Suicide Risk Factors: A Language Analysis Approach in Social Media

Sierra, Gerardo; Andrade-Palos, Patricia; Bel-Enguix, Gemma; Osornio-Arteaga, Alejandro; Cabrera-Mora, Adriana; García-Nieto, Luis; Sierra-Aparicio, Tamara

doi:10.1177/0261927x211036171

Cited by 13 publications

(4 citation statements)

References 36 publications

(55 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The research literature on STB has exploded in the past several years with an impressive array of descriptive analyses and modeling efforts aiming to better detect (Renjith et al, 2022), predict (Roy et al, 2020), describe (Sierra et al, 2022), and explain (Unruh-Dawes et al, 2022) suicidal phenomenology through the leverage of online social media and the "big data" afforded by web-based communication platforms. Given the nature of the medium, natural language processing (NLP) has emerged as a prominent analytical tool, effectively paired with a variety of other cutting-edge quantitative approaches such as network analysis (Sawhney et al, 2022) and machine learning (Castillo-Sánchez et al, 2020).…”

Section: Introductionmentioning

confidence: 99%

The Hidden Depths of Suicidal Discourse: Network Analysis and Natural Language Processing Unmask Uncensored Expression

Lekkas¹,

Jacobson²

2023

Preprint

View full text Add to dashboard Cite

Background: The socially unattractive and stigmatizing nature of suicidal thought and behavior (STB) makes it especially susceptible to censorship across most modern digital communication platforms. The ubiquitous integration of technology with day-to-day life has presented an invaluable opportunity to leverage unprecedented amounts of data to study STB, yet the complex etiologies and consequences of censorship for research within mainstream online communities render an incomplete picture of STB manifestation. Analyses targeting online written content of suicidal users in environments where fear of reproach is mitigated may provide novel insight into modern trends and signals of STB expression.Methods: Complete written content of N=192 users, including n=48 identified as potential suicide completers/highest-risk users (HRUs), on the pro-choice suicide forum, Sanctioned Suicide, was modeled using a combination of lexicon-based topic modeling (EMPATH) and exploratory network analysis techniques to characterize and highlight prominent aspects of censorship-free suicidal discourse. Results: Modeling of over 2 million tokens across 37,136 forum posts found higher frequency of positive emotion and optimism among HRUs, emphasis on methods seeking and sharing behaviors, prominence of previously undocumented jargon, and semantics related to loneliness and life adversity.Limitations: Context (e.g., negation, irony) and words of posts not contained within the EMPATH lexicon could not be considered. Anonymity of Sanctioned Suicide precluded assessments of sociodemographic representation and generalizability. Conclusions: This NLP- and network-driven exposé of online STB subculture uncovered trends that deserve further attention within suicidology as they may be able to bolster detection, intervention, and prevention of suicidal outcomes and exposures.

show abstract

Section: Introductionmentioning

confidence: 99%

The Hidden Depths of Suicidal Discourse: Network Analysis and Natural Language Processing Unmask Uncensored Expression

Lekkas¹,

Jacobson²

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Applying a combination of natural language processing (Brown et al, 2019), network analysis (Kemp & Collings, 2011), and machine learning techniques (Tadesse et al, 2020), among others, research has demonstrated the ability to extract meaningful signals of STB from the content and behaviors reflected in online activity. Works have applied and tested prominent suicide theories (Unruh-Dawes et al, 2022), highlighted important semantic features (Sierra et al, 2022), characterized conversational topics (Grant et al, 2018), profiled emotion (Ren et al, 2016), studied information flow (Kemp & Collings, 2011), and probed one or more specific concepts such as stigma (Li et al, 2018), anti-mattering (Deas et al, 2023), and negative social comparison (Spitzer et al, 2023). The richness of the data that drive these endeavors is owed in part to source ubiquity and ease of access, the potential for interactive anonymity, and a temporal density of sampling that typically characterizes a "passively collected" record of internet activity.…”

Section: Introductionmentioning

confidence: 99%

Breaking the Silence: Leveraging Social Interaction Data to Identify High-Risk Suicide Users Online Using Network Analysis and Machine Learning

Lekkas¹,

Jacobson²

2023

Preprint

View full text Add to dashboard Cite

Suicidal thought and behavior (STB) is highly stigmatized and taboo. Prone to censorship, yet pervasive online, the development of uniquely insightful digital markers can be used to improve STB risk detection and aid a globally ailing population. Focusing on Sanctioned Suicide, an online pro-choice suicide forum, this work developed a social network-based operationalization of community engagement to derive 17 egocentric network features that captured the social dynamics of interaction within this uniquely uncensored community. Using network data generated from over 3.2 million unique interactions of N=192 individuals, n=48 of which were determined to be highest risk users (HRUs), a machine learning classification model was trained and validated to predict HRU status. Model prediction dynamics were analyzed using introspection techniques to uncover patterns in feature influence and highlight social phenomena. The model achieved an AUC=0.73 ([0.66, 0.8], 95% C.I.), suggesting that network-based socio-behavioral patterns of online interaction can signal heightened suicide risk. Transitivity, density, and in-degree centrality were among the most important features driving this performance. Their patterns of influence suggested that HRUs tended to be targets of social exchanges with lesser frequency and possessed egocentric networks with “small world” network properties. This research contributes to the modern efforts of data-driven suicidology through the implementation and assessment of an underutilized method on an unlikely data source. Findings support future incorporation of network-based social interaction features in STB research and highlight foci for further consideration within descriptive, predictive, and preventative pipelines.

show abstract

“…Miyagi et al [19] highlighted the potential for social media-based prevention measures to be undermined by the proliferation of offensive opinions and nonpreventive advertisements following a high-profile suicide-related incident. Numerous other studies have corroborated the association between social media use and suicide risk, further emphasizing the need for a comprehensive understanding of this complex relationship [20][21][22][23][24]. Nonetheless, regulating suicide-related information on these platforms is challenging due to the vast number of users and limited oversight.…”

Section: Introductionmentioning

confidence: 99%

Assessing Vulnerability to Surges in Suicide-Related Tweets Using Japan Census Data: Case-Only Study

Mitsuhashi¹

2023

JMIR Form Res

View full text Add to dashboard Cite

Background As the use of social media becomes more widespread, its impact on health cannot be ignored. However, limited research has been conducted on the relationship between social media and suicide. Little is known about individuals’ vulnerable to suicide, especially when social media suicide information is extremely prevalent. Objective This study aims to identify the characteristics underlying individuals’ vulnerability to suicide brought about by an increase in suicide-related tweets, thereby contributing to public health. Methods A case-only design was used to investigate vulnerability to suicide using individual data of people who died by suicide and tweet data from January 1, 2011, through December 31, 2014. Mortality data were obtained from Japanese government statistics, and tweet data were provided by a commercial service. Tweet data identified the days when suicide-related tweets surged, and the date-keyed merging was performed by considering 3 and 7 lag days. For the merged data set for analysis, the logistic regression model was fitted with one of the personal characteristics of interest as a dependent variable and the dichotomous exposure variable. This analysis was performed to estimate the interaction between the surges in suicide-related tweets and personal characteristics of the suicide victims as case-only odds ratios (ORs) with 95% CIs. For the sensitivity analysis, unexpected deaths other than suicide were considered. Results During the study period, there were 159,490 suicides and 115,072 unexpected deaths, and the number of suicide-related tweets was 2,804,999. Following the 3-day lag of a highly tweeted day, there were significant interactions for those who were aged 40 years or younger (OR 1.09, 95% CI 1.03-1.15), male (OR 1.12, 95% CI 1.07-1.18), divorced (OR 1.11, 95% CI 1.03 1.19), unemployed (OR 1.12, 95% CI 1.02-1.22), and living in urban areas (OR 1.26, 95% CI 1.17 1.35). By contrast, widowed individuals had significantly lower interactions (OR 0.83, 95% CI 0.77-0.89). Except for unemployment, significant relationships were also observed for the 7-day lag. For the sensitivity analysis, no significant interactions were observed for other unexpected deaths in the 3-day lag, and only the widowed had a significantly larger interaction than those who were married (OR 1.08, 95% CI 1.02-1.15) in the 7-day lag. Conclusions This study revealed the interactions of personal characteristics associated with susceptibility to suicide-related tweets. In addition, a few significant relationships were observed in the sensitivity analysis, suggesting that such an interaction is specific to suicide deaths. In other words, individuals with these characteristics, such as being young, male, unemployed, and divorced, may be vulnerable to surges in suicide-related tweets. Thus, minimizing public health strain by identifying people who are vulnerable and susceptible to a surge in suicide-related information on the internet is necessary.

show abstract

Suicide Risk Factors: A Language Analysis Approach in Social Media

Cited by 13 publications

References 36 publications

The Hidden Depths of Suicidal Discourse: Network Analysis and Natural Language Processing Unmask Uncensored Expression

The Hidden Depths of Suicidal Discourse: Network Analysis and Natural Language Processing Unmask Uncensored Expression

Breaking the Silence: Leveraging Social Interaction Data to Identify High-Risk Suicide Users Online Using Network Analysis and Machine Learning

Assessing Vulnerability to Surges in Suicide-Related Tweets Using Japan Census Data: Case-Only Study

Contact Info

Product

Resources

About