The research identifies two primary models for this integration: the element model and the process model. The element model focuses on the five key aspects of evaluation: who, what, when, how, and why. It emphasizes the inclusion of multiple evaluation subjects, comprehensive content covering knowledge, skills, and emotions, process-oriented methods, diverse evaluation techniques, and development-focused functions. The process model, on the other hand, outlines the framework for data acquisition, analysis, and result feedback. It highlights the importance of full-time, global, and lossless data acquisition, multi-dimensional and intelligent data analysis, and intuitive, personalized, and accurate result feedback.
The paper delves into practical application of the model at MUC, showcasing its implementation in teaching and learning evaluation, early warning of teachers’ appointment term assessment, and early warning of students’ abnormal behavior. It also discusses the challenges and limitations of Big Data-based education evaluation, such as data heterogeneity and the need for further verification of key technologies.
To address these challenges, the paper proposes a practical path for the implementation of Big Data-based education evaluation. This path emphasizes the importance of exploring application scenarios, continuously accumulating and sharing data, and maximizing data utilization. It also highlights the need for teacher training and improving data literacy to ensure effective use of educational data. Additionally, it underscores the criticality of prioritizing data security and implementing robust protection measures.
Overall, this paper provides a comprehensive framework for the construction and application of a Big Data-based education evaluation model. It offers valuable insights into the potential of Big Data to transform education evaluation and improve educational outcomes.
The work titled “Big Data-Based Evaluation of Higher Education: Model Construction and Practice Path”, was published on Frontiers of Digital Education (published on August 29, 2024).
DOI: 10.1007/s44366-024-0006-y