Abstract
Discourse power is a tool to express social ideology, which controls the direction of public opinion in the whole society, and the competition for discourse power is the concrete manifestation of ideological struggle. With the development of artificial intelligence, the trend of information globalization is becoming more and more obvious. In the field of ideology, a hundred flowers bloom and a hundred schools of thought contend. At present, China’s socialist mainstream ideology is Sinicized Marxism - it is Mao Zedong Thought and socialist ideological system with Chinese characteristics guided by Marxism. However, with the influx and flood of Western discourse thoughts, our ideological education discourse has also been impacted to a certain extent. *** Therefore, this paper proposes an effective classification method for unbalanced data sets. The core idea of the classification of educational discourse unbalanced data sets based on mixed big data analysis is to provide a comprehensive solution for the classification of unbalanced data sets from two aspects: sample preprocessing and classifier improvement.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Jiang, D., He, J.: Text semantic classification of long discourses based on neural networks with improved focal loss. Comput. Intell. Neurosci. 2021(1), 1–9 (2021)
Zhang, H., Hu, J., Zhang, Y.: Research on classification method of network resources based on modified SVM algorithm. Security and Communication Networks 2021(69), 1–8 (2021)
Stoica, A.S., et al.: Classification of educational videos by using a semi-supervised learning method on transcripts and keywords. Neurocomputing 456, 637–647 (2021)
Spangher, A., May, J., Shiang, S.R., et al.: Multitask Learning for Class-Imbalanced Discourse Classification (2021)
Lugini, L., Litman, D.: Contextual argument component classification for class discussions (2021)
Radyuk, A.V., Kozubenko, A.V.: Semantic classification of phraseological verbs in publicistic discourse of economic orientation. Revista Amazonia Investiga 10(37), 107–115 (2021)
Poddenezhnyi, O.: Management of digital transformation in education: modern scientific discourse. Scientific Papers NaUKMA Economics 6(1), 105–110 (2021)
Taniguchi, T.: Classification of educational skills for university students in computer programming classes. Int. J. Inf. Educ. Technol. 11(7), 313–318 (2021)
Ismail, S.: Distribution of discourse markers elements or discourse particle as an entity relationship in discourse. Turkish J. Comput. Math. Educ. (TURCOMAT) 12(3), 190–200 (2021)
Yankovskaya, T.: Mastering by students of the second grades of the universal educational action of classification. Primary Education, 35–39 (2021)
Acknowledgements
General topic of Zhejiang Federation of Social Sciences “analysis and Reflection on the competency characteristics of excellent ideological and political teachers in Colleges and universities” (No.: 2022N124)).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering
About this paper
Cite this paper
Teng, J. (2023). Classification Method of Educational Discourse Power Imbalance Data Set Based on Mixed Big Data Analysis. In: Jan, M.A., Khan, F. (eds) Application of Big Data, Blockchain, and Internet of Things for Education Informatization. BigIoT-EDU 2022. Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering, vol 466. Springer, Cham. https://doi.org/10.1007/978-3-031-23947-2_58
Download citation
DOI: https://doi.org/10.1007/978-3-031-23947-2_58
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-23946-5
Online ISBN: 978-3-031-23947-2
eBook Packages: Computer ScienceComputer Science (R0)