Search engine ads for suicide prevention: analysis of engagement from Indonesia relative to Australia, the USA, and the medical industry standards
Bibliographic record
Abstract
Background: Suicide is a global public health issue, with over 75% of deaths occurring in low- and middle-income countries (LMICs), where access to mental health services is often limited. In Indonesia, where stigma is high and professional support scarce, there is a critical need for scalable, non-traditional approaches to reach individuals at risk. One such approach is using online search engine advertisements to engage individuals searching for suicide-related content and encourage help-seeking. Methods: This study analysed data from an online Google Ads campaign conducted in Indonesia in March 2023, targeting individuals searching for suicide-related keywords. The campaign was co-designed with local experts and people with lived experience. We compared its engagement and cost-effectiveness to similar campaigns previously conducted in the USA and Australia. The primary outcome was total engagement rate (engagements/impressions), and the secondary outcome was effective cost per engagement (adjusted for purchasing power and inflation). Findings: The Indonesian campaign achieved an engagement rate of 11.04%, which was 18 times higher than the US campaign (0.61%) and 15 times higher than the Australian campaign (0.72%). It also had an effective cost per engagement five times lower than those in the USA and Australia. All campaigns outperformed industry standards for health and medical advertising. Interpretation: Search engine advertising is a rapid, cost-effective, and scalable tool to connect individuals in Indonesia with suicide prevention support. These findings underscore the importance of context-specific research in LMICs, where interventions may have greater impact than predicted from high-income country data. Funding: The study was funded by the Australian Department of Foreign Affairs and Trade, Australian-Indonesian Institute (AII2020322), an NHMRC Investigator Grant (GNT2034904), Suicide Prevention Australia Innovation Grant, and the Lynch Family Foundation Research Fellowship in Global Health Equity.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.003 | 0.014 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.002 | 0.002 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.000 | 0.002 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.003 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".