TY  - JOUR
AU  - Salmi, Salim
AU  - Mérelle, Saskia
AU  - Gilissen, Renske
AU  - van der Mei, Rob
AU  - Bhulai, Sandjai
PY  - 2024
DA  - 2024/9/26
TI  - 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
JO  - JMIR Ment Health
SP  - e57362
VL  - 11
KW  - suicide
KW  - suicidality
KW  - suicide prevention
KW  - helpline
KW  - suicide helpline
KW  - classification
KW  - interpretable AI
KW  - explainable AI
KW  - conversations
KW  - BERT
KW  - bidirectional encoder representations from transformers
KW  - machine learning
KW  - artificial intelligence
KW  - large language models
KW  - LLM
KW  - natural language processing
AB  - 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. 
SN  - 2368-7959
UR  - https://mental.jmir.org/2024/1/e57362
UR  - https://doi.org/10.2196/57362
DO  - 10.2196/57362
ID  - info:doi/10.2196/57362
ER  -