A machine learning approach to detect potentially harmful and protective suicide-related content in broadcast media.

Suicide-related media content has preventive or harmful effects depending on the specific content. Proactive media screening for suicide prevention is hampered by the scarcity of machine learning approaches to detect specific characteristics in news reports. This study applied machine learning to label large quantities of broadcast (TV and radio) media data according to media recommendations reporting suicide. We manually labeled 2519 English transcripts from 44 broadcast sources in Oregon and Washington, USA, published between April 2019 and March 2020. We conducted a content analysis of media reports regarding content characteristics. We trained a benchmark of machine learning models including a majority classifier, approaches based on word frequency (TF-IDF with a linear SVM) and a deep learning model (BERT). We applied these models to a selection of more simple (e.g., focus on a suicide death), and subsequently to putatively more complex tasks (e.g., determining the main focus of a text from 14 categories). Tf-idf with SVM and BERT were clearly better than the naive majority classifier for all characteristics. In a test dataset not used during model training, F1-scores (i.e., the harmonic mean of precision and recall) ranged from 0.90 for celebrity suicide down to 0.58 for the identification of the main focus of the media item. Model performance depended strongly on the number of training samples available, and much less on assumed difficulty of the classification task. This study demonstrates that machine learning models can achieve very satisfactory results for classifying suicide-related broadcast media content, including multi-class characteristics, as long as enough training samples are available. The developed models enable future large-scale screening and investigations of broadcast media.

Suicide-Related Media Reporting With a Focus on Sexual and Gender Minority Identities.

Background: Little is known about the quality of media reports on suicide and prevention targeting persons with sexual or gender minority identities (LGBTQ+). Aims: To assess the quality of suicide-related media reporting of LGBTQ+ people and its consistency with media guidelines. Method: We conducted a content analysis of 5,652 media items in two US states (Washington and Oregon) published within 1 year. Results: There were only few differences in the reporting about suicide in LGBTQ+ as compared to non-LGBTQ+ reports. LGBTQ+ media items more often portrayed suicide as monocausal [Oregon: OR = 1.75, 95% CI (1.03-2.98), p = .038; Washington: OR = 3.00, 95% CI (1.81-4.97), p < .001] and linked them to adverse life experiences [OR = 2.16, 95% CI (1.38-3.38), p < .001; OR = 2.09, 95% CI (1.30-3.38), p = .002] than non-LGBTQ+ items. They also more often featured mental health experts [OR = 1.79, 95% CI (1.04-3.10), p = .034; OR = 2.12, 95% CI (1.23-3.67), p = .006] and contacts to support services [OR = 2.22, 95% CI (1.41-3.48), p < .001; OR = 2.70, 95% CI (1.64-4.45), p < .001]. Limitations: Aspects possibly influencing the portrayal of LGBTQ+ suicide and prevention beyond the characteristics listed were not investigated. Conclusion: Suicide-related media reporting related to LGBTQ+ issues features potentially beneficial aspects but tends to overlook multifactorial causes of suicide. Diverse factors contributing to LGBTQ+ suicide and prevention warrant greater attention.

"Breaking the Silence" Suicide Prevention Media Campaign in Oregon, April 7-14, 2019.

Background: Between April 7 and 14, 2019, the "Breaking the Silence" media engagement campaign was launched in Oregon. Aims: We aimed to assess the consistency of media content related to the campaign with media guidelines and the quantitative footprint on Twitter (now X) over time. Method: Media items related to the campaign were analyzed regarding focus and consistency with media guidelines for suicide reporting and compared with other suicide-related reports published in the same time frame, as well as with reporting in Washington, the control region. Tweets related to the campaign were retrieved to assess the social media footprint. Results: There were n = 104 media items in the campaign month, mainly in the campaign week. Items typically used a narrative featuring suicide advocacy or policy/prevention programs. As compared to other items with a similar focus, they scored better on several protective characteristics listed in media recommendations. Stories of coping with adversity, however, were scarce. The social media footprint on Twitter was small. Limitations: Inability to make causal claims about campaign impact. Conclusion: Media items from the Breaking the Silence campaign appeared mainly consistent with media guidelines, but some aspects, such as stories of recovery, were under-represented.

Associations of Suicide Referents With Different Moral Connotation With Actual Suicides.

Background: Different words used for suicide (so-called suicide referents) have different moral connotations, and neutral referents are recommended in media reporting guidelines. Aims: To assess how different referents in media reports are related to actual suicides. Method: Austrian news articles for each month between 2000 and 2021 (n = 276 months) were obtained from the Austrian Press Agency. Time series were modeled for media items referring to suicide as a crime [Selbstmord], an act of freedom [Freitod], or neutral connotation [Suizid]. Temporal associations with suicides in the month before, during, and after the reporting were examined. Results: Terminology referring to suicide as an act of free will [Freitod] was weakly associated with increases in total, male, and female suicides and with suicides in up to 64-year-olds in the same month. No other statistically significant associations were found. Limitations: No detailed content analysis of media reports was done. Conclusion: During times of prevalent use of referents suggesting suicide to be an act of freedom, there are small-sized increases in suicides. The simultaneous occurrence of this referent and suicides might reflect effects of a societal framing present in both the media and the community rather than a sheer media effect.

The Development, Progress, and Impact of National Suicide Prevention Strategies Worldwide.

National suicide prevention strategies have been identified as evidence-informed interventions that require multisectoral efforts by governments. This article reviews the rationale for national strategies, the need for a whole-of-government approach, and current progress on national strategies worldwide, including successes and challenges regarding implementation. We highlight the limitations of existing evidence and describe how future research may help to address knowledge gaps. We conclude that national strategies are an important tool for suicide prevention worldwide. However, a more robust evidence base evaluating the impact of strategies on suicide-related outcomes is needed.

Changes in Media Reporting Quality and Suicides Following National Media Engagement on Responsible Reporting of Suicide in Canada: Changements de la Qualité des reportages dans les médias sur les suicides suite à l'engagement des médias nationaux à la déclaration responsable du suicide au Canada.

OBJECTIVE: Responsible media reporting is an accepted strategy for preventing suicide. In 2015, suicide prevention experts launched a media engagement initiative aimed at improving suicide-related reporting in Canada; its impact on media reporting quality and suicide deaths is unknown. METHOD: This pre-post observational study examined changes in reporting characteristics in a random sample of suicide-related articles from major publications in the Greater Toronto Area (GTA) media market. Articles (n = 900) included 450 from the 6-year periods prior to and after the initiative began. We also examined changes in suicide counts in the GTA between these epochs. We used chi-square tests to analyse changes in reporting characteristics and time-series analyses to identify changes in suicide counts. Secondary outcomes focused on guidelines developed by media professionals in Canada and how they may have influenced media reporting quality as well as on the overarching narrative of media articles during the most recent years of available data. RESULTS: Across-the-board improvement was observed in suicide-related reporting with substantial reductions in many elements of putatively harmful content and substantial increases in all aspects of putatively protective content. However, overarching article narratives remained potentially harmful with 55.2% of articles telling the story of someone's death and 20.8% presenting an other negative message. Only 3.6% of articles told a story of survival. After controlling for potential confounders, a nonsignificant numeric decrease in suicide counts was identified after initiative implementation (ω = -5.41, SE = 3.43, t = 1.58, p = 0.12). CONCLUSIONS: We found evidence that a strategy to engage media in Canada changed the content of reporting, but there was only a nonsignificant trend towards fewer suicides. A more fundamental change in media narratives to focus on survival rather than death appears warranted.

"Breaking the silence" suicide Prevention media campaign in Oregon: Evaluation of impact on help-seeking and suicide mortality.

INTRODUCTION: Research has established that suicide-related media can impact suicide rates both positively and negatively, supporting efforts to engage the media in the service of suicide prevention. The goal of the current study is to evaluate the impact of a suicide prevention media campaign implemented April 7-14, 2019 in Oregon. METHODS: Several indices of help-seeking behavior and suicide risk were employed: suicide-related Google Health API searches, National Suicide Prevention Lifeline (Lifeline) (currently known as the 988 Suicide and Crisis Lifeline) call volume, and state suicide mortality data from April 7, 2016-May 6, 2019. Eight states with similar 2016-2018 average suicide rates were compared with Oregon. Bayesian structural time-series modeling in R was used to test intervention effects. RESULTS: During the 30 days following the start of the campaign, there was a significant increase in Lifeline calls from Oregon area codes (2488 observed vs. 2283 expected calls, p = 0.03). There were no significant changes in suicide mortality or suicide-related Google searches in Oregon. CONCLUSIONS: The campaign appeared to increase help-seeking behavior in the form of Lifeline calls, without any indication of an iatrogenic suicide contagion effect. However, the campaign's potential to reduce suicide mortality was unmet.

Effects of the mental health promotion seminar 'Coping with stress' in the undergraduate medical curriculum of the Medical University of Vienna.

BACKGROUND: High prevalence rates of distress and burnout in medical students are well-documented in mental health literature. Different types of interventions have been developed in the past in order to reduce stress in medical undergraduate students and promote better coping skills. There is, however, a paucity of studies that have tested the effectiveness of these interventions. This study aimed to examine the effect of different versions of the seminar 'Coping with stress', which was implemented in the first year of the undergraduate curriculum of the Medical University of Vienna in the summer semester of 2018, on students' mental health. METHODS: Invitations to participate in the study were sent via email to six cohorts of students from the Medical University of Vienna. Two cohorts participated in the onsite version of the seminar 'Coping with stress', whereas two cohorts participated in the online version of the seminar, and two cohorts received no intervention (control group). Data on burnout risk, life satisfaction, stress, and knowledge about available help resources were collected via online questionnaires from n = 137 students before and after the curriculum module that contained the seminar. RESULTS: Medical students who participated in the onsite seminar reported a reduction of some aspects of burnout, a decrease in stress, and an increase in knowledge about available help resources. No such effect was seen in the control group. Participants of the online seminar experienced a similar increase in knowledge about available help resources, but no changes in other outcomes. CONCLUSIONS: The findings support the notion that the onsite seminar of 'Coping with stress' had a positive impact on medical students' mental health and is a useful addition to the medical curriculum by promoting mental health literacy. TRIAL REGISTRATION: This research has been registered in the German Clinical Trial Registry with the registration number DRKS00018981 and the registration date 14/11/2019.

Experiences of suicide survivors of sharing their stories about suicidality and overcoming a crisis in media and public talks: a qualitative study.

BACKGROUND: Media stories of hope and recovery from suicidal ideation have been found to have a positive impact on the audience, but little is known about how individuals who share their own experiences perceive the effects of their storytelling. This study aimed to assess qualitatively, through focus groups, how individuals who shared their personal story of hope and recovery in the media and public talks experienced the process, and which aspects they perceived as important in sharing their coping story. METHODS: Three focus groups were conducted with a total of n = 12 individuals. These included n = 5 participants with experience of suicidal ideation or a suicide attempt, n = 4 individuals who had been bereaved through suicide, and n = 3 participants who experienced both. Participants were recruited from the American organisation "Suicide Survivors United". Thematic analysis was used to assess the participants' perception and experiences of sharing their story. RESULTS: Participants shared that the intention to help others was the main motivation to share their story of hope and recovery. Participants noted many positive effects of their storytelling on themselves and also received positive feedback from the audience, such as improved help-seeking attitudes. The participants offered recommendations for those who want to share their story of hope and recovery, including careful personal preparation and media training before going public. They also discussed media recommendations for talking about suicide in the media. CONCLUSIONS: Sharing a personal story of hope and recovery may have a beneficial impact on the storytellers. Storytelling requires a careful preparation and training before going public and support and guidance is crucial in all stages of the storytelling, particularly to help unexperienced storytellers in going public and using their personal narratives to help prevent suicide.

The Role of the Narrative in Educative Suicide Awareness Materials: A Randomized Controlled Trial.

There has been a debate about the suitability of different narratives in educative suicide prevention materials. Whereas some suicide prevention experts recommend raising awareness of suicide by highlighting its prevalence, others argue that this approach may normalize suicide and advocate focusing on help resources instead. Unfortunately, empirical evidence regarding this question is lacking. This randomized controlled trial aimed to test the impact of educative news articles that conveyed different narratives of suicide prevention. One article focused on the prevalence of suicide, one article highlighted professional help resources, and one article emphasized on how everyone can help to prevent suicide. We randomized n = 334 participants to read either one of these three articles or an article unrelated to suicide. Data on suicidal ideation, stigmatizing attitudes toward suicidal individuals, attitudes toward suicide prevention, and help-seeking intentions were collected with questionnaires, and implicit measures were used to assess participants' mental accessibility of concepts related to suicide and suicide prevention. Participants exposed to the article highlighting the high prevalence of suicide tended to show a higher accessibility of potentially detrimental cognitive concepts related to suicide. In contrast, the accessibility of the concept of "helping" and that "suicide is preventable" was higher in participants' memory when exposed to materials focusing on help. It seems that the impact of educative suicide awareness materials on readers' access to suicide- and suicide-prevention-related concepts in memory varied depending on the narrative featured in the article.

Facilitators and barriers to implementation of suicide prevention interventions: Scoping review.

We know that suicide is preventable, yet hundreds of thousands of people still die due to suicide every year. Many interventions were proven to be effective, and dozens of others showed promising results. However, translating these interventions into new settings brings several challenges. One of the crucial obstacles to success is not anticipating possible barriers to implementation nor enhancing possible benefits of factors facilitating the implementation. While we witnessed great support for suicide prevention activities globally in the past years, implementation barriers and facilitating factors are yet to be comprehensively mapped to help implementation activities worldwide. This scoping review maps current knowledge on facilitators and barriers to the implementation of suicide prevention interventions while using the Consolidated Framework for Implementation Research (CFIR) for classification. We included 64 studies. Barriers and facilitators were most commonly identified in the outer setting CFIR domain, namely in the sub-domain of patient needs and resources, which refers to the way in which these needs and resources are reflected by the reviewed interventions. The second most saturated CFIR domain for facilitators was intervention characteristics, where relative advantage, adaptability and cost of intervention sub-domains were equally represented. These sub-domains refer mostly to how the intervention is perceived by key stakeholders, to what extent it can be tailored to the implementation context and how much it costs. While intervention characteristics domain was the second most common also for barriers, the complexity sub-domain referring to high perceived difficulty of implementation was the most frequently represented. With reference to the results, we recommend adapting interventions to the needs of the target groups. Furthermore, carefully selecting the intervention to suit the target context concerning their adaptability, costs and complexity is vital for a successful implementation. Further implications for practice and research are discussed.

The role of monocausal versus multicausal explanations of suicide in suicide reporting: A randomized controlled trial.

BACKGROUND: Media guidelines for reporting on suicide recommend that journalists should avoid monocausal explanations of suicide, but it is unclear if media items with monocausal explanations elicit different effects as compared to multicausal portrayals. METHOD: Using a web-based randomized controlled trial (n = 969), we tested five versions of a news article about the suicide of a teenage girl with varying portrayals of reasons for the suicide: (1) bullying as the sole (external) factor (i.e., monocausal), (2) several external social factors, (3) a combination of internal and external factors, (4) a combination of internal and external factors along with a focus on suicide prevention, or (5) no reason for the suicide (control group). We measured perceptions about the cause of suicide, attitudes toward suicide and suicide prevention, and identification with the suicidal protagonist with questionnaires. RESULTS: Readers of articles that portrayed suicide as being caused by one specific reason or exclusively social factors tended to adopt these misconceptions. Identification with the suicidal protagonist did not vary between interventions groups, but was lower in the control group. CONCLUSION: Highlighting the multifactorial etiology of suicide in news articles may help to avoid the misconception that suicide is a monocausal issue.

Effects of gatekeeper trainings from the Austrian national suicide prevention program.

Background: The development and implementation of gatekeeper trainings were first goals in the national suicide prevention strategy "Suicide Prevention Austria" (SUPRA). The current study aims to assess the short- and longer-term effects of the SUPRA gatekeeper trainings in comparison with established gatekeeper trainings. Methods: We evaluated 28 gatekeeper trainings including 427 participants by assessing improvement of knowledge (facts about suicide and suicide prevention), gatekeeper self-efficacy and attitudes, and gatekeeper behavior (e.g., asking depressed people about suicide). Assessments were immediately before and after the gatekeeper trainings, with an additional follow-up 6 months later. Effects were compared with benchmark effects of established gatekeeper trainings. Results: There were substantial improvements in knowledge, self-efficacy and attitudes immediately after the training, comparable or larger than known from evaluations of established gatekeeper trainings. Most of these changes were upheld in the follow-up assessment, with effects comparable to other gatekeeper trainings. There was only a small increase of self-reported gatekeeper behavior, in line with results from other gatekeeper trainings. Conclusion: The SUPRA gatekeeper training had some beneficial effects in the short- and longterm, with effect sizes comparable to established gatekeeper trainings.

Gone Too Soon: priorities for action to prevent premature mortality associated with mental illness and mental distress.

Globally, too many people die prematurely from suicide and the physical comorbidities associated with mental illness and mental distress. The purpose of this Review is to mobilise the translation of evidence into prioritised actions that reduce this inequity. The mental health research charity, MQ Mental Health Research, convened an international panel that used roadmapping methods and review evidence to identify key factors, mechanisms, and solutions for premature mortality across the social-ecological system. We identified 12 key overarching risk factors and mechanisms, with more commonalities than differences across the suicide and physical comorbidities domains. We also identified 18 actionable solutions across three organising principles: the integration of mental and physical health care; the prioritisation of prevention while strengthening treatment; and the optimisation of intervention synergies across social-ecological levels and the intervention cycle. These solutions included accessible, integrated high-quality primary care; early life, workplace, and community-based interventions co-designed by the people they should serve; decriminalisation of suicide and restriction of access to lethal means; stigma reduction; reduction of income, gender, and racial inequality; and increased investment. The time to act is now, to rebuild health-care systems, leverage changes in funding landscapes, and address the effects of stigma, discrimination, marginalisation, gender violence, and victimisation.

Suicide mortality among physicians, dentists, veterinarians, and pharmacists as well as other high-skilled occupations in Austria from 1986 through 2020.

Some evidence puts health professionals at increased risk of suicide, especially females, whereas other research suggests a lower risk in high-skilled occupations. This study investigated the suicide risk of four health professions (physicians, dentists, veterinarians, pharmacists) and three other high-skilled occupations (notaries, lawyers, tax advisors/public accountants) in Austria compared to the general population, and analyzed suicide methods across occupations. Data was collected from professional associations and Austrian cause-of-death statistics to determine suicide cases. Gender-specific standardized mortality ratios (SMRs), crude and age-adjusted suicide rates and frequencies for suicide methods were calculated for each profession (maximum time span 1986-2020). Among males, only veterinarians had a significantly elevated suicide risk compared to the general population. Physicians and tax advisors/public accountants had a significantly lower suicide risk. Among females, the veterinarians, physicians, and pharmacists had a significantly elevated suicide risk; for dentists, it was also elevated, though non-significantly. Age-adjusted suicide rates showed a smaller gap between men and women in all professions compared to the general population. Poisoning was the predominant suicide method among health professions, except dentists. These findings are consistent with some of the prior literature and call for specific suicide prevention efforts in health professions, focusing on women.

Association of 7 million+ tweets featuring suicide-related content with daily calls to the Suicide Prevention Lifeline and with suicides, United States, 2016-2018.

OBJECTIVE: The aim of this study was to assess associations of various content areas of Twitter posts with help-seeking from the US National Suicide Prevention Lifeline (Lifeline) and with suicides. METHODS: We retrieved 7,150,610 suicide-related tweets geolocated to the United States and posted between 1 January 2016 and 31 December 2018. Using a specially devised machine-learning approach, we categorized posts into content about prevention, suicide awareness, personal suicidal ideation without coping, personal coping and recovery, suicide cases and other. We then applied seasonal autoregressive integrated moving average analyses to assess associations of tweet categories with daily calls to the US National Suicide Prevention Lifeline (Lifeline) and suicides on the same day. We hypothesized that coping-related and prevention-related tweets are associated with greater help-seeking and potentially fewer suicides. RESULTS: The percentage of posts per category was 15.4% (standard deviation: 7.6%) for awareness, 13.8% (standard deviation: 9.4%) for prevention, 12.3% (standard deviation: 9.1%) for suicide cases, 2.4% (standard deviation: 2.1%) for suicidal ideation without coping and 0.8% (standard deviation: 1.7%) for coping posts. Tweets about prevention were positively associated with Lifeline calls (B = 1.94, SE = 0.73, p = 0.008) and negatively associated with suicides (B = -0.11, standard error = 0.05, p = 0.038). Total number of tweets were negatively associated with calls (B = -0.01, standard error = 0.0003, p = 0.007) and positively associated with suicide, (B = 6.4 × 10-5, standard error = 2.6 × 10-5, p = 0.015). CONCLUSION: This is the first large-scale study to suggest that daily volume of specific suicide-prevention-related social media content on Twitter corresponds to higher daily levels of help-seeking behaviour and lower daily number of suicide deaths. PREREGISTRATION: As Predicted, #66922, 26 May 2021.