Tweets can prevent suicides


Dec 14, 2022

It is not primarily a question of whether people tweet about suicide, but how.

 

A new study by Complexity Science Hub Vienna and MedUni Vienna shows that postings about suicide can actually have a protective effect.

 

 

“If the number of tweets with suicide prevention information increases, the number of suicides decreases and more people call help facilities to ask for support,” Hannah Metzler from the CSH explains the results of the new study. “Especially tweets about one’s own coping with a suicidal crisis show enormous potential to encourage people in a similar life situation to get in touch with a help facility,” Thomas Niederkrotenthaler cites a key detail of the research. Such tweets are rarely posted, but whenever they are, a relatively large number of people seek help afterwards.

 

MEDIA COVERAGE DOES NOT INCREASE SUICIDE RATE 

 

Moreover, the new study again suggests that news about suicide cases does not generally lead to an increase in the suicide rate. “All postings about suicide cases taken together do not show a recognisable increase,” explains Metzler. What matters is how it is reported and about whom. Studies have shown that especially reports about the suicide of famous people or those in highly sensational language are problematic. “Especially when a high volume of posts is made on social media in the context of sensational suicides, there is a risk that vulnerable people will slip deeper into the crisis as a result and that there will be an increase in suicides,” Niederkrotenthaler continues to call for a responsible approach to the topic.

 

HARDLY ANY STUDIES ON SOCIAL MEDIA

 

Although the influence of social media has increased strongly in recent years, especially in dealing with suicidal crises, there is currently hardly any research with meaningful data on this. Similar studies of traditional media usually work with relatively small data sets. This is due to the fact that the effort to manually categorise large data sets is enormous. New models can change that. “Our study shows that modern machine learning models can very precisely distinguish between different types of tweets that are relevant for prevention,” explains Metzler.

 

SEVEN MILLION TWEETS ANALYSED 

 

The research team analysed a total of 7,159,610 million tweets – a quantity that would be almost impossible to handle manually. First, they optimised the model with a training set of 3,200 tweets. Only when it correctly recognises tweets relevant to suicide prevention in a completely new data set can such a model be considered reliable.  “The models recorded many prevention tweets when NGOs actually do a lot of prevention work – for example on World Suicide Prevention Day or around Christmas and New Year’s Day,” explains Metzler, which underlines the reliability of the machine learning model.

 

Deep learning models can detect relevant tweets for suicide prevention © CSH Vienna

 

HUGH POTENTIAL OF DEEP LEARNING 

 

While older machine learning models only track the frequency of certain words, deep learning models can do much more complex analyses. For example, they take into account where a word is located in a sentence, as well as what comes before and after it. “Since words can have very different meanings in certain contexts, such models make our research more precise and, as in this case, can provide an important contribution to suicide prevention,” says Metzler.

 

“Our work is the first large-scale study to suggest that the daily volume of specific suicide prevention-related tweets is associated with higher daily rates of help-seeking behaviour and lower daily rates of suicide deaths,” Niederkrotenthaler summarises the study results.

 

 

 


Publication

A. Nerpel, et al.

SARS-ANI: a global open access dataset of reported SARS-CoV-2 events in animals

Scientific Data 9 (438) (2022)

Publication

C. Deischinger, E. Dervic, S. Nopp, M. Kaleta, P. Klimek, A. Kautzky-Willer

Diabetes mellitus is associated with a higher relative risk for venous thromboembolism in females than in males

Diabetes Res Clin Pract. (2022) 36471550

News

May 31, 2023

Forensic analysis shows signs of election fraud in Turkey

Press

End Times by Peter Turchin review – can we predict the collapse of societies?


The Guardian, May 28, 2023

Event

CSH Talk by Thomas Choi "Supply Networks: Dyads, Triads, Tetrads, and Beyond"


Jun 06, 2023 | 15:0016:00

Complexity Science Hub Vienna

Press

Wie Medikamente durch die Welt reisen


NEWS, May 31, 2023

People

May 30, 2023

Meet Sachin Rawat

Research News

May 30, 2023

Obesity increases risk of mental disorders throughout life

Publication

V.D.P. Servedio, M. R. Ferreira, N. Reisz, R. Costas, S. Thurner

Scale-free growth in regional scientific capacity building explains long-term scientific dominance

Chaos, Solitons & Fractals 167 (2023) 113020

Press

Obesity increases the chances of developing mental disorders for all age groups


News Medical, May 30, 2023

Event

CSH Talk by François Lafond "Firm-level production networks: what do we (really) know?"


Jun 07, 2023 | 15:0016:00

Complexity Science Hub Vienna

News

May 31, 2023

Forensic analysis shows signs of election fraud in Turkey

People

May 30, 2023

Meet Sachin Rawat

Research News

May 30, 2023

Obesity increases risk of mental disorders throughout life

News

May 25, 2023

Quotas alone will not solve the problem

Spotlight

May 17, 2023

Complexity Research for Digital Humanism

People

May 12, 2023

Peter Turchin introduces his new book

Research News

May 2, 2023

Scientists create high-resolution poverty maps using big data

News

Apr 26, 2023

BEYOND COLLECTIVE STUPIDITY

Spotlight

Apr 21, 2023

How does a region become a center for innovation?

Spotlight

Apr 14, 2023

Are cars our kings?

Press

End Times by Peter Turchin review – can we predict the collapse of societies?


The Guardian, May 28, 2023

Press

Obesity increases the chances of developing mental disorders for all age groups


News Medical, May 30, 2023

Press

Wie Medikamente durch die Welt reisen


NEWS, May 31, 2023

Press

Kritik an EU-Chatkontrolle


Ö1 | Digital.leben, May 11, 2023

Press

Treibjagd im Darknet: Neue Technologien für Cyber-Ermittler


Salzburger Nachrichten, May 16, 2023

Press

„Die Älteren halten zu Erdogan, die jüngere Generation hat andere Sorgen“


Cicero, May 9, 2023

Press

Stablecoin Destabilization - why should we care?


Forbes, Apr 27, 2023

Press

„Wir sind nicht so einfach zu manipulieren“ [feat. Hannah Metzler]


Kurier, Apr 29, 2023

Press

Die manchmal fatale Lust, alles selbst zu recherchieren [feat. Mirta Galesic & Henrik Olsson]


Die Presse, Apr 14, 2023

Press

La scienza ha creato una nuova classificazione delle aperture degli scacchi [ital | feat. Vito Servedio & Giordano De Marzo]


WIRED, Apr 10, 2023

Publication

R. Prieto-Curiel, J. E. Patino, B. Anderson

Scaling of the morphology of African cities

PNAS 120 (9) (2023) e2214254120

Publication

A. Di Natale, D. Garcia

LEXpander: applying colexification networks to automated lexicon expansion

Behaviour Research Methods (2023)

Publication

V.D.P. Servedio, M. R. Ferreira, N. Reisz, R. Costas, S. Thurner

Scale-free growth in regional scientific capacity building explains long-term scientific dominance

Chaos, Solitons & Fractals 167 (2023) 113020

Publication

C. Deischinger, E. Dervic, S. Nopp, M. Kaleta, P. Klimek, A. Kautzky-Willer

Diabetes mellitus is associated with a higher relative risk for venous thromboembolism in females than in males

Diabetes Res Clin Pract. (2022) 36471550

Publication

A. Nerpel, et al.

SARS-ANI: a global open access dataset of reported SARS-CoV-2 events in animals

Scientific Data 9 (438) (2022)

Publication

E. D. Lee, X. Chen, B. C. Daniels

Discovering sparse control strategies in neural activity

PLoS Computational Biology (May 27) (2022)

Publication

H. Kong, S. Martin-Gutierrez, F. Karimi

Influence of the first-mover advantage on the gender disparities in physics citations

Communications Physics 5 (243) (2022)

Publication

T.M. Pham, J. Korbel, R. Hanel, S. Thurner

Empirical social triad statistics can be explained with dyadic homophylic interactions

PNAS 119 (2022) e2121103119

Publication

G. De Marzo, V.D.P. Servedio

Quantifying the complexity and similarity of chess openings using online chess community data

Scientific Reports 13 (2023) 5327

Publication

D. R. Lo Sardo, S. Thurner, et al.

Systematic population-wide ecological analysis of regional variability in disease prevalence

Heliyon 9(4) (2023) e15377

Publication

J. Wachs

Digital traces of brain drain: developers during the Russian invasion of Ukraine

EPJ Data Science 12 (2023) 14

Publication

D. Diodato, R. Hausmann, F. Neffke

The impact of return migration on employment and wages in Mexican cities

Journal of Urban Economics 135 (2023) 103557

Event

CSH Talk by Thomas Choi "Supply Networks: Dyads, Triads, Tetrads, and Beyond"


Jun 06, 2023 | 15:0016:00

Complexity Science Hub Vienna

Event

CSH Workshop: "Firm-level supply network data for policy making"


Jun 05, 2023 | 8:00Jun 06, 2023 | 17:00

Complexity Science Hub Vienna

Event

CSH Talk by François Lafond "Firm-level production networks: what do we (really) know?"


Jun 07, 2023 | 15:0016:00

Complexity Science Hub Vienna