K.V. Sazonov1, A.A. Makunin2

1,2 Military University of Radio Electronics (Cherepovets, Russia)

Emotional content analysis is used to classify text messages based on their context. This article deals with the problem of class imbalance, which is one of the important issues in evaluating the emotional content of messages with a mixed code. Mixed code in the article refers to messages consisting of text formed from the terms of two or more languages. Class imbalance is a common occurrence in data with such a mixed code. The article proposes an approach to the analysis of emotional content for mixed code text messages using the sampling method in combination with Levenshtein distance metrics. In addition, the article compares the characteristics of various approaches to machine learning.

Sazonov K.V., Makunin A.A. Problems of content analysis of mixed-code text messages. Electromagnetic waves and electronic systems. 2023. V. 28. № 3. P. 38−45. DOI: https://doi.org/10.18127/j15604128-202303-05 (in Russian)

1. Chen Y., Xie J. Online Consumer Review: Word-of-Mouth as a New Element of Marketing Communication Mix. Management Science. 2008. V. 54. № 3. P. 477-491. DOI 10.1287/mnsc.1070.0810.
2. Asif M., Ishtiaq A., Ahmad H., Aljuaid H., Shah J. Sentiment analysis of extremism in social media from textual information. Telematics and Informatics. 2020. V. 48. P. 101345. DOI 10.1016/j.tele.2020.101345.
3. Nasukawa T., Yi D. Sentiment analysis: Capturing favorability using natural language processing. Proceedings of the 2nd international conference on Knowledge capture. Association for Computing Machinery. 2003. P. 70–77. DOI 10.1145/945645.945658.
4. Volkov A.S., Chernenky M.V., Silantieva E.Yu. Two-stage procedure of neural network analysis of the tonality of texts in Russian. Dynamics of Complex Systems – XXI century. 2021. V. 15. № 4. P. 5–13. DOI 10.18127/j19997493-202104-01. (in Russian)
5. Nguyen T., Nguyen L., Cao T. Sentiment analysis on medical text using combination of machine learning and SO-CAL scoring. 21st Asia Pacific Symposium on Intelligent and Evolutionary Systems. 2017. P. 49–54. DOI 10.1109/IESYS.2017.8233560.
6. Park D.-H., Lee J., Han I. The Effect of On-Line Consumer Reviews on Consumer Purchasing Intention: The Moderating Role of Involvement. International Journal of Electronic Commerce. V. 11. № 4. 2007. P. 125–148. DOI 10.2753/JEC1086-4415110405.
7. Gonçalves P., Araújo M., Benevenuto F., Cha M. Comparing and combining sentiment analysis methods. Proceedings of the first ACM conference on Online social networks. 2013. P. 27–38. DOI 10.1145/2512938.2512951.
8. Chen J.I.Z., Lai K. Machine Learning based Energy Management at Internet of Things Network Nodes. Journal of Trends in Computer Science and Smart Technology. 2020. V. 2. № 3. P. 127–133. DOI 10.36548/jtcsst.2020.3.001.
9. Mitelkov D.V., Novikov A.Yu. An improved method for improving the accuracy of selecting relevant text messages based on identifying the referential connectivity of text elements. Science Intensive Technologies. 2015. V. 16. № 12. P. 62–66. (in Russian)
10. Duraipandian D.M. Performance Evaluation of Routing Algorithm for Manet Based on the Machine Learning Techniques. Journal of Trends in Computer Science and Smart Technology. 2019 V.1. № 1. P. 24–35. DOI 10.36548/jtcsst.2019.1.003.
11. López V., Fernández A., García S., Palade V., Herrera F. An insight into classification with imbalanced data: Empirical results and current trends on using data intrinsic characteristics. Information Sciences. 2013. V. 250. P. 113–141.
12. Haixiang G., Li Y., Shang J., Gu M., Yuanyue H., Bing G. Learning from class-imbalanced data: Review of methods and applications. Expert Systems with Applications. 2017. V. 73. P. 220–239. DOI 10.1016/j.eswa.2016.12.035.
13. Li Y., Guo H., Zhang Q., Gu M., Yang J. Imbalanced text sentiment classification using universal and domain-specific knowledge. Knowledge-Based Systems. 2018. V. 160. P. 1–15.  DOI 10.1016/j.knosys.2018.06.019.