杂志文章%@ 2561-326X %I JMIR出版物%V 6 %N 卡塔尔世界杯8强波胆分析9 %P使用孟加拉社交媒体关于精神健康的帖子检测抑郁症的严重程度:使用自然语言处理技术研究%A Kabir,Muhammad Khubayeeb %A Islam,Maisha %A Kabir,Anika Nahian Binte %A Haque,Adiba %A Rhaman,Md Khalilur %+布拉克大学计算机科学系，66 Mohakhali，达卡，1212，孟加拉国，880 1708812609，muhammad.khubayeeb.kabir@g.bracu.ac.bd %K心理健康论坛%K自然语言处理%K严重性%K重度抑郁症%K深度学习%K机器学习%K多类文本分类%D 2022 %7 28.9.2022 %9原创论文%J JMIR Form Res %G英语%X背景:在书面文本中，有无数的语言线索表明抑郁，自然语言处理(NLP)研究人员已经证明了机器学习和深度学习方法检测这些线索的能力。然而，到目前为止，这些为孟加拉文学连接国家语言处理和心理健康领域的方法并不全面。说孟加拉语的人可以用他们的母语更详细地表达情感。目的:我们的目标是通过生成新的孟加拉语抑郁帖子语料库来检测使用孟加拉语文本的抑郁严重程度。我们与心理健康专家合作，生成了一个临床可靠的标签方案和一个注释语料库，用于训练机器学习和深度学习模型。方法:我们使用来自博客和开源平台的基于孟加拉语文本的数据进行研究。我们构建了一个生成注释语料库的程序，并从孟加拉语文献中提取文本信息进行预测分析。 We developed our own structured data set and designed a clinically sound labeling scheme with the help of mental health professionals, adhering to the Diagnostic and Statistical Manual of Mental Disorders, Fifth Edition (DSM-5) during the process. We used 5 machine learning models for detecting the severity of depression: kernel support vector machine (SVM), random forest, logistic regression K-nearest neighbor (KNN), and complement naive Bayes (NB). For the deep learning approach, we used long short-term memory (LSTM) units and gated recurrent units (GRUs) coupled with convolutional blocks or self-attention layers. Finally, we aimed for enhanced outcomes by using state-of-the-art pretrained language models. Results: The independent recurrent neural network (RNN) models yielded the highest accuracies and weighted F1 scores. GRUs, in particular, produced 81% accuracy. The hybrid architectures could not surpass the RNNs in terms of performance. Kernel SVM with term frequency–inverse document frequency (TF-IDF) embeddings generated 78% accuracy on test data. We used validation and training loss curves to observe and report the performance of our architectures. Overall, the number of available data remained the limitation of our experiment. Conclusions: The findings from our experimental setup indicate that machine learning and deep learning models are fairly capable of assessing the severity of mental health issues from texts. For the future, we suggest more research endeavors to increase the volume of Bengali text data, in particular, so that modern architectures reach improved generalization capability. %M 36169989 %R 10.2196/36118 %U https://formative.www.mybigtv.com/2022/9/e36118 %U https://doi.org/10.2196/36118 %U http://www.ncbi.nlm.nih.gov/pubmed/36169989