Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2024 Sep 26:11:e57362.
doi: 10.2196/57362.

The Most Effective Interventions for Classification Model Development to Predict Chat Outcomes Based on the Conversation Content in Online Suicide Prevention Chats: Machine Learning Approach

Salim Salmi  1 , Saskia Mérelle  1 , Renske Gilissen  1 , Rob van der Mei  2 , Sandjai Bhulai  3
Affiliations

The Most Effective Interventions for Classification Model Development to Predict Chat Outcomes Based on the Conversation Content in Online Suicide Prevention Chats: Machine Learning Approach

Salim Salmi et al. JMIR Ment Health. .

Abstract

Background: For the provision of optimal care in a suicide prevention helpline, it is important to know what contributes to positive or negative effects on help seekers. Helplines can often be contacted through text-based chat services, which produce large amounts of text data for use in large-scale analysis.

Objective: We trained a machine learning classification model to predict chat outcomes based on the content of the chat conversations in suicide helplines and identified the counsellor utterances that had the most impact on its outputs.

Methods: From August 2021 until January 2023, help seekers (N=6903) scored themselves on factors known to be associated with suicidality (eg, hopelessness, feeling entrapped, will to live) before and after a chat conversation with the suicide prevention helpline in the Netherlands (113 Suicide Prevention). Machine learning text analysis was used to predict help seeker scores on these factors. Using 2 approaches for interpreting machine learning models, we identified text messages from helpers in a chat that contributed the most to the prediction of the model.

Results: According to the machine learning model, helpers' positive affirmations and expressing involvement contributed to improved scores of the help seekers. Use of macros and ending the chat prematurely due to the help seeker being in an unsafe situation had negative effects on help seekers.

Conclusions: This study reveals insights for improving helpline chats, emphasizing the value of an evocative style with questions, positive affirmations, and practical advice. It also underscores the potential of machine learning in helpline chat analysis.

Keywords: BERT; LLM; artificial intelligence; bidirectional encoder representations from transformers; classification; conversations; explainable AI; helpline; interpretable AI; large language models; machine learning; natural language processing; suicidality; suicide; suicide helpline; suicide prevention.

PubMed Disclaimer

Conflict of interest statement

Conflicts of Interest: None declared.

Figures

Figure 1
Figure 1
Overview of the hierarchical classification of chats.
Figure 2
Figure 2
Histogram of logits for the hierarchical weighted model.
See this image and copyright information in PMC

Similar articles

See all similar articles

Cited by

References

    1. Gould MS, Pisani A, Gallo C, Ertefaie A, Harrington D, Kelberman C, Green S. Crisis text-line interventions: Evaluation of texters' perceptions of effectiveness. Suicide Life Threat Behav. 2022 Jun;52(3):583–595. doi: 10.1111/sltb.12873. https://europepmc.org/abstract/MED/35599358 - DOI - PMC - PubMed
    1. Pisani AR, Gould MS, Gallo C, Ertefaie A, Kelberman C, Harrington D, Weller D, Green S. Individuals who text crisis text line: Key characteristics and opportunities for suicide prevention. Suicide Life Threat Behav. 2022 Jun;52(3):567–582. doi: 10.1111/sltb.12872. https://europepmc.org/abstract/MED/35615898 - DOI - PMC - PubMed
    1. Gould MS, Lake AM, Munfakh JL, Galfalvy H, Kleinman M, Williams C, Glass A, McKeon R. Helping callers to the national suicide prevention lifeline who are at imminent risk of suicide: evaluation of caller risk profiles and interventions implemented. Suicide Life Threat Behav. 2016 Apr 04;46(2):172–90. doi: 10.1111/sltb.12182. - DOI - PubMed
    1. Mokkenstorm JK, Eikelenboom M, Huisman A, Wiebenga J, Gilissen R, Kerkhof AJFM, Smit JH. Evaluation of the 113 online suicide prevention crisis chat service: outcomes, helper behaviors and comparison to telephone hotlines. Suicide Life Threat Behav. 2016 Aug 19;47(3):282–296. doi: 10.1111/sltb.12286. - DOI - PubMed
    1. Mishara BL, Chagnon F, Daigle M, Balan B, Raymond S, Marcoux I, Bardon C, Campbell JK, Berman A. Which helper behaviors and intervention styles are related to better short-term outcomes in telephone crisis intervention? Results from a Silent Monitoring Study of Calls to the U.S. 1-800-SUICIDE Network. Suicide Life Threat Behav. 2007 Jun;37(3):308–21. doi: 10.1521/suli.2007.37.3.308. - DOI - PubMed

LinkOut - more resources