Poor performance discovery of college students based on behavior pattern

Zhang, Xi; Sun, Guoqiang; Yong, Pan; Sun, Hao; Tan, Jia-li

doi:10.1109/uic-atc.2017.8397506

Cited by 4 publications

(1 citation statement)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To ensure that the cosine distances of similar students' embeddings can be updated to closer, we design a subtask for better parameter learning inspired by prior works Lian et al (2016); Zhang et al (2017); Yao et al (2019). We utilize a shallow neural network to predict each similar student Student1..M in P s for a given student s. Thus, we get better student representations to assist the main task.…”

Section: Additional Inference Taskmentioning

confidence: 99%

Explainable Student Performance Prediction With Personalized Attention for Explaining Why A Student Fails

Niu¹,

Cao²,

Yu³

2021

Preprint

View full text Add to dashboard Cite

As student failure rates continue to increase in higher education, predicting student performance in the following semester has become a significant demand. Personalized student performance prediction helps educators gain a comprehensive view of student status and effectively intervene in advance. However, existing works scarcely consider the explainability of student performance prediction, which educators are most concerned about. In this paper, we propose a novel Explainable Student performance prediction method with Personalized Attention (ESPA) by utilizing relationships in student profiles and prior knowledge of related courses. The designed Bidirectional Long Short-Term Memory (BiLSTM) architecture extracts the semantic information in the paths with specific patterns. As for leveraging similar paths' internal relations, a local and global-level attention mechanism is proposed to distinguish the influence of different students or courses for making predictions. Hence, valid reasoning on paths can be applied to predict the performance of students. The ESPA consistently outperforms the other state-of-the-art models for student performance prediction, and the results are intuitively explainable. This work can help educators better understand the different impacts of behavior on students' study.

show abstract

Section: Additional Inference Taskmentioning

confidence: 99%