JMIR Publications

ABSTRACT

Background:

To provide 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 chat services, which produce large amounts of text data, to use in large-scale analysis.

Objective:

We trained a machine learning classification model and identify which counsellor utterances have 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 (like hopelessness, feeling entrapped, will to live, etc) before and after a chat conversation of the suicide prevention helpline in the Netherlands (113 Suicide Prevention). Machine learning text analysis was used to predict help seeker scores on these factors. The model was interpreted, to show which messages of the helpers in a conversation contributed to the prediction.

Results:

According to the machine learning model, positive affirmations and expressing involvement of helpers contributed to improved scores of help seekers. Use of macros and ending the conversation 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 conversations, emphasizing the value of an evocative style with questions, positive affirmations, and practical advice. It also underscores the potential of machine learning in helpline analysis.