Related Experiment Video
Updated: Jul 7, 2026
12:55
Multimodal Protocol for Assessing Metacognition and Self-Regulation in Adults with Learning Difficulties
Published on: September 27, 2020
Identifying foreign language learning burnout: latent profiles, cutoff points, and an explainable web-based
Nuoyi She1, Xu Chen1, Qiang Wan2
1School of English Studies, Xi'an International Studies University, Xi'an, China.
Frontiers in Psychology
|July 2, 2026
Summary
Foreign language learning burnout (FLLB) affects many students. This study identified a high-risk group and developed a predictive tool to help identify and support learners experiencing burnout.
Area of Science:
- Educational Psychology
- Mental Health
- Machine Learning in Education
Background:
- Foreign language learning burnout (FLLB) is common among English as a foreign language learners.
- FLLB negatively impacts academic performance and mental well-being.
- Current tools for FLLB identification and risk prediction are limited.
Purpose of the Study:
- To establish a clear cutoff point for identifying FLLB.
- To develop and validate an individualized risk prediction tool for FLLB.
- To provide practical support for FLLB screening and intervention.
Main Methods:
- Cross-sectional study with 1,343 Chinese secondary school students.
- Latent profile analysis (LPA) for FLLB risk profiling.
- Receiver operating characteristic (ROC) curve analysis for cutoff determination.
- Comparison and validation of six machine learning models, including logistic regression.
- Shapley additive explanation (SHAP) analysis for model interpretation.
Main Results:
- 14.2% of students were identified in the FLLB high-risk group.
- Optimal cutoff points: Exhaustion ≥14, Cynicism ≥3, Reduced Efficacy ≥3.
- Logistic regression model achieved AUC of 0.903 (internal) and 0.813 (external validation).
- Key predictors identified: academic stress and foreign language enjoyment.
Conclusions:
- An operational cutoff point for FLLB was successfully determined.
- A validated, high-performing risk prediction model was developed and deployed as a web-based calculator.
- The tool facilitates efficient FLLB risk screening and targeted support for learners.
