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

2024-11-14

AI Summary

This study investigates the cognitive mechanisms underlying human deviations from information-theoretically optimal guessing strategies in Wordle. Methodologically, it integrates semantic (word embedding), phonological (phoneme-based encoding), and orthographic (edit distance) representations to computationally disentangle and quantify the distinct influences of these three linguistic biases on real-time lexical decision-making. Leveraging large-scale behavioral data from actual players and a near-optimal baseline strategy derived from entropy maximization, results show that semantic and phonological similarity significantly increase repetition probability by 37% and 29%, respectively, whereas orthographic similarity exerts a comparatively weaker effect. This work constitutes the first computational decomposition of linguistic cognitive dimensions within a gamified constrained inference task, thereby bridging NLP modeling with cognitive linguistic theory and revealing how deep linguistic representations systematically shape everyday inductive reasoning.

Technology Category

• Natural Language Processing: Lexical Semantics and Morphology
• Cognitive Modeling & Cognitive Systems: Analogy
• Knowledge Representation and Reasoning: Preferences

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems

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

Problem

• Analyzes semantic orthographic phonological biases in Wordle
• Compares human guesses with optimal computational strategies
• Studies constrained language use between natural and artificial tasks

Innovation

• Analyzed semantic orthographic phonological biases
• Compared human guesses with near-optimal ones
• Studied language use in constrained Wordle environment