The Relationship Between Suicide-Related Twitter Events and Suicides in Ontario From 2015 to 2016

Does suicide contagion (Werther effect) take place in response to social media? A systematic review

INTRODUCTION

The Werther, Copycat or contagion effect of suicidal behaviour is a complex phenomenon that can arise due to exposure to media stories in which identifiable people take their lives. On the contrary, the Papageno effect prevents people from suicide by promoting positives examples of suicidal crisis management. Impact of both effects has been widely studied in different types of situations, but its existence in social media is a source of much debate.

METHODS

A systematic search following the PRISMA guidelines of PubMed, Scopus, Embase, PsycInfo, Web of Science and the references of prior reviews yielded 25 eligible studies.

RESULTS

Most of the studies found were observational, with very different methodologies and generally with low risk of bias. In these, the results suggest the existence of the Werther effect in response to social media stories about suicide. This is mediated by multiple factors, including the characteristic of the users, the type of interaction and the content of the publications. At the same time, the Papageno effect is also described. Evidence found by type of social media and future implications are discussed.

CONCLUSION

Suicidal content on social media can be both contagious and protective. It is confirmed that the Werther and Papageno effects may occur in response to social media, so they could be an interesting target for preventive interventions.

"What Do I Say? How Do I Say it?" Twitter as a Knowledge Dissemination Tool for Mental Health Research

This study aims to generate evidence-based guidelines for researchers regarding how to effectively disseminate mental health research via Twitter. Three hundred mental health research Tweets posted from September 2018 to September 2019 were sampled from two large Australian organizations. Twenty-seven predictor variables were coded for each Tweet across five thematic categories: messaging; research area; mental health area; external networks; and media features. Regression analyses were conducted to determine associations with engagement outcomes of Favourites, Retweets, and Comments. Less than half (n = 10) of predictor variables passed validity tests. Notably, conclusions could not reliably be drawn on whether a Tweet featured evidence-based information. Tweets were significantly more likely to be Retweeted if they contained a hyperlink or multimedia. Tweets were significantly more likely to receive comments if they focused on a specific population group. These associations remain significant when controlling for organization. These findings indicate that researchers may be able to maximize engagement on Twitter by highlighting the population groups that the research applies to and enriching Tweets with multimedia content. In addition, care should be taken to ensure users can infer which messages are evidence-based. Guidelines and an accompanying resource are proposed.

Dynamic reciprocal relationships between traditional media reports, social media postings, and youth suicide in Taiwan between 2012 and 2021

Rising social media use over the past decade has been linked with increasing suicide rates among young people. Previous studies that assessed the impact of social media on suicide have typically focused on single social media platforms, such as Twitter, and assumed unidirectional associations, where social media posts leads to suicide. Our study focused on the past decade (2012-2021) which has witnessed a rapid increase of social media platforms and use. Poisson and negative binominal auto-regression models were employed to examine the dynamic reciprocity between social media, traditional media and youth suicides in Taiwan. Increased volume in suicide-related social media posts positively correlated with increased youth suicide rates (β = 2.53 × 10-5, 95% CI= (0.83 × 10-5, 4.24 × 10-5), P < 0.01), but increased rates of youth suicide was not related to an increase in suicide-related social media posts. Suicide-related posts on social media triggered reporting of suicide-related news on traditional media platforms (β = 3.35 × 10-2, 95% CI= (2.51 × 10-2, 4.19 × 10-2), P < 0.001), whilst traditional media reports of suicide led to increased suicide-related social media posts (β = 6.13 × 10-1, 95% CI = (4.58 × 10-1, 7.68 × 10-1); P < 0.001). However, suicide-related reports on traditional media platforms did not directly lead to an increase in youth suicide rates. Our findings highlight challenges for suicide prevention strategies in the 21st Century, in dealing with the increasing prominence of social media over traditional media. As social media is more difficult to regulate than traditional media, suicide prevention efforts must adapt to this new landscape by developing innovative strategies that address the unique risks and opportunities presented by social media.

Suicide risk detection using artificial intelligence: the promise of creating a benchmark dataset for research on the detection of suicide risk

Suicide is a leading cause of death that demands cross-disciplinary research efforts to develop and deploy suicide risk screening tools. Such tools, partly informed by influential suicide theories, can help identify individuals at the greatest risk of suicide and should be able to predict the transition from suicidal thoughts to suicide attempts. Advances in artificial intelligence have revolutionized the development of suicide screening tools and suicide risk detection systems. Thus, various types of AI systems, including text-based systems, have been proposed to identify individuals at risk of suicide. Although these systems have shown acceptable performance, most of them have not incorporated suicide theories in their design. Furthermore, directly applying suicide theories may be difficult because of the diversity and complexity of these theories. To address these challenges, we propose an approach to develop speech- and language-based suicide risk detection systems. We highlight the promise of establishing a benchmark textual and vocal dataset using a standardized speech and language assessment procedure, and research designs that distinguish between the risk factors for suicide attempt above and beyond those for suicidal ideation alone. The benchmark dataset could be used to develop trustworthy machine learning or deep learning-based suicide risk detection systems, ultimately constructing a foundation for vocal and textual-based suicide risk detection systems.

Detecting Potentially Harmful and Protective Suicide-Related Content on Twitter: Machine Learning Approach

Background

Research has repeatedly shown that exposure to suicide-related news media content is associated with suicide rates, with some content characteristics likely having harmful and others potentially protective effects. Although good evidence exists for a few selected characteristics, systematic and large-scale investigations are lacking. Moreover, the growing importance of social media, particularly among young adults, calls for studies on the effects of the content posted on these platforms.

Objective

This study applies natural language processing and machine learning methods to classify large quantities of social media data according to characteristics identified as potentially harmful or beneficial in media effects research on suicide and prevention.

Methods

We manually labeled 3202 English tweets using a novel annotation scheme that classifies suicide-related tweets into 12 categories. Based on these categories, we trained a benchmark of machine learning models for a multiclass and a binary classification task. As models, we included a majority classifier, an approach based on word frequency (term frequency-inverse document frequency with a linear support vector machine) and 2 state-of-the-art deep learning models (Bidirectional Encoder Representations from Transformers [BERT] and XLNet). The first task classified posts into 6 main content categories, which are particularly relevant for suicide prevention based on previous evidence. These included personal stories of either suicidal ideation and attempts or coping and recovery, calls for action intending to spread either problem awareness or prevention-related information, reporting of suicide cases, and other tweets irrelevant to these 5 categories. The second classification task was binary and separated posts in the 11 categories referring to actual suicide from posts in the off-topic category, which use suicide-related terms in another meaning or context.

Results

In both tasks, the performance of the 2 deep learning models was very similar and better than that of the majority or the word frequency classifier. BERT and XLNet reached accuracy scores above 73% on average across the 6 main categories in the test set and F₁-scores between 0.69 and 0.85 for all but the suicidal ideation and attempts category (F₁=0.55). In the binary classification task, they correctly labeled around 88% of the tweets as about suicide versus off-topic, with BERT achieving F₁-scores of 0.93 and 0.74, respectively. These classification performances were similar to human performance in most cases and were comparable with state-of-the-art models on similar tasks.

Conclusions

The achieved performance scores highlight machine learning as a useful tool for media effects research on suicide. The clear advantage of BERT and XLNet suggests that there is crucial information about meaning in the context of words beyond mere word frequencies in tweets about suicide. By making data labeling more efficient, this work has enabled large-scale investigations on harmful and protective associations of social media content with suicide rates and help-seeking behavior.

Differences in Suicide-Related Twitter Content According to User Influence

Background: The content of suicide-specific social media posts may impact suicide rates, and putatively harmful and/or protective content may vary by the author's influence. Aims: This study sought to characterize how suicide-related Twitter content differs according to user influence. Method: Suicide-related tweets from July 1, 2015, to June 1, 2016, geolocated to Toronto, Canada, were collected and randomly selected for coding (n = 2,250) across low, medium, or high user influence levels (based on the number of followers, tweets, retweets, and posting frequency). Logistic regression was used to identify differences by user influence for various content variables. Results: Low- and medium-influence users typically tweeted about personal experiences with suicide and associations with mental health and shared morbid humor/flippant tweets. High-influence users tended to tweet about suicide clusters, suicide in youth, older adults, indigenous people, suicide attempts, and specific methods. Tweets across influence levels predominantly focused on suicide deaths, and few described suicidal ideation or included helpful content. Limitations: Social media data were from a single location and epoch. Conclusion: This study demonstrated more problematic content vis-à-vis safe suicide messaging in tweets by high-influence users and a paucity of protective content across all users. These results highlight the need for further research and potential intervention.

Media coverage of Canadian Veterans, with a focus on post traumatic stress disorder and suicide

BACKGROUND

A large corpus of research indicates that the media plays a key role in shaping public beliefs, opinions and attitudes towards social groups. Some research from the United States indicates that military Veterans are sometimes framed in a stereotypical and stigmatizing manner, however there is a lack of research on Canadian media coverage of Veterans. As such, the overarching aim of this study is to assess the tone and content of Canadian media coverage of military Veterans, with a focus on PTSD and suicide. The first objective is to document and analyze common themes, content and temporal patterns in Canadian media coverage of Veterans per se. The second objective is to examine common themes and content in the sub-set of articles having PTSD as a theme. The third objective is to assess adherence to responsible reporting of suicide guidelines in the sub-set of articles having suicide as a theme.

METHODS

We used validated and systematic methods including use of key words, retrieval software and inter-rater reliability tests to collect and code news articles (N = 915) about Veterans from over 50 media sources during a 12-month period, with specific coding of articles about PTSD (N = 93) and suicide (N = 61).

RESULTS

Analysis revealed that the most common theme is 'honour or commemoration of Veterans' which occurred in over half of the articles. In contrast 14% of articles focused on danger, violence or criminality. In the sub-set of articles with PTSD as a theme, over 60% focused on danger, violence or criminality, while only around 1 in 3 focused on recovery, rehabilitation, or health/social service intervention. In the sub-set of articles about suicide, there was generally strong adherence to responsible reporting guidelines, though less than 5% gave help-seeking information. Moreover, most reporting on PTSD and suicide focused on a single anomalous murder-suicide incident, with few articles about suicide prevention, helpful resources and modifiable risk factors.

CONCLUSIONS

The results reveal some encouraging findings as well as a need to diversify media coverage of Canadian Veterans. This could be achieved through targeted educational outreach to help Canadian journalists responsibly report on Veterans and their mental health issues.

Suicide-related Twitter Content in Response to a National Mental Health Awareness Campaign and the Association between the Campaign and Suicide Rates in Ontario

OBJECTIVE

Mental health awareness (MHA) campaigns have been shown to be successful in improving mental health literacy, decreasing stigma, and generating public discussion. However, there is a dearth of evidence regarding the effects of these campaigns on behavioral outcomes such as suicides. Therefore, the objective of this article is to characterize the association between the event and suicide in Canada's most populous province and the content of suicide-related tweets referencing a Canadian MHA campaign (Bell Let's Talk Day [BLTD]).

METHODS

Suicide counts during the week of BTLD were compared to a control window (2011 to 2016) to test for associations between the BLTD event and suicide. Suicide tweets geolocated to Ontario, posted in 2016 with the BLTD hashtag were coded for specific putatively harmful and protective content.

RESULTS

There was no associated change in suicide counts. Tweets (n = 3,763) mainly included content related to general comments about suicide death (68%) and suicide being a problem (42.8%) with little putatively helpful content such as stories of resilience (0.6%) and messages of hope (2.2%).

CONCLUSIONS

In Ontario, this national mental health media campaign was associated with a high volume of suicide-related tweets but not necessarily including content expected to diminish suicide rates. Campaigns like BLTD should strongly consider greater attention to suicide-related messaging that promotes help-seeking and resilience. This may help to further decrease stigmatization, and potentially, reduce suicide rates.