigit, G. (2012). Sentimentor: Sentiment Analysis of Twitter Data. In The 1st International Workshop on Sentiment Discovery from Affective Data (SDAD), Bristol, UK, 28 September (pp.56-66). http://www.iosrjournals.org/
  • Hasan, A., Moin, S., Karim, A., Shamshirband, S. (2018). Machine Learning-Based Sentiment Analysis for Twitter Accounts International Journal of Mathematical and Computational Applications, 23(11), 1-15. https://doi.org/10.3390/MCA23010011
  • Yadav, S.J., Ranjan, P. (2017). Proposed Approach for Sarcasm Detection in Twitter Shubhodip. Indian Journal of Science and Technology, 10(25), 1-8. https://doi.org/10.17485/ijst/2017/v10i25/114443
  • Bahrainian, S.A., Denge, A. (2013).Sentiment Analysis using Sentiment Features. Proc. of IEEE/WIC/ACM International Conferences on Web Intelligence (WI) and Intelligent Agent Technology (IAT), Washington, USA, November 2013, pp. 26-29. https://doi.org/10.1109/WI-IAT.2013.145
  • Kawade, D.R., Oza, K.S. (2017). Sentiment Analysis: Machine Learning Approach. International Journal of Engineering and Technology, 9(3), pp.2183-2186. https://doi.org/10.21817/IJET/2017/V9I3/1709030151
  • Hafez, A.A., Xu, Y., Tjondronegoro, D. (2012). Product Reputation Model: An Opinion Mining Based Approach. Proc. of the 1st International Workshop on Sentiment Discovery from Affective Data, London, UK, January 2012 (pp.16-27). http://ceur-ws.org/Vol-917/
  • Saleena, A.N. (2018). An Ensemble Classification System for Twitter Sentiment Analysis. Proc. of the International Conference on Computational Intelligence and Data Science (ICCIDS), Gurugram, İndia, January 2018 (pp. 937-946). https://doi.org/10.1016/j.procs.2018.05.109
  • Sumathy, Dr.P., Muthukumari, S.M. (2018). Sentiment Analysis of Twitter Data Using Multi Class Semantic Approach. International Journal of Scientific Research in Computer Science, Engineering and Information Technology (IJSRCSEIT), 3(6), 262-269. https://doi.org/10.32628/CSEIT183654
  • Shehu, H.A., Tokat, S., Sharif, Md. H., Uyaver, S. (2019). Sentiment Analysis of Turkish Twitter Data. Proc of the AIP Conference, 2183(1), AIP Publishing (pp.1-4).  https://doi.org/10.1063/1.5136197
  • Hacırəhimova, M., İmamverdiyeva, A. (2018) Twitter məlumatlarının sentiment analizi. “İnformasiya təhlükəsizliyinin aktual multidissiplinar elmi-praktiki problemləri” IV respublika konfransı, Bakı, Azərbaycan, 14 dekabr 2018 (s. 245-248). https://doi.org/10.25045/NCInfoSec.2018.59
  • Kumar, R. (2015). A survey on opinion mining and sentiment analysis: tasks, approaches and applications. Knowledge-Based Systems, 89, 14-46. https://doi.org/10.1016/j.knosys.2015.06.015
  • Kharde, V.A., Sonawane, S.S. Sentiment Analysis of Twitter Data: A (2016). Survey of Techniques Vishal A. International Journal of Computer Applications, 139(11), 5-15.  https://doi.org/10.5120/ijca2016908625
  • Tang, H., Tan, S., Cheng, X. (2009). A survey on sentiment detection of reviews. International Journal Expert Systems with Applications, 36(7), 10760–10773. https://doi.org/10.1016/j.eswa.2009.02.063
  • Medhat, W., Hassan, A., Korashy, H. (2014). Sentiment analysis algorithms and applications: A survey. Ain Shams Engineering Journal, 5(4), 1093–1113. https://doi.org/10.1016/j.asej.2014.04.011
  • Vinodhini, G., Chandrasekaran, R.M. (2012). Sentiment Analysis and Opinion Mining: A Survey. International Journal of Advanced Research in Computer Science and Software Engineering, 2(6), 282-292. https://doi.org/10.5121/ijasuc.2013.4102
  • Wawre, S.V., Deshmukh, S.N. (2016). Sentiment Classification using Machine Learning Techniques. International Journal of Science and Research, 5(4), 819-821.
  • Padmaja, S., Fatima, S.S. (2013). Opinion Mining and Sentiment Analysis –An Assessment of Peoples’ Belief: A Survey. International Journal of Ad hoc, Sensor & Ubiquitous Computing (IJASUC), 4(1), 21-33. http://www.ijsr.net
  • Pranali, B., Dilipkumar, A.B. (2016). An Approach to Sentiment Analysis using Artificial Neural Network with Comparative Analysis of Different Techniques. Journal of Computer Engineering, 18(2), 64-69. https://doi.org/10.9790/0661-1802056469
  • Chena, L-S, Liub, C-H, Chiu, H-J. (2011). A neural network based approach for sentiment classification in the blogosphere. Journal of Informetrics, 5(2), 313–322. https://doi.org/10.1016/j.joi.2011.01.003
  • Mathur, R., Bandil, D., Pathak, V. (2018). Analyzing Sentiment of Twitter Data using Machine Learning Algorithm. GADL Journal of Inventions in Computer Science and Communication Technology (JICSCT), 4(2), 1-7.