How well do semantic networks infered from free association and relatedness judgments recover the semantic representations of simulated individuals?

We systematically varied four characteristics of empirical study designs: cue set type, cue set size, number of responses, and response type.

To analyze group differences in the LLM-generated response frequencies from each cluster.

In the tutorial, we show, how we analyzed LLM-generated example free associations to the term 'intelligence', grouping responses into six clusters.

Preprint: Individual-level semantic networks are a critical ingredient for building realistic cognitive models. In our simulation, @ruimata.bsky.social, @dirkwulff.bsky.social, and I show when measurements of individual semantic networks are accurate and when they are not.
📄 arxiv.org/abs/2410.18326

Unsere Wortassoziationsstudie zeigt nun die Häufigkeit der eigenen Assoziationen an. Zudem werden die häufigsten Assoziationen aller Teilnehmer:innen angezeigt.

5 Minuten teilnehmen und eigene Assoziationen vergleichen: smallworldofwords.org/de

By prompting GPT-4 to produce responses typical for different genders, we compare it's gender-specific representation of 'intelligence'.

We demonstrate the associatoR workflow by analyzing GPT-4-generated free associations to the term 'intelligence'.

I am happy to share a preprint of a tutorial with @ruimata.bsky.social and @dirkwulff.bsky.social on analyzing free associations using our new R package associatoR!

Have a look...

📄 at the preprint:
doi.org/10.31234/osf...
💻 at the R package:
github.com/samuelae/ass...