Formative Evaluation of College Students’ Online English Learning Based on Learning Behavior Analysis

Abstract

To measure the achievements and progress of college students in online learning, online learning platforms and teachers must pay attention to the formative evaluation of the learning process. The relevant data should be fully utilized to analyze the online English learning behavior of college students, such that online learning platforms and teachers can make formative evaluation of the students’ online learning. However, the existing studies on formative evaluation are mostly theoretical. To solve the problem, this paper explores the formative evaluation of college students’ online English learning based on learning behavior analysis. Firstly, the density-based spatial clustering of applications with noise (DBSCAN) was adopted to analyze the data samples of college students’ online English learning behavior, the evaluation indices were selected for the formative evaluation of the said behavior, and the index weighting method was explained in details. Next, the school precaution function of online English learning was realized through the graph structure data prediction of students’ online learning behavior. Based on the proposed graph neural network, the clustering Euclidean distance weight was introduced to measure the similarity between two nodes. In addition, the weight update process was illustrated for the distance weight-based attention mechanism. The proposed formative evaluation approach was proved effective through experiments.

A study on academic dishonesty among English as a foreign language students

“…In addition, allowing sufficient time to take assessments permits students to demonstrate their understanding and apply what they have learned properly. These assessment methods contribute to a fair, objective, and meaningful assessment of student learning [ 81 , 82 ].…”

Student Online Learning Behavior Characteristics Based on Multidimensional Cognitive Model

“…In personalized teaching, teachers can develop personalized teaching plans and resources for students based on their interests, learning habits, and ability differences, thereby improving students' learning interests and grades [4,5]. Online learning platforms can analyze students' online learning behavior characteristics by collecting their learning data (such as login frequency, video viewing time, and completion of assignments), and provide more targeted teaching suggestions for educators [6][7][8][9].…”

Estrategias de evaluación formativa: Una revisión sistemática

“…Ahora bien, la evaluación formativa puede servir, además de lo mencionado, como predictores para medir cuán significativo ha sido el proceso de aprendizaje en los estudiantes (Zhang et al, 2022).…”