Extracting depressive symptoms and their associations from an online depression community

Yu, Guang; Tang, Jingyun; Zhang, Jialing

doi:10.1016/j.chb.2021.106734

Cited by 25 publications

(10 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“… Graph model combined with Convolutional Neural Network 129 A unified hybrid model combining CNN with factor graph model which leverages social interactions and content. RNN-based methods LSTM or GRU (some with attention mechanism) 32 , 133 , 136 , 232 – 234 Standard RNN structure: Long Short-Term Memory networks(LSTM) or Gate Recurrent Unit(GRU), and some studies add attention mechanism. Hierarchical Attention Network (HAN) with GRU 138 The GRU with a word-level attention layer and a sentence-level attention layer.…”

Section: Resultsmentioning

confidence: 99%

Natural language processing applied to mental illness detection: a narrative review

et al. 2022

View full text Add to dashboard Cite

Mental illness is highly prevalent nowadays, constituting a major cause of distress in people’s life with impact on society’s health and well-being. Mental illness is a complex multi-factorial disease associated with individual risk factors and a variety of socioeconomic, clinical associations. In order to capture these complex associations expressed in a wide variety of textual data, including social media posts, interviews, and clinical notes, natural language processing (NLP) methods demonstrate promising improvements to empower proactive mental healthcare and assist early diagnosis. We provide a narrative review of mental illness detection using NLP in the past decade, to understand methods, trends, challenges and future directions. A total of 399 studies from 10,467 records were included. The review reveals that there is an upward trend in mental illness detection NLP research. Deep learning methods receive more attention and perform better than traditional machine learning methods. We also provide some recommendations for future studies, including the development of novel detection methods, deep learning paradigms and interpretable models.

show abstract

Section: Resultsmentioning

confidence: 99%

Natural language processing applied to mental illness detection: a narrative review

et al. 2022

View full text Add to dashboard Cite

show abstract

“…The accuracy of the automatic sentiment analysis was 81%. Further details about the identification of public emotional posting by a supervised learning process have been described elsewhere (Tian et al, 2016 ; Wang et al, 2018 ; Yao et al, 2020 , 2021 ). All sampled 20,114 Weibo posts were automatically classified with “optimistic orientation,” “pessimistic orientation,” or “neutral orientation” tags.…”

Section: Methodsmentioning

confidence: 99%

Capturing the Trajectory of Psychological Status and Analyzing Online Public Reactions During the Coronavirus Disease 2019 Pandemic Through Weibo Posts in China

et al. 2021

View full text Add to dashboard Cite

When a major, sudden infectious disease occurs, people tend to react emotionally and display reactions such as tension, anxiety, fear, depression, and somatization symptoms. Social media played a substantial awareness role in developing countries during the outbreak of coronavirus disease 2019 (COVID-19). This study aimed to analyze public opinion regarding COVID-19 and to explore the trajectory of psychological status and online public reactions to the COVID-19 pandemic by examining online content from Weibo in China. This study consisted of three steps: first, Weibo posts created during the pandemic were collected and preprocessed on a large scale; second, public sentiment orientation was classified as “optimistic/pessimistic/neutral” orientation via natural language processing and manual determination procedures; and third, qualitative and quantitative analyses were conducted to reveal the trajectory of public psychological status and online public reactions during the COVID-19 pandemic. Public psychological status differed in different periods of the pandemic (from December 2019 to May 2020). The newly confirmed cases had an almost 1-month lagged effect on public psychological status. Among the 15 events with high impact indexes or related to government decisions, there were 10 optimism orientation > pessimism orientation (OP) events (2/3) and 5 pessimism orientation > optimism orientation (PO) events (1/3). Among the top two OP events, the high-frequency words were “race against time” and “support,” while in the top two PO events, the high-frequency words were “irrationally purchase” and “pass away.” We proposed a hypothesis that people developed negative self-perception when they received PO events, but their cognition was developed by how these external stimuli were processed and evaluated. These results offer implications for public health policymakers on understanding public psychological status from social media. This study demonstrates the benefits of promoting psychological healthcare and hygiene activity in the early period and improving risk perception for the public based on public opinion and the coping abilities of people. Health managers should focus on disseminating socially oriented strategies to improve the policy literacy of Internet users, thereby facilitating the disease prevention work for the COVID-19 pandemic and other major public events.

show abstract

“…The main focus of this work was to use an auxiliary classification task to detect figurative speech that might be used to express symptoms and can be hard to detect via lexicon lookup. Yao et al [ 34 ] analyzed a Chinese depression forum for depression symptom prediction. Their work aimed to develop a comprehensive annotation scheme for a list of symptoms that goes beyond the diagnostic symptoms of DSM-5.…”

Section: Related Workmentioning

confidence: 99%

Towards automatic text-based estimation of depression through symptom prediction

2023

View full text Add to dashboard Cite

Major Depressive Disorder (MDD) is one of the most common and comorbid mental disorders that impacts a person’s day-to-day activity. In addition, MDD affects one’s linguistic footprint, which is reflected by subtle changes in speech production. This allows us to use natural language processing (NLP) techniques to build a neural classifier to detect depression from speech transcripts. Typically, current NLP systems discriminate only between the depressed and non-depressed states. This approach, however, disregards the complexity of the clinical picture of depression, as different people with MDD can suffer from different sets of depression symptoms. Therefore, predicting individual symptoms can provide more fine-grained information about a person’s condition. In this work, we look at the depression classification problem through the prism of the symptom network analysis approach, which shifts attention from a categorical analysis of depression towards a personalized analysis of symptom profiles. For that purpose, we trained a multi-target hierarchical regression model to predict individual depression symptoms from patient–psychiatrist interview transcripts from the DAIC-WOZ corpus. Our model achieved results on par with state-of-the-art models on both binary diagnostic classification and depression severity prediction while at the same time providing a more fine-grained overview of individual symptoms for each person. The model achieved a mean absolute error (MAE) from 0.438 to 0.830 on eight depression symptoms and showed state-of-the-art results in binary depression estimation (73.9 macro-F1) and total depression score prediction (3.78 MAE). Moreover, the model produced a symptom correlation graph that is structurally identical to the real one. The proposed symptom-based approach provides more in-depth information about the depressive condition by focusing on the individual symptoms rather than a general binary diagnosis.

show abstract

Extracting depressive symptoms and their associations from an online depression community

Cited by 25 publications

References 26 publications

Natural language processing applied to mental illness detection: a narrative review

Natural language processing applied to mental illness detection: a narrative review

Capturing the Trajectory of Psychological Status and Analyzing Online Public Reactions During the Coronavirus Disease 2019 Pandemic Through Weibo Posts in China

Towards automatic text-based estimation of depression through symptom prediction

Contact Info

Product

Resources

About