Can you tell us more about your role and how you apply data science to your projects?

I use advanced analytical tools (data science empowered textual and voice analytics) to measure psychological constructs and build statistical models that capture workplace behaviour patterns. These methods help us understand complex organisational phenomena with greater precision than traditional approaches allow. I also study the psychological and managerial processes that determine how these technologies are implemented and experienced by employees.

As a core member of the Amsterdam People Analytics Centre (APAC), I also coordinate academic presentations, organize industry-focused events that bring researchers and practitioners together, and speak regularly to our industry partners about AI applications in HR.

Is there a project from this past year that you are most proud of?

Together with some talented bachelor's students, we are exploring Large Language Models (LLMs) as new methods for measuring psychological constructs. This project challenges traditional psychometric approaches by examining how LLMs can analyze textual responses in ways that go beyond conventional natural language processing techniques.

Can LLMs capture subtle psychological dimensions that standard surveys miss? How might they help us understand complex human experiences through more natural forms of expression? Rather than forcing people to choose from predetermined response scales, LLMs could analyze open-ended responses to detect patterns and meanings that traditional methods overlook.

Our initial findings are promising. LLMs appear to address several fundamental limitations of traditional self-report measures (e.g., they may reduce social desirability bias and minimize response fatigue). 

What do you like most about being a DSC member?

The vibrant intellectual ecosystem and the community feeling. The centre's diverse talks and training sessions keep me current with new methodologies. Working alongside researchers who share a passion for data-driven discovery creates unique opportunities. Informal conversations often lead to insights that wouldn't emerge within traditional departmental boundaries. These exchanges push me to think differently about my own research initiatives. 

What is your favourite data science method?

Clustering methods for big data are my favorite because they excel at uncovering heterogeneity—the natural variation in human behavior that disappears when we only examine averages. In organizational settings, clustering helps us identify distinct employee profiles based on multiple characteristics simultaneously, or trace different career development paths that employees actually follow. These methods become especially valuable with the increasingly available high-dimensional data. When we have hundreds of variables describing employees, their behaviors, and their work contexts, clustering provides a more nuanced and concise way of understanding our valuable employees and create targeted interventions.

Are you camp Python/R/or something else?

Camp R all the way!