Dragan Stoll
Dragan Stoll
ZHAW
School of Social Work
Institute of Childhood, Youth and Family
Pfingstweidstrasse 96
8037 Zürich
Work at ZHAW
Position
Research associate / PhD Candidate
Focus
Development of machine learning models for text analysis and predictive analytics
Experience
- Research Associate
ZHAW Zurich University of Applied Sciences
09 / 2024 - today - Research Assistance
ZHAW Zurich University of Applied Sciences
09 / 2022 - 08 / 2024 - Data Scientist
Cantonal Office for Youth and Career Services, Canton Zurich
05 / 2013 - 06 / 2022 - Research Associate
Federal Office of Information Technology, Systems and Telecommunication FOITT
09 / 2012 - 04 / 2013 - Research Associate
gfs-zürich Markt- & Sozialforschung
10 / 2000 - 06 / 2012
Education and Continuing education
Education
- lic. phil. / Master of Arts / Political Science, Computer Science
University of Zurich
10 / 2005 - 05 / 2012 - Business Economist HFW / Business Administration
Swiss Institute of Business Administration (SIB)
09 / 2001 - 10 / 2004
Network
ORCID digital identifier
Projects
- Interventions in domestic conflicts involving older people: An analysis of complaints handled by the Independent Complaints Office for Older People (UBA) / Team member / ongoing
- AI for Child Protection: Developing and Evaluating Machine Learning Applications for Decision Support in Child Protection / Project leader / ongoing
- Assessing and improving access to health and social care SErvices for children RENdered vulnerable by Abuse / Team member / ongoing
- Algorithmic fairness in child protection decision-making / Team member / completed
Publications
Articles in scientific journal, peer-reviewed
- Perron, B. E. et al. (2026) 'Validation of a small language model for DSM-5 substance category classification in child welfare records', Journal of Evidence-Based Social Work. doi: 10.1080/26408066.2026.2673377.
- Qi, Z. et al. (2026) 'Small models achieve large language model performance : evaluating reasoning-enabled AI for secure child welfare research', Journal of Evidence-Based Social Work. doi: 10.1080/26408066.2026.2616711.
- Stoll, D. et al. (2025) 'Case reports unlocked : leveraging retrieval-augmented generation with large language models to advance research on psychological child maltreatment', Child Abuse & Neglect, 169(107653). doi: 10.1016/j.chiabu.2025.107653.
- Stoll, D., Wehrli, S. and Lätsch, D. (2024) 'Case reports unlocked : harnessing large language models to advance research on child maltreatment', Child Abuse & Neglect, 160(107202). doi: 10.1016/j.chiabu.2024.107202.
Written conference contributions, peer-reviewed
Stoll, D. et al. (2025) 'Case reports unlocked : leveraging retrieval-augmented generation with large language models to advance research on child psychological maltreatment', in 18th International Conference of the European Scientific Association on Residential & Family Care for Children and Adolescents (EuSARF), Zagreb, Croatia, 8-12 September 2025.
Other publications
Reimer, D., Stoll, D. and Tausendfreund, T. (2025) '«Transformation, Transition and Innovation in Child and Youth Care», EuSARF Konferenz im September 2025 in Zagreb', Forum Erziehungshilfen, 31(5), pp. 300–301. doi: 10.3262/FOE2505300.
Oral conference contributions and abstracts
- Eicher, N. F. et al. (2026) 'Child protection in challenging contexts : trends in administrative data and experiences of service users during and after Covid-19', in 7th Annual Meeting of the Swiss Society for Early Childhood Research (SSECR), Fribourg, Switzerland, 2-3 February 2026.
- Eicher, N. F. et al. (2025) 'Impact of the Covid-19 pandemic on child protection services through the lens of administrative data : a systematic review', in ISPCAN Congress, Vilnius, Lithuania, 5-9 October 2025.
- Stoll, D. et al. (2025) 'Case reports unlocked : applying RAG-prompting methods and large language models to advance research on child maltreatment', in ISPCAN Congress, Vilnius, Lithuania, 5-9 October 2025.
- Eicher, N. F. et al. (2025) 'A multi-sectoral review of child protection : trends and transitions in administrative data from pre- to post-pandemic', in 18th International Conference of the European Scientific Association on Residential & Family Care for Children and Adolescents (EuSARF), Zagreb, Croatia, 8-12 September 2025.
- Stoll, D., Lätsch, D. and Wehrli, S. (2024) 'Applying machine learning text classification methods and large language models for data collection of mentions of child maltreatment', in ISPCAN Congress, Uppsala, Sweden, 18-21 August 2024.