Author(s)

ZeYu Wang¹, XinYao Wu¹, Miao Qin¹, LiXuan Wang^2*

Affiliation(s)

¹School of Public Administration, Guangzhou University, Guangzhou 510006, Guangdong, China.

²Birmingham Business School, University of Birmingham, Birmingham B15 2TT, United Kingdom.

Corresponding Author

LiXuan Wang

ABSTRACT

This study focuses on the perception of college students' ideological dynamics and explores the application of multimodal data fusion technology in precision intervention. With the rapid development of information technology, the value of multimodal data fusion in social sciences has become increasingly prominent; therefore, this study proposes a mechanism for the perception and precision intervention of college students' ideological dynamics based on multimodal data fusion. The study first defines the connotation and classification of multimodal data, the constituent elements of students' ideological dynamics, and the theoretical framework of the precision intervention mechanism. Theoretically grounded in Social Cognitive Theory, Data Fusion Theory, and Precision Governance Theory, the research constructs an overall framework and technical roadmap, proposing hypotheses and defining variable operationalization. Regarding data collection, sources and types were selected, collection tools and processes were designed, and methods for quality control and preprocessing were established. For model construction and implementation, the study conducted data preprocessing and feature engineering, designed a fusion model architecture, and verified the model's validity through comparative experiments. Empirical results demonstrate that multimodal data fusion significantly enhances the perception of students' ideological dynamics, with the perception model achieving high accuracy and recall, and varying contributions observed across different data modalities. Furthermore, regarding the precision intervention mechanism, an intelligent matching algorithm for intervention needs was proposed, and a multi-dimensional intervention strategy system was constructed, with practical feasibility verified through simulation experiments. The results indicate that the proposed mechanism has significant application value, offering a theoretical basis and practical path for the digital transformation of ideological education in universities and new perspectives for applying multimodal data fusion in social sciences. However, acknowledging limitations in algorithm optimization and intervention diversity, the study suggests future research directions including ethical norms and privacy protection regarding multimodal data.

KEYWORDS

Multimodal data fusion; College students; Ideological dynamics; Precision intervention; Intelligent perception

CITE THIS PAPER

ZeYu Wang, XinYao Wu, Miao Qin, LiXuan Wang. Multimodal data fusion empowered perception and precision intervention for ideological dynamics of university students. World Journal of Educational Studies. 2025, 3(8): 60-71. DOI: https://doi.org/10.61784/wjes3110.

REFERENCES

[1] Feng Z X. Ethical Stance and Governance of Generative AI Applications: A Case Study of ChatGPT. Journal of East China University of Political Science and Law, 2024(1): 61-71.

[2] Wu H Z, Zhang G H. Research on the Innovation of College Students’ Ideological and Political Work Driven by Digital Technology. The Party Building and Ideological Education in Schools, 2024(10): 74-76.

[3] Li Q, Yang S. Research Progress of Ideological and Political Education in the Era of Artificial Intelligence: A Bibliometric Visualization Analysis Based on CiteSpace. Journal of Liuzhou Vocational & Technical College, 2024(2): 65-72.

[4] Wang S M, Hou H T, Wu S Y. Analyzing the knowledge construction and cognitive patterns of blog-based instructional activities using four frequent interactive strategies (problem solving, peer assessment, role playing and peer tutoring): a preliminary study. Educational Technology Research and Development, 2017, 65: 301-323.

[5] Xu Z G, Zhao C Y, Wang Y, et al. Influencing Factors of College Students’ Deep Learning in the Smart Learning Environment. Modern Educational Technology, 2023, 33(1): 58-65.

[6] Jiang X, Su X N. AI-Enabled Transformation of Social Science Research Process. Journal of Xihua University (Philosophy & Social Sciences), 2024(6).

[7] Lu Y, Yu J L, Chen P H, et al. Research and Prospects of Multimodal Large Models in Education. e-Education Research, 2023(6).

[8] Russell J A. A Circumplex Model of Affect. Journal of Personality and Social Psychology, 1980, 39(6): 1161-1178.

[9] Li Q Y, Jia E L. Exploration of the Construction Path of College Students’ Mental Health Education Work Platform in the New Media Era. Journal of News Research, 2023, 14(4): 170-172.

[10] Cao J H. The Theoretical Logic and Practical Prospect of AI-Enabled Precision in Ideological and Political Course Teaching. Journal of Ideological & Theoretical Education, 2022(4).

[11] Akgun S, Greenhow C. Artificial intelligence in education: Addressing ethical challenges in K-12 settings. AI and Ethics, 2021, 2(3).

[12] Rakowski R, Polak P, Kowalikova P. Ethical Aspects of the Impact of AI: the Status of Humans in the Era of Artificial Intelligence. Society, 2021.

[13] Bates T, Cobo C, Marino O, et al. Can artificial intelligence transform higher education. International Journal of Educational Technology in Higher Education, 2020, 17(1).

[14] Su Y B, Li H. The Realistic Situation and Practical Path of Digital Intelligence Technology Empowering Ideological and Political Education. Journal of Jiangxi Normal University (Philosophy and Social Sciences Edition), 2024(1): 42-49.

[15] Zhang Y, Liu H D. The Value Implication, Realistic Dilemma and Practical Path of Digital Technology Empowering Ideological and Political Education in Colleges and Universities. The Party Building and Ideological Education in Schools, 2024(21): 79-82.

[16] Xing Y Y. The Patterns, Hidden Concerns and Paths of Digital Intelligence Technology Empowering Ideological and Political Education Scenarios. Journal of Socialist Theory Guide, 2024(12): 116-122.

[17] Li F Q, Pan F. The Prospect, Practical Dilemmas, and Pathways of the Digital-Intelligent Transformation of Ideological and Political Education. China University Teaching, 2024(8): 69-76+85.

[18] Woolf B P, Lane H C, Chaudhri V K, Kolodner J L. AI Grand Challenges for Education. AI Magazine, 2013, 34(4): 66-84.