Summary of our three analyses.

This paper demonstrates how artificial-intelligence language analysis can inform understanding of human–nature relationships and other social phenomena. We demonstrate three techniques by investigating relationships within the popular word2vec word embedding, which is trained on a sample from over 50,000 worldwide news sources. Our first technique investigates what theory-generated analogies are most similar to nature:people. The resource:user analogy is most similar, followed by the playground:child and gift:receiver analogies. Our second technique explores whether nature-related words are affiliated with words that denote race, class, or gender. Nature words tend slightly toward associations with femininity and wealth. Our third technique demonstrates how the relationship between nature and wellbeing compares to other concepts’ relationships to wellbeing—e.g., spirituality–wellbeing, social relations–wellbeing. Nature is more semantically connected to wellbeing than money, social relations, and multiple other wellbeing correlates. Findings are consistent with previous social science and humanities research on human-nature relationships, but do not duplicate them exactly; our results thus offer insight into dominant trends and prevalence of associations. Our analysis also offers a model for using word embeddings to investigate a wide variety of topics.