scholarly journals Correction: Distant Supervision for Mental Health Management in Social Media: Suicide Risk Classification System Development Study

10.2196/33229 ◽  
2021 ◽  
Vol 23 (9) ◽  
pp. e33229
Author(s):  
Guanghui Fu ◽  
Changwei Song ◽  
Jianqiang Li ◽  
Yue Ma ◽  
Pan Chen ◽  
...  
Keyword(s):  
Mental Health ◽  
Social Media ◽  
Classification System ◽  
Suicide Risk ◽  
Health Management ◽  
System Development ◽  
Risk Classification ◽  
Development Study ◽  
Distant Supervision

scholarly journals Distant Supervision for Mental Health Management in Social Media: Suicide Risk Classification System Development Study

10.2196/26119 ◽  
2021 ◽  
Vol 23 (8) ◽  
pp. e26119
Author(s):  
Guanghui Fu ◽  
Changwei Song ◽  
Jianqiang Li ◽  
Yue Ma ◽  
Pan Chen ◽  
...  
Keyword(s):  
Social Media ◽  
Suicide Risk ◽  
Health Management ◽  
System Development ◽  
Common People ◽  
Web Based ◽  
Social Media Data ◽  
Distant Supervision ◽  
Data Source ◽  
Media Data

Background Web-based social media provides common people with a platform to express their emotions conveniently and anonymously. There have been nearly 2 million messages in a particular Chinese social media data source, and several thousands more are generated each day. Therefore, it has become impossible to analyze these messages manually. However, these messages have been identified as an important data source for the prevention of suicide related to depression disorder. Objective We proposed in this paper a distant supervision approach to developing a system that can automatically identify textual comments that are indicative of a high suicide risk. Methods To avoid expensive manual data annotations, we used a knowledge graph method to produce approximate annotations for distant supervision, which provided a basis for a deep learning architecture that was built and refined by interactions with psychology experts. There were three annotation levels, as follows: free annotations (zero cost), easy annotations (by psychology students), and hard annotations (by psychology experts). Results Our system was evaluated accordingly and showed that its performance at each level was promising. By combining our system with several important psychology features from user blogs, we obtained a precision of 80.75%, a recall of 75.41%, and an F1 score of 77.98% for the hardest test data. Conclusions In this paper, we proposed a distant supervision approach to develop an automatic system that can classify high and low suicide risk based on social media comments. The model can therefore provide volunteers with early warnings to prevent social media users from committing suicide.

Distant Supervision for Mental Health Management in Social Media: Suicide Risk Classification System Development Study (Preprint)

2020 ◽  
Author(s):  
Guanghui Fu ◽  
Changwei Song ◽  
Jianqiang Li ◽  
Yue Ma ◽  
Pan Chen ◽  
...  
Keyword(s):  
Social Media ◽  
Suicide Risk ◽  
Health Management ◽  
System Development ◽  
Common People ◽  
Web Based ◽  
Social Media Data ◽  
Distant Supervision ◽  
Data Source ◽  
Media Data

BACKGROUND Web-based social media provides common people with a platform to express their emotions conveniently and anonymously. There have been nearly 2 million messages in a particular Chinese social media data source, and several thousands more are generated each day. Therefore, it has become impossible to analyze these messages manually. However, these messages have been identified as an important data source for the prevention of suicide related to depression disorder. OBJECTIVE We proposed in this paper a distant supervision approach to developing a system that can automatically identify textual comments that are indicative of a high suicide risk. METHODS To avoid expensive manual data annotations, we used a knowledge graph method to produce approximate annotations for distant supervision, which provided a basis for a deep learning architecture that was built and refined by interactions with psychology experts. There were three annotation levels, as follows: free annotations (zero cost), easy annotations (by psychology students), and hard annotations (by psychology experts). RESULTS Our system was evaluated accordingly and showed that its performance at each level was promising. By combining our system with several important psychology features from user blogs, we obtained a precision of 80.75%, a recall of 75.41%, and an F1 score of 77.98% for the hardest test data. CONCLUSIONS In this paper, we proposed a distant supervision approach to develop an automatic system that can classify high and low suicide risk based on social media comments. The model can therefore provide volunteers with early warnings to prevent social media users from committing suicide.

scholarly journals Correction: Distant Supervision for Mental Health Management in Social Media: Suicide Risk Classification System Development Study (Preprint)

2021 ◽  
Author(s):  
Guanghui Fu ◽  
Changwei Song ◽  
Jianqiang Li ◽  
Yue Ma ◽  
Pan Chen ◽  
...  
Keyword(s):  
Social Media ◽  
Suicide Risk ◽  
Health Management ◽  
System Development ◽  
Common People ◽  
Web Based ◽  
Social Media Data ◽  
Distant Supervision ◽  
Data Source ◽  
Media Data

BACKGROUND Web-based social media provides common people with a platform to express their emotions conveniently and anonymously. There have been nearly 2 million messages in a particular Chinese social media data source, and several thousands more are generated each day. Therefore, it has become impossible to analyze these messages manually. However, these messages have been identified as an important data source for the prevention of suicide related to depression disorder. OBJECTIVE We proposed in this paper a distant supervision approach to developing a system that can automatically identify textual comments that are indicative of a high suicide risk. METHODS To avoid expensive manual data annotations, we used a knowledge graph method to produce approximate annotations for distant supervision, which provided a basis for a deep learning architecture that was built and refined by interactions with psychology experts. There were three annotation levels, as follows: free annotations (zero cost), easy annotations (by psychology students), and hard annotations (by psychology experts). RESULTS Our system was evaluated accordingly and showed that its performance at each level was promising. By combining our system with several important psychology features from user blogs, we obtained a precision of 80.75%, a recall of 75.41%, and an F1 score of 77.98% for the hardest test data. CONCLUSIONS In this paper, we proposed a distant supervision approach to develop an automatic system that can classify high and low suicide risk based on social media comments. The model can therefore provide volunteers with early warnings to prevent social media users from committing suicide.

scholarly journals Monitoring Online Discussions About Suicide Among Twitter Users With Schizophrenia: Exploratory Study (Preprint)

2018 ◽  
Author(s):  
Yulin Hswen ◽  
John A Naslund ◽  
John S Brownstein ◽  
Jared B Hawkins
Keyword(s):  
Mental Health ◽  
Social Media ◽  
Suicide Prevention ◽  
Exploratory Study ◽  
Suicide Risk ◽  
Elevated Risk ◽  
Online Discussions ◽  
Mental Health Symptoms ◽  
Health Symptoms ◽  
Twitter Users

BACKGROUND People with schizophrenia experience elevated risk of suicide. Mental health symptoms, including depression and anxiety, contribute to increased risk of suicide. Digital technology could support efforts to detect suicide risk and inform suicide prevention efforts. OBJECTIVE This exploratory study examined the feasibility of monitoring online discussions about suicide among Twitter users who self-identify as having schizophrenia. METHODS Posts containing the terms suicide or suicidal were collected from a sample of Twitter users who self-identify as having schizophrenia (N=203) and a random sample of control users (N=173) over a 200-day period. Frequency and timing of posts about suicide were compared between groups. The associations between posting about suicide and common mental health symptoms were examined. RESULTS Twitter users who self-identify as having schizophrenia posted more tweets about suicide (mean 7.10, SD 15.98) compared to control users (mean 1.89, SD 4.79; t374=-4.13, P<.001). Twitter users who self-identify as having schizophrenia showed greater odds of tweeting about suicide compared to control users (odds ratio 2.15, 95% CI 1.42-3.28). Among all users, tweets about suicide were associated with tweets about depression (r=0.62, P<.001) and anxiety (r=0.45, P<.001). CONCLUSIONS Twitter users who self-identify as having schizophrenia appear to commonly discuss suicide on social media, which is associated with greater discussion about other mental health symptoms. These findings should be interpreted cautiously, as it is not possible to determine whether online discussions about suicide correlate with suicide risk. However, these patterns of online discussion may be indicative of elevated risk of suicide observed in this patient group. There may be opportunities to leverage social media for supporting suicide prevention among individuals with schizophrenia.

scholarly journals Monitoring Online Discussions About Suicide Among Twitter Users With Schizophrenia: Exploratory Study

10.2196/11483 ◽  
2018 ◽  
Vol 5 (4) ◽  
pp. e11483 ◽  
Author(s):  
Yulin Hswen ◽  
John A Naslund ◽  
John S Brownstein ◽  
Jared B Hawkins
Keyword(s):  
Mental Health ◽  
Social Media ◽  
Suicide Prevention ◽  
Exploratory Study ◽  
Suicide Risk ◽  
Elevated Risk ◽  
Online Discussions ◽  
Mental Health Symptoms ◽  
Health Symptoms ◽  
Twitter Users

Background People with schizophrenia experience elevated risk of suicide. Mental health symptoms, including depression and anxiety, contribute to increased risk of suicide. Digital technology could support efforts to detect suicide risk and inform suicide prevention efforts. Objective This exploratory study examined the feasibility of monitoring online discussions about suicide among Twitter users who self-identify as having schizophrenia. Methods Posts containing the terms suicide or suicidal were collected from a sample of Twitter users who self-identify as having schizophrenia (N=203) and a random sample of control users (N=173) over a 200-day period. Frequency and timing of posts about suicide were compared between groups. The associations between posting about suicide and common mental health symptoms were examined. Results Twitter users who self-identify as having schizophrenia posted more tweets about suicide (mean 7.10, SD 15.98) compared to control users (mean 1.89, SD 4.79; t374=-4.13, P<.001). Twitter users who self-identify as having schizophrenia showed greater odds of tweeting about suicide compared to control users (odds ratio 2.15, 95% CI 1.42-3.28). Among all users, tweets about suicide were associated with tweets about depression (r=0.62, P<.001) and anxiety (r=0.45, P<.001). Conclusions Twitter users who self-identify as having schizophrenia appear to commonly discuss suicide on social media, which is associated with greater discussion about other mental health symptoms. These findings should be interpreted cautiously, as it is not possible to determine whether online discussions about suicide correlate with suicide risk. However, these patterns of online discussion may be indicative of elevated risk of suicide observed in this patient group. There may be opportunities to leverage social media for supporting suicide prevention among individuals with schizophrenia.

The Psychology behind Users Mental Health in Social Media

2018 ◽  
Vol 6 (5) ◽  
pp. 309-316
Author(s):  
D. Sridhar ◽  
◽  
◽  
V. Kathiresan
Keyword(s):  
Mental Health ◽  
Social Media

Social Media Use in College-age Youth: A Comprehensive Review and a Call to Action

2020 ◽  
Vol 9 (2) ◽  
pp. 128-143
Author(s):  
Hilary Holmes ◽  
Alba E. Lara ◽  
Gregory S. Brown
Keyword(s):  
Mental Health ◽  
Social Media ◽  
Media Use ◽  
Experimental Studies ◽  
Health Awareness ◽  
Social Media Use ◽  
Call To Action ◽  
College Age ◽  
Mental Health Awareness ◽  
Privacy Breaches

Background: Social media is a relatively new and impactful way to connect millions of people around the world. The intersection of mental health and social media is a poorly studied, yet important area of research. Specifically, with regard to college-aged youth, social media can potentially offer an educational tool to enhance mental health awareness or augment treatment when it is used for professional purposes by mental health advocates or healthcare professionals. There is also the added risk of disinformation, cyberbullying, and privacy breaches. Objective: This review aims to assess the current state of social media use and its influence on mental health, especially in college-age youth. Methods: The authors of this paper utilized PubMed and Medline databases to review the most recent experimental studies and literature reviews available on the topic of mental health and social media. Results: Abstracts and relevant papers were read in full, and information from these studies was cited accordingly. Conclusion: The authors conclude that although more research needs to be conducted, social media may offer benefits for mental health awareness, education, and treatment, specifically in populations such as college-age youth.

Sign in / Sign up

Export Citation Format

Share Document