Predicting recurrent chat contact in a psychological intervention for the youth using natural language processing

Research output: Journal contributionsJournal articlesResearchpeer-review

Authors

Chat-based counseling hotlines emerged as a promising low-threshold intervention for youth mental health. However, despite the resulting availability of large text corpora, little work has investigated Natural Language Processing (NLP) applications within this setting. Therefore, this preregistered approach (OSF: XA4PN) utilizes a sample of approximately 19,000 children and young adults that received a chat consultation from a 24/7 crisis service in Germany. Around 800,000 messages were used to predict whether chatters would contact the service again, as this would allow the provision of or redirection to additional treatment. We trained an XGBoost Classifier on the words of the anonymized conversations, using repeated cross-validation and bayesian optimization for hyperparameter search. The best model was able to achieve an AUROC score of 0.68 (p < 0.01) on the previously unseen 3942 newest consultations. A shapely-based explainability approach revealed that words indicating younger age or female gender and terms related to self-harm and suicidal thoughts were associated with a higher chance of recontacting. We conclude that NLP-based predictions of recurrent contact are a promising path toward personalized care at chat hotlines.

Original languageEnglish
Article number132
Journalnpj Digital Medicine
Volume7
Issue number1
Number of pages9
DOIs
Publication statusPublished - 12.2024

Bibliographical note

Publisher Copyright:
© The Author(s) 2024.

Recently viewed

Publications

  1. Self-perceived quality of life predicts mortality risk better than a multi-biomarker panel, but the combination of both does best
  2. Internet and computer based interventions for cannabis use
  3. Optimal control strategies for PMSM with a decoupling super twisting SMC and inductance estimation in the presence of saturation
  4. A Two-Stage Sliding-Mode High-Gain Observer to Reduce Uncertainties and Disturbances Effects for Sensorless Control in Automotive Applications
  5. A Configurational Approach to Investigating the Relationship Between Organizational Culture and Organizational Effectiveness Using Fuzzy-Set Analysis
  6. Sensorless Control of AC Motor Drives with Adaptive Extended Kalman Filter
  7. Geometric Properties on the Perfect Decoupling Disturbance Control in Manufacturing Systems
  8. Validity claims in context
  9. Work availability types and well-being in Germany–a latent class analysis among a nationally representative sample
  10. The challenges of gamifying CSR communication
  11. Like! You saved #energy today. Fostering Energy Efficiency in Buildings – The implementation of social media patterns as symbols in Building Management Systems‘ Graphical User Interfaces using Peirce’s semeiosis as a communication concept
  12. Diversity: Konzept. Programmatik. Praxis.
  13. A transfer operator based numerical investigation of coherent structures in three-dimensional Southern ocean circulation
  14. Using (Quantitative) Structure-Activity Relationships in Pharmaceutical Risk Assessment
  15. Schreibberatung
  16. Development and criterion validity of differentiated and elevated vocational interests in adolescence
  17. Considering Teachers’ Beliefs, Motivation, and Emotions Regarding Teaching Mathematics With Digital Tools
  18. A Transatlantic Symposium on the Restatement (Fourth)
  19. Principals between exploitation and exploration
  20. Sustainable Development
  21. Interpersonal Physiological Synchrony Predicts Group Cohesion
  22. Der "fachdidaktische Code" der Lebenswelt- und/oder (?) Situationsorientierung
  23. Glancing into the Applied Tool Box
  24. Credit Constraints and the Extensive Margins of Exports
  25. About the Sense of Useless Software
  26. Tree-tree interactions and crown complementarity
  27. Effects on the (CSR) Reputation