计算机工程与应用2025,Vol.61Issue(19):127-136,10.DOI:10.3778/j.issn.1002-8331.2406-0368
基于层次数据增强的多维度特征融合社交媒体抑郁症识别
Hierarchical Data Augmentation Based Multi-Dimensional Feature Fusion for Social Media Depression Recognition
摘要
Abstract
Depression,a common mental disorder,poses significant challenges in feature extraction for recognition due to the scarcity of data samples.This study proposes a hierarchical data augmentation technique,generating new depressive text samples through synonym replacement and syntactic tree adjustment,enriching the dataset.A multidimensional fea-ture fusion model for social media depression recognition is then constructed,integrating stylistic,emotional,and contex-tual features,with a multi-head attention mechanism emphasizing key depressive information for precise text classifica-tion.Experimental results show that this method effectively expands the sample data and accurately extracts depressive features,achieving a recognition accuracy of 92%,confirming the model's effectiveness.关键词
社交媒体/抑郁症识别/数据增强/多维度特征Key words
social media/depression recognition/data augmentation/multi-dimensional feature分类
信息技术与安全科学引用本文复制引用
李世琪,刁宇峰,张浩,杨亮,林鸿飞,樊小超..基于层次数据增强的多维度特征融合社交媒体抑郁症识别[J].计算机工程与应用,2025,61(19):127-136,10.基金项目
国家自然科学基金(62366040,62006130,62066044) (62366040,62006130,62066044)
内蒙古自然科学基金(2022MS06028) (2022MS06028)
内蒙古自治区高等学校青年科技英才支持计划(NJYT24037) (NJYT24037)
中央高校基本科研业务费资助(DUT24LAB123) (DUT24LAB123)
新疆师范大学智慧教育工程技术研究中心课题资助(XJNU-ZHJY202402) (XJNU-ZHJY202402)
内蒙古自治区高校科研直属项目(GXKYZ2050) (GXKYZ2050)
内蒙古民族大学博士启动基金(662). (662)