CoChat

Can acute suicidality be predicted by Instagram data? Results from qualitative and quantitative language analyses

Open access
Brown, Rebecca C., Bendig, Eileen, Fischer, Tin, Goldwich, A. David, Baumeister, Harald, Plener, Paul L. · 2019 · PLOS ONE
Cited by 46

The DOI matches its Crossref record; 9 of the 9 references it cites were found in a registry or an index.

Abstract

BACKGROUND: Social media has become increasingly important for communication among young people. It is also often used to communicate suicidal ideation. AIMS: To investigate the link between acute suicidality and language use as well as activity on Instagram. METHOD: A total of 52 participants, aged on average around 16 years, who had posted pictures of non-suicidal self-injury on Instagram, and reported a lifetime history of suicidal ideation, were interviewed using Instagram messenger. Of those participants, 45.5% reported suicidal ideation on the day of the interview (acute suicidal ideation). Qualitative text analysis (software ATLAS.ti 7) was used to investigate experiences with expressions of active suicidal thoughts on Instagram. Quantitative text analysis of language use in the interviews and directly on Instagram (in picture captions) was performed using the Linguistic Inquiry and Word Count software. Language markers in the interviews and in picture captions, as well as activity on Instagram were added to regression analyses, in order to investigate predictors for current suicidal ideation. RESULTS: Most participants (80%) had come across expressions of active suicidal thoughts on Instagram and 25% had expressed active suicidal thoughts themselves. Participants with acute suicidal ideation used significantly more negative emotion words (Cohen's d = 0.66, 95% CI: 0.088-1.232) and words expressing overall affect (Cohen's d = 0.57, 95% CI: 0.001-1.138) in interviews. However, activity and language use on Instagram did not predict acute suicidality. CONCLUSIONS: While participants differed with regard to their use of language in interviews, differences in activity and language use on Instagram were not associated with acute suicidality. Other mechanisms of machine learning, like identifying picture content, might be more valuable.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1371/journal.pone.0220623

Cites

9 of 9 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Cited by

See all 46

Metadata

Authors
Brown, R. C., Bendig, E., Fischer, T., Goldwich, A. D., Baumeister, H., & Plener, P. L.
Venue
PLOS ONE
Published
2019-09-10
Volume
14
Issue
9
Pages
e0220623
ISSN
1932-6203 (ISSN-L)
OpenAlex
W2973122675
Cited by
46
References
9
FWCI
7.86
Type
journal article
Language
en
Open access
gold

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.