Postpartum Depression (PPD) is a frequently ignored birth-related consequence. Social network analysis can be used to address this issue because social media network serves as a platform for their users to communicate with their friends and share their opinions, photos, and videos, which reflect their moods, feelings, and sentiments. In this work, the depression of delivered mothers is identified using the PPD score and segregated into control and depressed groups. Recently, to detect depression, deep learning methods have played a vital role. However, these methods still do not clarify why some people have been identified as depressed. We have developed Attribute Selection Hybrid Network (ASHN) to detect the postpartum depression diagnoses framework. Later analysis of the post of mothers who have been confirmed with the score calculated by the experts of the field using physiological questionnaire score. The model works on the analysis of the attributes of the negative Facebook posts for Depressed user Diagnosis, which is a large general forum. This framework explains the process of analyzing posts containing Sentiment, depressive symptoms, and reflective thinking and suggests psycho-linguistic and stylistic attributes of depression in posts. The experimental results show that ASHN works well and is easy to understand. Here, four attribute networks based on psychological studies were used to analyze the different parts of posts by depressed users. The results of the experiments show the extraction of psycho-linguistic markers-based attributes, the recording of assessment metrics including Precision, Recall and F1 score and visualization of those attributes were used title-wise as well as words wise and compared with daily life, depression and postpartum depressed people using Word cloud. Furthermore, a comparison to a reference with Baseline and ASHN model was carried out. Attribute Selection Hybrid Network (ASHN) mimics the importance of attributes in social media posts to predict depressed mothers. Those mothers were anticipated to be depressed by answering a questionnaire designed by domain experts with prior knowledge of depression. This work will help researchers look at social media posts to find useful evidence for other depressive symptoms.

中文翻译：

---

利用社交媒体进行产后抑郁症危险因素分析的属性选择混合网络模型

产后抑郁症 (PPD) 是一种经常被忽视的与生育相关的后果。社交网络分析可以用来解决这个问题，因为社交媒体网络是用户与朋友交流并分享他们的观点、照片和视频的平台，这些反映了他们的心情、感受和情绪。在这项工作中，使用 PPD 评分来识别产妇的抑郁症，并将其分为对照组和抑郁组。最近，在检测抑郁症方面，深度学习方法发挥了至关重要的作用。然而，这些方法仍然无法阐明为什么有些人被诊断为抑郁症。我们开发了属性选择混合网络（ASHN）来检测产后抑郁症诊断框架。随后对已确认的母亲职位进行分析，并由该领域的专家使用生理问卷评分计算出分数。该模型致力于分析抑郁症用户诊断（一个大型综合论坛）的 Facebook 负面帖子的属性。该框架解释了分析包含情绪、抑郁症状和反思性思维的帖子的过程，并提出了帖子中抑郁症的心理语言和风格属性。实验结果表明ASHN效果良好且易于理解。在这里，基于心理学研究的四个属性网络被用来分析抑郁用户帖子的不同部分。实验结果表明，基于心理语言标记的属性的提取、包括精确度、召回率和 F1 分数在内的评估指标的记录以及这些属性的可视化均按标题和单词进行使用，并与日常生活进行比较，抑郁症和产后抑郁症患者使用词云。此外，还与 Baseline 和 ASHN 模型的参考进行了比较。属性选择混合网络（ASHN）模仿社交媒体帖子中属性的重要性来预测抑郁的母亲。通过回答由具有抑郁症先验知识的领域专家设计的调查问卷，预计这些母亲会患有抑郁症。这项工作将帮助研究人员查看社交媒体帖子，找到其他抑郁症状的有用证据。