Our research group works at the intersection of computational social science and mental health.
We strive to improve scientific methods and insights by developing, adapting and validating AI-driven methods.
We analyse language from digital text and audio recordings to gain psychological insights and explore complex psychological experiences.
Software for Social Sciences
We develop and maintain an ecosystem of open-source R-packages designed to facilitate the use of state-of-the-art AI methods and large language models in social sciences:
- talk transforms voice recordings into text, audio features, or embeddings optimized for capturing psychological dimensions in speech.
- text converts written text into word embeddings and includes machine learning techniques optimized for social sciences to analyze these embeddings.
talk and text provide access to Large Language Models from Hugging Face.
- topics visualizes language patterns into topics to generate psychological insights.
You can contact us if you’d like us to host a workshop on using these packages for your research group, department, or organization.
Probed language-based assessments
Over the past decade, we have pioneered the development of probed language-based assessments, enabling individuals to express their thoughts and feelings in their own words. Language is a natural way to communicate and describe complex psychological states of mind. Our research has shown that analysing descriptions of mental states with AI produces highly valid and reliable assessments. In our research, we have, through robust and open methods, demonstrated that these assessments are:
- Valid and Reliable: Ensuring accuracy and consistency.
- Descriptive: Capturing the richness of personal experiences – providing psychological insights beyond rating scale scores.
- Predictive: Providing insights into future behaviours.
We have researched numerous psychological constructs and topics using probed language-based assessments, including:
- Well-being, including experienced well-being, harmony in life and satisfaction with life
- Mental health problems, including depression, anxiety and stress
- Personality, including implicit motives
Our assessment models are accessible through the Language-Based Assessment Models (L-BAM) library.
Related methods projects
The LEADING Guidelines: Accurate assessments, such as for depression, are essential but face many challenges. Similar assessment methods across psychology, psychiatry, and medicine involve experts reviewing several sources of longitudinal information to achieve best-estimate assessments. However, the quality of these assessments is often difficult to evaluate due to poor reporting of the assessment methods. Referring to an assessment as a best-estimate assessment (and sometimes even a gold standard) while vaguely reporting the assessment method is alarming. To tackle this gap, we have developed the LEADING reporting guideline to support researchers in reporting research that aims to achieve best-estimate assessments.
Sequential Evaluation with Model Pre-registration: We developed the Sequential Evaluation with Model Pre-registration (SEMP) –a study design procedure that combines good scientific practices (i.e., pre-registration) with robust artificial intelligence (AI) model development practices (i.e., data preprocessing, hyper-parameter tuning, and out-of-sample test).
Mental health assessments dashboard
The Harmony in Life Scale: Translations and validations
Precision mental health
MIND – Sweden’s largest suicide prevention helpline – together, we are researching and improving their chat helplines.
Sund Psykologi comprises three clinics in Malmö and Lund, providing therapy to more than 1000 patients/year.
Minding Health (founded by Oscar Kjell) provide language-based assessments in clinical settings.
Research collaborators
The Word Well-Being Project: Stony Brook University, Stanford University, and Pennsylvania University.
The LEADING Guidelines: Lund University, Leiden University, Stonybrook University, Dundee University, Copenhagen University, University of Amsterdam
The Nordic Well-Being Consortium
The Love and Human Strengths Project at Standford University
