关键词: 眼动追踪, 抑郁倾向, 多特征融合, 扫描堆叠模型

Abstract: In recent years, the tendency of depression tends to occur at a younger age and affect more people. Although research on the topic has achieved some results, it still lacks a more objective and accurate method for identifying depressive tendencies, and research on depressive tendencies from multiple perspectives is lacking. With the continuous development of eye tracking, the application of this field are continuously expanding. To improve the accuracy and scientificity of depressive tendency assessment methods, the combination of mental health self-check table and eye tracking is proposed as a method for identifying depressive tendencies and is studied from multiple perspectives. The innovative features of eye movement, memory, cognitive style, and network behaviors are incorporated. Furthermore, in order to address complex feature relationship and extract more useful information, a scanning process is proposed, which is combined with a stacking method to form a proposed recognition model for depressive tendencies called the Scanning stacking model. To comprehensively and objectively evaluate the performance of the Scanning stacking model, the independent contributions of both the scanning process and the stacking method are evaluated, in addition, the Scanning stacking model is compared to different classification models.

Key words: eye tracking, depressive tendency, multi-feature fusion, Scanning stacking model