Mental Health Survey Dataset (India)

This dataset contains anonymized responses from a mental health survey of 257 Indian young adults. The survey includes 30 Likert-type items assessing emotional well-being, sleep quality, social support, coping behavior, and self-harm ideation. Each item is scored on a 4-point scale (0–3), measuring symptom severity. A total score (0–90) was computed for each participant. Unsupervised K-Means clustering (K = 4) was used to generate four mental-health severity categories:• Low Risk• Mild• Moderate• Severe Psychometric analysis demonstrated good internal consistency (Cronbach’s α > 0.80), acceptable sampling validity (KMO > 0.70), and a 6-factor structure under Promax rotation. The dataset may be used for research on mental-health screening, factor-analysis studies, and machine-learning classification models. No personally-identifiable data are included. All participants provided informed consent.本数据集包含257名印度青年的心理健康调查问卷匿名应答数据。本次问卷包含30道李克特式（Likert-type）题目，用以评估情绪幸福感、睡眠质量、社会支持、应对行为与自伤意念。每道题目采用0-3分的4级计分体系，用于衡量症状严重程度。 为每位受访者计算了总得分，总分范围为0至90分。研究采用无监督K均值聚类（K-Means）算法，设置聚类数K=4，生成四类心理健康严重程度分级：低风险、轻度、中度、重度。 心理测量学分析结果显示，该量表具有良好的内部一致性（克朗巴赫α系数（Cronbach’s α）>0.80）、可接受的抽样效度（KMO检验值（Kaiser-Meyer-Olkin）>0.70），且经Promax旋转（Promax rotation）后得到六因子结构。 本数据集适用于心理健康筛查、因子分析研究及机器学习分类模型相关研究。 本数据集未包含任何个人可识别信息，所有受访者均已签署知情同意书。