Research

12 pages, 871 KiB

Open AccessArticle

Linguistic Analysis for Identifying Depression and Subsequent Suicidal Ideation on Weibo: Machine Learning Approaches

by Wei Pan, Xianbin Wang, Wenwei Zhou, Bowen Hang and Liwen Guo

Int. J. Environ. Res. Public Health 2023, 20(3), 2688; https://doi.org/10.3390/ijerph20032688 - 02 Feb 2023

Cited by 1 | Viewed by 2204

Depression is one of the most common mental illnesses but remains underdiagnosed. Suicide, as a core symptom of depression, urgently needs to be monitored at an early stage, i.e., the suicidal ideation (SI) stage. Depression and subsequent suicidal ideation should be supervised on [...] Read more.

Depression is one of the most common mental illnesses but remains underdiagnosed. Suicide, as a core symptom of depression, urgently needs to be monitored at an early stage, i.e., the suicidal ideation (SI) stage. Depression and subsequent suicidal ideation should be supervised on social media. In this research, we investigated depression and concomitant suicidal ideation by identifying individuals’ linguistic characteristics through machine learning approaches. On Weibo, we sampled 487,251 posts from 3196 users from the depression super topic community (DSTC) as the depression group and 357,939 posts from 5167 active users on Weibo as the control group. The results of the logistic regression model showed that the SCLIWC (simplified Chinese version of LIWC) features such as affection, positive emotion, negative emotion, sadness, health, and death significantly predicted depression (Nagelkerke’s R² = 0.64). For model performance: F-measure = 0.78, area under the curve (AUC) = 0.82. The independent samples’ t-test showed that SI was significantly different between the depression (0.28 ± 0.5) and control groups (−0.29 ± 0.72) (t = 24.71, p < 0.001). The results of the linear regression model showed that the SCLIWC features, such as social, family, affection, positive emotion, negative emotion, sadness, health, work, achieve, and death, significantly predicted suicidal ideation. The adjusted R² was 0.42. For model performance, the correlation between the actual SI and predicted SI on the test set was significant (r = 0.65, p < 0.001). The topic modeling results were in accordance with the machine learning results. This study systematically investigated depression and subsequent SI-related linguistic characteristics based on a large-scale Weibo dataset. The findings suggest that analyzing the linguistic characteristics on online depression communities serves as an efficient approach to identify depression and subsequent suicidal ideation, assisting further prevention and intervention. Full article

(This article belongs to the Special Issue Suicide and Self-Harm Behavior on the Internet)

11 pages, 545 KiB

Open AccessArticle

Suicide Possibility Scale Detection via Sina Weibo Analytics: Preliminary Results

by Yun Gu, Deyuan Chen and Xiaoqian Liu

Int. J. Environ. Res. Public Health 2023, 20(1), 466; https://doi.org/10.3390/ijerph20010466 - 27 Dec 2022

Cited by 1 | Viewed by 1657

Abstract

Suicide, as an increasingly prominent social problem, has attracted widespread social attention in the mental health field. Traditional suicide clinical assessment and risk questionnaires lack timeliness and proactivity, and high-risk groups often conceal their intentions, which is not conducive to early suicide prevention. [...] Read more.

Suicide, as an increasingly prominent social problem, has attracted widespread social attention in the mental health field. Traditional suicide clinical assessment and risk questionnaires lack timeliness and proactivity, and high-risk groups often conceal their intentions, which is not conducive to early suicide prevention. In this study, we used machine-learning algorithms to extract text features from Sina Weibo data and built a suicide risk-prediction model to predict four dimensions of the Suicide Possibility Scale—hopelessness, suicidal ideation, negative self-evaluation, and hostility—all with model validity of 0.34 or higher. Through this method, we can detect the symptoms of suicidal ideation in a more detailed way and improve the proactiveness and accuracy of suicide risk prevention and control. Full article

(This article belongs to the Special Issue Suicide and Self-Harm Behavior on the Internet)

► Show Figures

Figure 1

11 pages, 1587 KiB

Open AccessArticle

Transition from Depression to Suicidal Attempt in Young Adults: The Mediation Effect of Self-Esteem and Interpersonal Needs

by Xingyun Liu, Miao Liu, He Li, Liuling Mo and Xiaoqian Liu

Int. J. Environ. Res. Public Health 2022, 19(21), 14342; https://doi.org/10.3390/ijerph192114342 - 02 Nov 2022

Cited by 2 | Viewed by 1541

Abstract

Background: Depression increases the risk of suicide. Depression and suicide attempts are significantly impacted by low self-esteem and interpersonal needs (i.e., thwarted belongingness (TB) and perceived burdensomeness (PB)). More research is required to clarify how these factors affected the change from depression to [...] Read more.

Background: Depression increases the risk of suicide. Depression and suicide attempts are significantly impacted by low self-esteem and interpersonal needs (i.e., thwarted belongingness (TB) and perceived burdensomeness (PB)). More research is required to clarify how these factors affected the change from depression to suicidal attempts, which would dramatically lower the suicide fatality rate. We sought to examine the mediating roles of self-esteem, TB, and PB in Chinese young adults, since previous research shows that self-esteem has a strong relationship with TB, while TB and PB have strong relationships with suicide attempts. Methods: Measures on depression, interpersonal needs, and attempted suicide were completed by a sample of 247 Chinese social media users who had stated suicidal ideation online. Results: The findings showed that people who attempted suicide had significantly higher levels of TB and PB. Suicidal attempts were also impacted by depression via the mediational chains, which included self-esteem, TB, and PB. Conclusions: Our findings might contribute to the expansion of the interpersonal theory of suicide and have an impact on effective suicide prevention. Full article

(This article belongs to the Special Issue Suicide and Self-Harm Behavior on the Internet)

► Show Figures

Figure 1

11 pages, 715 KiB

Open AccessArticle

The Relationship between Cyber-Ostracism and Adolescents’ Non-Suicidal Self-Injury: Mediating Roles of Depression and Experiential Avoidance

by Huimin Ding, Liyue Zhu, Hua Wei, Jingyu Geng, Feng Huang and Li Lei

Int. J. Environ. Res. Public Health 2022, 19(19), 12236; https://doi.org/10.3390/ijerph191912236 - 27 Sep 2022

Cited by 6 | Viewed by 2245

Abstract

Based on the experiential avoidance model, the current study aims to test the relationship between cyber-ostracism and adolescents’ non-suicidal self-injury and to explore the mediating roles of depression and experiential avoidance. A sample of 1062 middle school students completed questionnaires on cyber-ostracism, depression, [...] Read more.

Based on the experiential avoidance model, the current study aims to test the relationship between cyber-ostracism and adolescents’ non-suicidal self-injury and to explore the mediating roles of depression and experiential avoidance. A sample of 1062 middle school students completed questionnaires on cyber-ostracism, depression, experiential avoidance, and self-injurious behavior. The results showed that cyber-ostracism, depression, experiential avoidance, and non-suicidal self-injury were positively correlated with each other. After controlling for gender and age, the mediation model test shows that cyber-ostracism was significantly and positively associated with non-suicidal self-injury. Depression and experiential avoidance mediated the relationship between cyber-ostracism and non-suicidal self-injury parallelly and sequentially. This study highlights the potential mechanisms of action between cyber-ostracism and adolescent non-suicidal self-injury and finds that cyber-ostracism is a risk factor for non-suicidal self-injury. This founding suggests that extra attention should be paid to the role of the online environment in addition to the offline environment experiences for the intervention of non-suicidal self-injury. Full article

(This article belongs to the Special Issue Suicide and Self-Harm Behavior on the Internet)

► Show Figures

Figure 1

11 pages, 1643 KiB

Open AccessArticle

Exploring the Suicide Mechanism Path of High-Suicide-Risk Adolescents—Based on Weibo Text Analysis

by Liuling Mo, He Li and Tingshao Zhu

Int. J. Environ. Res. Public Health 2022, 19(18), 11495; https://doi.org/10.3390/ijerph191811495 - 13 Sep 2022

Cited by 1 | Viewed by 2840

Abstract

Background: Adolescent suicide can have serious consequences for individuals, families and society, so we should pay attention to it. As social media becomes a platform for adolescents to share their daily lives and express their emotions, online identification and intervention of adolescent suicide [...] Read more.

Background: Adolescent suicide can have serious consequences for individuals, families and society, so we should pay attention to it. As social media becomes a platform for adolescents to share their daily lives and express their emotions, online identification and intervention of adolescent suicide problems become possible. In order to find the suicide mechanism path of high-suicide-risk adolescents, we explore the factors that influence is, especially the relations between psychological pain, hopelessness and suicide stages. Methods: We identified high-suicide-risk adolescents through machine learning model identification and manual identification, and used the Weibo text analysis method to explore the suicide mechanism path of high-suicide-risk adolescents. Results: Qualitative analysis showed that 36.2% of high-suicide-risk adolescents suffered from mental illness, and depression accounted for 76.3% of all mental illnesses. The mediating effect analysis showed that hopelessness played a complete mediating role between psychological pain and suicide stages. In addition, hopelessness was significantly negatively correlated with suicide stages. Conclusion: mental illness (especially depression) in high-suicide-risk adolescents is closely related to suicide stages, the later the suicide stage, the higher the diagnosis rate of mental illness. The suicide mechanism path in high-suicide-risk adolescents is: psychological pain→ hopelessness → suicide stages, indicating that psychological pain mainly affects suicide risk through hopelessness. Adolescents who are later in the suicide stages have fewer expressions of hopelessness in the traditional sense. Full article

(This article belongs to the Special Issue Suicide and Self-Harm Behavior on the Internet)

► Show Figures

Figure 1

15 pages, 1710 KiB

Open AccessArticle

The Impact of Mortality Salience, Negative Emotions and Cultural Values on Suicidal Ideation in COVID-19: A Conditional Process Model

by Feng Huang, Sijia Li, Dongqi Li, Meizi Yang, Huimin Ding, Yazheng Di and Tingshao Zhu

Int. J. Environ. Res. Public Health 2022, 19(15), 9200; https://doi.org/10.3390/ijerph19159200 - 27 Jul 2022

Cited by 5 | Viewed by 1799

Abstract

As suicides incurred by the COVID-19 outbreak keep happening in many countries, researchers have raised concerns that the ongoing pandemic may lead to “a wave of suicides” in society. Suicidal ideation (SI) is a critical factor in conducting suicide intervention and also an [...] Read more.

As suicides incurred by the COVID-19 outbreak keep happening in many countries, researchers have raised concerns that the ongoing pandemic may lead to “a wave of suicides” in society. Suicidal ideation (SI) is a critical factor in conducting suicide intervention and also an important indicator for measuring people’s mental health. Therefore, it is vital to identify the influencing factors of suicidal ideation and its psychological mechanism during the outbreak. Based on the terror management theory, in the present study we conducted a social media big data analysis to explore the joint effects of mortality salience (MS), negative emotions (NE), and cultural values on suicidal ideation in 337 regions on the Chinese mainland. The findings showed that (1) mortality salience was a positive predictor of suicidal ideation, with negative emotions acting as a mediator; (2) individualism was a positive moderator in the first half-path of the mediation model; (3) collectivism was a negative moderator in the first half-path of the mediation model. Our findings not only expand the application of the terror management theory in suicide intervention but provide some insights into post-pandemic mental healthcare. Timely efforts are needed to provide psychological interventions and counseling on outbreak-caused negative emotions in society. Compared with people living in collectivism-prevailing regions, those living in individualism-prevailing regions may be more vulnerable to mortality salience and negative emotions and need more social attention. Full article

(This article belongs to the Special Issue Suicide and Self-Harm Behavior on the Internet)

► Show Figures

Figure 1

13 pages, 572 KiB

Open AccessArticle

Detecting Suicidal Ideation in Social Media: An Ensemble Method Based on Feature Fusion

by Jingfang Liu, Mengshi Shi and Huihong Jiang

Int. J. Environ. Res. Public Health 2022, 19(13), 8197; https://doi.org/10.3390/ijerph19138197 - 05 Jul 2022

Cited by 8 | Viewed by 2654

Abstract

Suicide has become a serious problem, and how to prevent suicide has become a very important research topic. Social media provides an ideal platform for monitoring suicidal ideation. This paper presents an integrated model for multidimensional information fusion. By integrating the best classification [...] Read more.

Suicide has become a serious problem, and how to prevent suicide has become a very important research topic. Social media provides an ideal platform for monitoring suicidal ideation. This paper presents an integrated model for multidimensional information fusion. By integrating the best classification models determined by single and multiple features, different feature information is combined to better identify suicidal posts in online social media. This approach was assessed with a dataset formed from 40,222 posts annotated by Weibo. By integrating the best classification model of single features and multidimensional features, the proposed model ((BSC + RFS)-fs, WEC-fs) achieved 80.61% accuracy and a 79.20% F1-score. Other representative text information representation methods and demographic factors related to suicide may also be important predictors of suicide, which were not considered in this study. To the best of our knowledge, this is the good try that feature combination and ensemble algorithms have been fused to detect user-generated content with suicidal ideation. The findings suggest that feature combinations do not always work well, and that an appropriate combination strategy can make classification models work better. There are differences in the information contained in different functional carriers, and a targeted choice classification model may improve the detection rate of suicidal ideation. Full article

(This article belongs to the Special Issue Suicide and Self-Harm Behavior on the Internet)

► Show Figures

Figure 1

9 pages, 620 KiB

Open AccessArticle

Internet Addiction as a Moderator of the Relationship between Cyberhate Severity and Decisional Forgiveness

by Justyna Mróz and Kinga Kaleta

Int. J. Environ. Res. Public Health 2022, 19(10), 5844; https://doi.org/10.3390/ijerph19105844 - 11 May 2022

Cited by 2 | Viewed by 1548

Abstract

(1) Background: Cyberhate is becoming increasingly prevalent, just as Internet addiction. One way to deal with hate speech may be to make a decision to forgive the offence. However, addiction to the Internet, due to cognitive changes caused, can play a role in [...] Read more.

(1) Background: Cyberhate is becoming increasingly prevalent, just as Internet addiction. One way to deal with hate speech may be to make a decision to forgive the offence. However, addiction to the Internet, due to cognitive changes caused, can play a role in the making of this decision. (2) Methods: A total of N = 246 participants completed the Online Cognitive Scale (OCS), Decision to Forgive Scale (DTFS), and a single-item scale to assess cyberhate severity. In our cross-sectional study, we tested the moderating role of Internet addiction in the relationship between the severity of cyberhate and decisional forgiveness. (3) Results: The results of our study show an inverse correlation between cyberhate severity and decisional forgiveness. We found that Internet addiction moderated the relationship between the perceived severity of cyberhate and forgiveness. In case of a high level of Internet addiction, the transgression severity–forgiveness link is not significant. (4) Conclusions: These results are in accordance with the studies that showed the negative effects of Internet addiction on cognitive processes. Full article

(This article belongs to the Special Issue Suicide and Self-Harm Behavior on the Internet)

► Show Figures

Figure 1

12 pages, 826 KiB

Open AccessArticle

The Relation between Neuroticism and Non-Suicidal Self-Injury Behavior among College Students: Multiple Mediating Effects of Emotion Regulation and Depression

by Chengju Liao, Xingmei Gu, Jie Wang, Kuiliang Li, Xiaoxia Wang, Mengxue Zhao and Zhengzhi Feng

Int. J. Environ. Res. Public Health 2022, 19(5), 2885; https://doi.org/10.3390/ijerph19052885 - 02 Mar 2022

Cited by 11 | Viewed by 3179

Abstract

Background: Non-suicidal self-injury (NSSI) behavior among college students is a focus of attention in current society. In the information era, the Internet serves as a public health concern and as an effective pathway for prevention. In order to reduce NSSI behavior, we explore [...] Read more.

Background: Non-suicidal self-injury (NSSI) behavior among college students is a focus of attention in current society. In the information era, the Internet serves as a public health concern and as an effective pathway for prevention. In order to reduce NSSI behavior, we explore its influence factors, especially the relations between neuroticism, emotion regulation (ER), depression, and NSSI behavior. Methods: A total of 450 college students were surveyed with the Big Five Inventory-2, Emotion Regulation Questionnaire, Self-Rating Depression Scale, and Adolescent Non-Suicidal Self-Injury Assessment Questionnaire. Results: Regression analysis showed that neuroticism significantly negatively predicted emotion regulation, while it positively predicted depression and NSSI. Multiple mediation modeling demonstrated that neuroticism and emotion regulation had no significant direct effects on NSSI. However, neuroticism could indirectly affect NSSI through four pathways of multiple mediating effects, including depression, cognitive reappraisal-depression, expressive suppression-depression, and cognitive reappraisal-expressive suppression-depression. Conclusions: Neuroticism positively predicts depression and NSSI behavior, and affects NSSI through the mediating effect of ER and depression. Therefore, amelioration of neuroticism from the perspectives of emotion regulation and depression is recommended, so as to reduce NSSI behavior among college students with highly neurotic personalities. Full article

(This article belongs to the Special Issue Suicide and Self-Harm Behavior on the Internet)

► Show Figures

Figure 1

Journal Menu

Journal Browser

Suicide and Self-Harm Behavior on the Internet

Share This Special Issue

Special Issue Editors

Special Issue Information

Keywords

Published Papers (9 papers)

Research

Further Information

Guidelines

MDPI Initiatives

Follow MDPI