The truth is no diaper: Human and AI-generated associations to emotional words

TL;DR

This study compares human and AI-generated associations to emotional words, revealing that AI models tend to amplify emotional content and are less creative and predictable than human responses.

Contribution

It provides a novel comparison of human and large language model associations to emotional words, highlighting differences in emotional amplification and creativity.

Findings

Moderate overlap between human and AI associations.

AI associations amplify emotional load.

AI responses are more predictable and less creative.

Abstract

Human word associations are a well-known method of gaining insight into the internal mental lexicon, but the responses spontaneously offered by human participants to word cues are not always predictable as they may be influenced by personal experience, emotions or individual cognitive styles. The ability to form associative links between seemingly unrelated concepts can be the driving mechanisms of creativity. We perform a comparison of the associative behaviour of humans compared to large language models. More specifically, we explore associations to emotionally loaded words and try to determine whether large language models generate associations in a similar way to humans. We find that the overlap between humans and LLMs is moderate, but also that the associations of LLMs tend to amplify the underlying emotional load of the stimulus, and that they tend to be more predictable and less creative than human ones.