Related Experiment Video
Updated: Jul 13, 2026

Integrating Computerized Linguistic and Social Network Analyses to Capture Addiction Recovery Capital in an Online Community
Published on: May 31, 2019
Applying language models for suicide prevention: evaluating news article adherence to WHO reporting guidelines
Zohar Elyoseph1,2,3, Inbar Levkovich4, Eyal Rabin5
1School of Counseling and Human Development, The Faculty of Education, The University of Haifa, Haifa, Israel. zohare@yvc.ac.il.
Generative AI, like ChatGPT-4, can effectively evaluate suicide news coverage against WHO guidelines. This technology offers a scalable solution to promote responsible media reporting and improve public health outcomes.
Area of Science:
- Public Health
- Media Studies
- Artificial Intelligence
Background:
- Responsible media reporting on suicide is vital for public health.
- Irresponsible coverage may inadvertently promote suicidal behaviors.
- Scalable solutions are needed to ensure adherence to reporting guidelines.
Purpose of the Study:
- To assess the capability of large language models (LLMs) in evaluating suicide-related news articles.
- To compare LLM performance against human reviewers using World Health Organization (WHO) guidelines.
- To explore AI's potential in promoting responsible suicide reporting.
Main Methods:
- Evaluated 40 suicide-related news articles.
- Compared assessments from two human reviewers and two LLMs (ChatGPT-4, Claude Opus).
- Utilized Intraclass Correlation Coefficients (ICC) to measure agreement.
Main Results:
- ChatGPT-4 showed strong agreement with human reviewers (ICC = 0.81–0.87).
- Claude Opus demonstrated good agreement with human reviewers (ICC = 0.73–0.78), but estimated lower compliance.
- No significant differences in overall evaluations between ChatGPT-4 and humans were found.
Conclusions:
- LLMs show significant potential for promoting responsible suicide reporting.
- AI can provide immediate feedback to journalists, enhancing guideline adherence.
- This technology could positively transform public discourse on suicide.
More Related Videos
Related Concept Videos
SBAR II: Application of SBAR
SBAR Report from a Nurse to a Health Care Provider
S: "Hello, Dr. Smith. This is Jane, RN, from the Med Surg unit. I am calling to tell you about Ms. White in Room 210, who is experiencing increased pain and redness at her incision site. Her recent...
Types of Reports III: Telephone and Verbal Reports
Here's an overview of each type:
Telephone Orders
Modeling in Therapy
Participant Modeling
Participant modeling involves therapists demonstrating calm and effective behaviors in situations...

