Semantic, Orthographic, and Phonological Biases in Humans' Wordle Gameplay

TL;DR

This study investigates how human players' guesses in Wordle are affected by semantic, orthographic, and phonological factors, comparing human behavior with NLP-optimized guesses to understand language use in constrained environments.

Contribution

The paper introduces an analysis of biases in human Wordle gameplay and compares it with near-optimal NLP-based guesses, revealing insights into language processing under game constraints.

Findings

Human guesses are influenced by semantic, orthographic, and phonological biases.

Comparison shows deviations from near-optimal NLP guesses.

Insights into human language use in constrained settings.

Abstract

We show that human players' gameplay in the game of Wordle is influenced by the semantics, orthography, and phonology of the player's previous guesses. We compare actual human players' guesses with near-optimal guesses using NLP techniques. We study human language use in the constrained environment of Wordle, which is situated between natural language use and the artificial word association task