Suicidality Detection on Social Media Using Metadata and Text Feature Extraction and Machine Learning

Jung, Woojin; Kim, Dong-Hun; Nam, Seojin; Zhu, Yongjun

doi:10.1080/13811118.2021.1955783

Cited by 5 publications

(3 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The crawled data included the user ID, post content, post timestamp, reply content, reply timestamp, number of followers, number of followings, and number of posts. We calculated sentiment scores of the crawled posts using KnuSentiLex (On et al, 2018), a Python library for Korean sentiment analysis, which was utilized by several studies (e.g., Jung et al, 2021;Park et al, 2019;Shin et al, 2021). We calculated each post's sentiment score and then classified them into positive or negative groups.…”

Section: Social Media Datamentioning

confidence: 99%

Interpretable machine learning‐based approaches for understanding suicide risk and protective factors among South Korean females using survey and social media data

Kim

Quan

Seo

et al. 2023

Suicide & Life Threat Behav

View full text Add to dashboard Cite

Objective We aimed to identify and understand risk and protective factors for suicide among South Korean females by linking survey and social media data and using interpretable machine learning approaches. Materials and Methods We collected a wide range of potential factors including the material, psychosocial, and behavioral data from a detailed survey, which we then linked to data from social media. In addition, we adopted interpretable machine learning approaches to (1) predict the suicide risk, (2) explain the relative importance of factors and their interactions regarding suicide, and (3) understand individual differences affecting suicide risk. Results The best‐performing machine learning model achieved an AUC of 0.737. Adverse childhood experiences, social connectedness, and mean positive sentiment score of social media posts were the three risk factors that had a monotonic or unimodal relationship with suicide, and satisfaction with life, narcissistic self‐presentation, and number of close friends on social media were the three protective factors that had a monotonic or unimodal relationship with suicide. We also found several meaningful interactions between specific psychiatric symptoms and narcissistic self‐presentation. Conclusions Our findings can help governmental organizations to better assess female suicide risk in South Korea and develop more informed and customized suicide prevention strategies.

show abstract

Section: Social Media Datamentioning

confidence: 99%

Interpretable machine learning‐based approaches for understanding suicide risk and protective factors among South Korean females using survey and social media data

Kim

Quan

Seo

et al. 2023

Suicide & Life Threat Behav

View full text Add to dashboard Cite

show abstract

“…The system attained an accuracy of 0.71%, lower than the models we surveyed in the literature. Woojin Jung et al [20] presented an RF and gradient boosting machine (GBM) for suicidal ideation detection. The system collected the data from Twitter, and preprocessing operations, such as the removal of stop words and hyperlinks, were performed.…”

Section: Mohamed Ali Ben Hassine Et Al [19]mentioning

confidence: 99%

Suicidal Ideation Detection from social media: A Detailed Review of Machine Learning and Deep Learning

Seby,

Elamparithi,

Anuratha

2023

ijmst

View full text Add to dashboard Cite

Social networks are crucial tools for learning about people's attitudes towards various issues since they allow them to express their thoughts to friends and family. Recent years have seen considerable challenges in natural language processing (NLP) and psychology regarding the detection of suicidal ideation via online social network analysis. The complex early signs of suicide ideations can be identified with the proper use of social media information, which can afterwards save many lives. Even though numerous strategies have been used over the past few decades to identify suicidal thoughts, machine learning (ML) and deep learning (DL) methods offer more insightful results. So, in this study, we examine several cutting-edge ML and DL approaches for detecting suicidal ideation. We also observe a few significant issues in the entire corpus of literature that could be explored in further research. Finally, we hope this study will shed light on critical issues in identifying suicidal thoughts on social media for readers and ML and DL researchers.

show abstract

“…In 2021, Jung et al [15] implemented a suicidality detection model for Twitter data using a machine learning approach. They randomly selected 20,000 tweets and analyzed metadata and text features to build this effective model.…”

Section: Literature Reviewmentioning

confidence: 99%

Perceived Factors Analysis for Depression and Suicidal Ideation among Bangladeshi University Students Using Association Algorithm

Alam,

Ejaz,

Hasan

et al. 2023

AJRCoS

View full text Add to dashboard Cite

Depression stands as a prominent and prevalent mental health issue, representing a significant global public health concern. Its emergence can be attributed to diverse factors. Suicide stands as a prominent global cause of death, eliciting concern on a widespread scale. This study was to analyze the perceived factors for depression and suicidal ideation among Bangladeshi university students in Bangladesh. There are so many factors such as Loneliness, Hopelessness, Helplessness, Relationship Issues, Grade problems, Academic Pressure, Parental problems, Money problems, Social Comparison, Social Media Influence, Family Expectations, Lack of Sleep, Uncertain Future, Health Issues, Bullying, Substance Abuse and Unemployment etc. These factors vary among male and female students. Apriori association algorithm were used to calculate support, confidence and lift of factors sets. Frequent factors sets and relationship were found from the work using Apriori association algorithm. The work is an online survey-based study about psychological and stress status of participants and statistical analysis is used for concluding the results. The research participants are Bangladeshi university students, Data collection carried out by online questionnaire. The findings from data analysis indicated that academic pressure (72.41%), uncertain future (56.32%), hopelessness (48.28%), family expectation (47.13%), financial crisis (42.53%), loneliness (41.38%) and unemployment (37.93%) are the key factors. The prevention of suicides is achievable. Hence, identifying depression and forecasting the potential for suicide risk serves as a means to prevent instances of self-harm within the university student population.

show abstract

Suicidality Detection on Social Media Using Metadata and Text Feature Extraction and Machine Learning

Cited by 5 publications

References 37 publications

Interpretable machine learning‐based approaches for understanding suicide risk and protective factors among South Korean females using survey and social media data

Interpretable machine learning‐based approaches for understanding suicide risk and protective factors among South Korean females using survey and social media data

Suicidal Ideation Detection from social media: A Detailed Review of Machine Learning and Deep Learning

Perceived Factors Analysis for Depression and Suicidal Ideation among Bangladeshi University Students Using Association Algorithm

Contact Info

Product

Resources

About