Using Multiple Data Mining Technologies to Analyze Process Evaluation in the Blended-Teaching Environment

Abstract

Under the background of new engineering, the integration of theory and practice in the blended-teaching environment has become the mainstream teaching mode amid science and engineering curriculum reform. Data analysis technology is used to study process evaluation based on the integration of theory and practice in the blended-teaching environment, and a reference for the innovation of process evaluation is provided. This paper makes four key contributions to the blended-teaching environment. The K-means algorithm is used to cluster students into five groups (“serious learners”, “active learners”, “self-directed learners”, “cooperative learners”, and “students with learning difficulties”), according to the results of the students’ process evaluation in the course, integrating theory and practice. The Apriori algorithm and C5.0 model are used to find the key indicators which affected students’ learning performance. They are: classroom performance, assignment submission, classroom testing, problem solving, and online learning. These indicators are used to predict the final learning outcome of students. The Bayesian network model is used to find that there is a strong correlation between learning participation and assignment submission, unit assessment and classroom testing, and classroom performance and work presentation. Data analysis technology is creatively used to strengthen process evaluation. Teaching and learning are promoted by evaluation, so that the true meaning of process evaluation can be revealed. This lays a theoretical and practical foundation for process evaluation, to impact the predominant situation of outcome evaluation and promote the sustainable development of education evaluation.