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
BackgroundFor 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...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
JMIR Publications
2024-09-01
|
| Series: | JMIR Mental Health |
| Online Access: | https://mental.jmir.org/2024/1/e57362 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850261723648360448 |
|---|---|
| author | Salim Salmi Saskia Mérelle Renske Gilissen Rob van der Mei Sandjai Bhulai |
| author_facet | Salim Salmi Saskia Mérelle Renske Gilissen Rob van der Mei Sandjai Bhulai |
| author_sort | Salim Salmi |
| collection | DOAJ |
| description |
BackgroundFor 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.
ObjectiveWe 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.
MethodsFrom 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.
ResultsAccording 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.
ConclusionsThis 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. |
| format | Article |
| id | doaj-art-daecd2d0aeb242ae9e4cd41cb15352ad |
| institution | OA Journals |
| issn | 2368-7959 |
| language | English |
| publishDate | 2024-09-01 |
| publisher | JMIR Publications |
| record_format | Article |
| series | JMIR Mental Health |
| spelling | doaj-art-daecd2d0aeb242ae9e4cd41cb15352ad2025-08-20T01:55:19ZengJMIR PublicationsJMIR Mental Health2368-79592024-09-0111e5736210.2196/57362The Most Effective Interventions for Classification Model Development to Predict Chat Outcomes Based on the Conversation Content in Online Suicide Prevention Chats: Machine Learning ApproachSalim Salmihttps://orcid.org/0000-0002-8342-4815Saskia Mérellehttps://orcid.org/0000-0002-0868-1790Renske Gilissenhttps://orcid.org/0000-0002-8009-6326Rob van der Meihttps://orcid.org/0000-0002-5685-5310Sandjai Bhulaihttps://orcid.org/0000-0003-1124-8821 BackgroundFor 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. ObjectiveWe 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. MethodsFrom 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. ResultsAccording 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. ConclusionsThis 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.https://mental.jmir.org/2024/1/e57362 |
| spellingShingle | Salim Salmi Saskia Mérelle Renske Gilissen Rob van der Mei Sandjai Bhulai 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 JMIR Mental Health |
| title | 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 |
| title_full | 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 |
| title_fullStr | 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 |
| title_full_unstemmed | 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 |
| title_short | 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 |
| title_sort | most effective interventions for classification model development to predict chat outcomes based on the conversation content in online suicide prevention chats machine learning approach |
| url | https://mental.jmir.org/2024/1/e57362 |
| work_keys_str_mv | AT salimsalmi themosteffectiveinterventionsforclassificationmodeldevelopmenttopredictchatoutcomesbasedontheconversationcontentinonlinesuicidepreventionchatsmachinelearningapproach AT saskiamerelle themosteffectiveinterventionsforclassificationmodeldevelopmenttopredictchatoutcomesbasedontheconversationcontentinonlinesuicidepreventionchatsmachinelearningapproach AT renskegilissen themosteffectiveinterventionsforclassificationmodeldevelopmenttopredictchatoutcomesbasedontheconversationcontentinonlinesuicidepreventionchatsmachinelearningapproach AT robvandermei themosteffectiveinterventionsforclassificationmodeldevelopmenttopredictchatoutcomesbasedontheconversationcontentinonlinesuicidepreventionchatsmachinelearningapproach AT sandjaibhulai themosteffectiveinterventionsforclassificationmodeldevelopmenttopredictchatoutcomesbasedontheconversationcontentinonlinesuicidepreventionchatsmachinelearningapproach AT salimsalmi mosteffectiveinterventionsforclassificationmodeldevelopmenttopredictchatoutcomesbasedontheconversationcontentinonlinesuicidepreventionchatsmachinelearningapproach AT saskiamerelle mosteffectiveinterventionsforclassificationmodeldevelopmenttopredictchatoutcomesbasedontheconversationcontentinonlinesuicidepreventionchatsmachinelearningapproach AT renskegilissen mosteffectiveinterventionsforclassificationmodeldevelopmenttopredictchatoutcomesbasedontheconversationcontentinonlinesuicidepreventionchatsmachinelearningapproach AT robvandermei mosteffectiveinterventionsforclassificationmodeldevelopmenttopredictchatoutcomesbasedontheconversationcontentinonlinesuicidepreventionchatsmachinelearningapproach AT sandjaibhulai mosteffectiveinterventionsforclassificationmodeldevelopmenttopredictchatoutcomesbasedontheconversationcontentinonlinesuicidepreventionchatsmachinelearningapproach |