ISALE: A Neuro-Symbolic Framework for Concealed Psychological Risk Assessment in K-12 Students
- DOI
- 10.2991/978-94-6239-733-0_13How to use a DOI?
- Keywords
- Affective Computing; Knowledge Graph; Neuro-Symbolic AI; Psychological Risk Assessment; Metaphorical Recognition; K-12 Education
- Abstract
Traditional automated sentiment analysis often fails to detect concealed emotional distress in K-12 students due to the subtle nature of their metaphorical expressions. This paper presents ISALE, a neuro-symbolic framework that integrates a Neo4j knowledge graph with the DeepSeek-V3 large language model. By employing a dual-pathway weighted fusion mechanism, ISALE maps unstructured student narratives to structured psychological metaphors to calculate a comprehensive risk index. Preliminary evaluation on 25 samples demonstrates an 88% precision rate, with high expert alignment (Pearson r=0.8626, p < 0.01; Quadratic Weighted Kappa 0.8758). These results indicate that bridging neural perception with symbolic knowledge significantly enhances the interpretability and accuracy of adolescent psychological screening.
- Copyright
- © 2026 The Author(s)
- Open Access
- Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.
Cite this article
TY - CONF AU - Xinyin Hu PY - 2026 DA - 2026/07/17 TI - ISALE: A Neuro-Symbolic Framework for Concealed Psychological Risk Assessment in K-12 Students BT - Proceedings of the 6th International Conference on Internet, Education and Information Technology (IEIT 2026) PB - Atlantis Press SP - 102 EP - 109 SN - 2667-128X UR - https://doi.org/10.2991/978-94-6239-733-0_13 DO - 10.2991/978-94-6239-733-0_13 ID - Hu2026 ER -