Interpersonal Sensitivity Prediction Based on Multi-strategy Artemisinin Optimization with Fuzzy K-Nearest Neighbor

The mental health issues of college students have become an increasingly prominent social problem, exerting severe impacts on their academic performance and overall well-being. Early identification of Interpersonal Sensitivity (IS) in students serves as an effective approach to detect psychological problems and provide timely intervention. In this study, 958 freshmen from higher education institutions in Zhejiang Province were selected as participants. We proposed a Multi-Strategy Artemisinin Optimization (MSAO) algorithm by enhancing the Artemisinin Optimization (AO) framework through the integration of a group-guided elimination strategy and a two-stage consolidation strategy. Subsequently, the MSAO was combined with the Fuzzy K-Nearest Neighbor (FKNN) classifier to develop the bMSAO-FKNN predictive model for assessing college students’ IS. The proposed algorithm’s efficacy was validated through the CEC 2017 benchmark test suite, while the model’s performance was evaluated on the IS dataset, achieving an accuracy rate of 97.81%. These findings demonstrate that the bMSAO-FKNN model not only ensures high predictive accuracy but also offers interpretability for IS prediction, making it a valuable tool for mental health monitoring in academic settings.