Author(s)

Lingjie Wu ¹, Zhenyi Liu ¹, Duoduo Yu ², Xi Wang ³, Shaochen Lin ⁴, Jianhan Peng ⁵, Dugui Chen ⁶

Affiliation(s)

¹ School of Health Sciences, Wenshan Vocational and Technical College, Wenshan, China
² School of General Education, Wenshan Vocational and Technical College, Wenshan, China
³ School of Medicine and Nursing, Shandong Vocational University of Foreign Affairs, Weihai, China
⁴ Department of Geriatrics, Yunnan Provincial Psychiatric Hospital, Kunming, China
⁵ School of Teacher Education, Wenshan University, Wenshan, China
⁶ School of Artificial Intelligence, Wenshan Vocational and Technical College, Wenshan, China

Corresponding Author

Duoduo Yu

ABSTRACT

This study integrated sandplay analysis with a hybrid convolutional neural network–support vector machine (CNN–SVM) framework to identify English learning difficulties among vocational college students, with the aim of improving the objectivity and reproducibility of projective assessment in educational psychology. A total of 190 students were included, of whom 134 were classified as having English learning difficulties and 56 as non-difficulty cases. Group assignment followed a dual-criterion approach: students with semester English scores below 60, low academic self-efficacy, and high foreign language anxiety were assigned to the difficulty group, whereas those with scores above 70, high self-efficacy, and low anxiety were assigned to the non-difficulty group. Under standardized and controlled conditions, all participants completed a sandplay task, and the resulting images were preprocessed through cropping, normalization, and resizing, with data augmentation applied to mitigate class imbalance. A shallow CNN was used to extract symbolic and spatial features from the sandplay images, and the resulting feature embeddings were then classified using an SVM with a radial basis function kernel. Model hyperparameters were optimized through nested cross-validation, and robustness was further evaluated using repeated hold-out validation. The CNN–SVM model achieved a mean validation accuracy of 91.5% and an area under the curve (AUC) of 0.95. On the independent test set, the model reached an accuracy of 83.9%, and recall for the difficulty group was 96.2%, indicating strong sensitivity and a reduced likelihood of missing at-risk students. Grad-CAM visualizations further showed that figurine clustering and central spatial arrangements were among the most important discriminative cues, consistent with established interpretations of sandplay symbolism. Overall, the findings suggest that quantifiable symbolic cues in sandplay can support accurate prediction of learning difficulties, and that this reproducible framework offers a promising bridge between projective techniques and artificial intelligence for early screening. Future research should include larger and more diverse samples, as well as broader assessment indicators, to strengthen the external validity of the model.

KEYWORDS

Sandplay analysis; learning difficulties; convolutional neural network; support vector machine; computational psychology

CITE THIS PAPER

Lingjie Wu, Zhenyi Liu, Duoduo Yu, Xi Wang, Shaochen Lin, Jianhan Peng, Dugui Chen. Integrating Sandplay Analysis and CNN–SVM Modeling for Predicting English Learning Difficulties among Vocational College Students: A Computational Psychology Approach. Applied & Educational Psychology (2026). Vol. 7, No.1, 48-67. DOI: http://dx.doi.org/10.23977/appep.2026.070107.

REFERENCES

[1] Berrich, Y., & Guennoun, Z. (2025). EEG-based epilepsy detection using CNN-SVM and DNN-SVM with feature dimensionality reduction by PCA. Scientific Reports, 15(1), 14313.
[2] Birthriya, S. K., Ahlawat, P., & Jain, A. K. (2025). Intelligent phishing website detection: A CNN-SVM approach with nature-inspired hyperparameter tuning. Cyber Security and Applications, 3, 100100.
[3] Clifford, V., Rhodes, A., & Paxton, G. (2014). Learning difficulties or learning English difficulties? Additional language acquisition: An update for paediatricians. Journal of Paediatrics and Child Health, 50(3), 175–181.
[4] Ge, Y., Huo, J. Y., Yang, H. B., Wenger, J. L., Yuan, J. Y., & Sun, X. J. (2023). Eye movement verification and evaluation of initial sandplay picture system for internet addiction symptoms in Chinese adolescents. Italian Journal of Pediatrics, 49(1), 86.
[5] Haiyan Liu, & Huimin Liu. (2025). A comparative study of EEG functional and effective connectivity patterns in children with learning difficulties during reading and math tasks. Frontiers in Neuroscience, 19, 1612884.
[6] Ko, J., Kang, M., & Jun, Y. J. (2025). Deep learning-based allergic rhinitis diagnosis using nasal endoscopy images. Scientific Reports, 15(1), 24341.
[7] Li, W., Baek, C. H., Lee, D. Y., Song, S. Y., Na, J. B., Hidayat, M. S., … Kim, D. H. (2024). The classification of metastatic spine cancer and spinal compression fractures by using CNN and SVM techniques. Bioengineering, 11(12), 1264.
[8] Liu, Y. Y., Li, K., Bin, T., Tan, J. F., Wang, Z. D., Wang, J. X., & Shen, H. Y. (2021). Psychological symptoms and the use of shadow miniatures in sandplay therapy. The Arts in Psychotherapy, 101834.
[9] Madison Reid, & Hamby, S. (2025). Strengths supporting resilience in individuals with learning disabilities: A scoping review. Children and Youth Services Review, 177, 108434.
[10] Qiu, Q. Z., Li, B. L., Yang, W. W., Zhu, Y., & Zhang, Q. Z. (2023). Analysis of initial sandplay characteristics among university students with different levels of loneliness. BMC Psychiatry, 23(1), 930.
[11] Semwal, T., Jain, S., Mohanta, A., & Jain, A. (2025). A hybrid CNN-SVM model optimized with PSO for accurate and non-invasive brain tumor classification. Neural Computing and Applications, 1–30.
[12] Preacher, K. J., Rucker, D. D., MacCallum, R. C., & Nicewander, W. A. (2005). Use of the extreme groups approach: A critical reexamination and new recommendations. Psychological Methods, 10(2), 178–192.
[13] Ministry of Education of the People’s Republic of China. (2017). English curriculum standards for ordinary senior high schools (2017 Edition). Beijing: People’s Education Press.
[14] Zhang, D. (2015). A study on English learning difficulties of Chinese vocational college students. Foreign Language World, 162(2), 45–53.
[15] Wang, Y. (2018). Characteristics and intervention of students with learning difficulties in Chinese secondary schools. Chinese Journal of Special Education, 203(6), 72–79.
[16] Wang, C. K., Hu, Z. F., & Liu, Y. (2001). Evidences for reliability and validity of the Chinese version of General Self-Efficacy Scale. Chinese Journal of Applied Psychology, 7(1), 37–40.
[17] Liang, Y. J. (2000). The development of academic self-efficacy scale for middle school students. Psychological Development and Education, 16(2), 48–51.
[18] Liu, M., & Huang, W. (2011). An exploration of foreign language classroom anxiety in Chinese university students. Journal of Asia TEFL, 8(3), 123–145.
[19] Zheng, Q. Q., Li, B. L., Yang, W. W., Zhu, Y., & Zhang, Q. Z. (2023). Analysis of initial sandplay characteristics among university students with different levels of loneliness. BMC Psychiatry, 23(1), 930.

Sponsors, Associates, and Links

---

• Advances in Educational Technology and Psychology
  
  
• Curriculum and Teaching Methodology
  
  
• Transactions on Comparative Education
  
  
• Advances in Vocational and Technical Education
  
  
• Adult and Higher Education