Wordle, a popular word-guessing game, challenges players to identify a five-letter secret word through iterative guesses and feedback on letter placement. The players must figure out the secret word within six guesses. After each guess, the letters will be color-coded based on different criteria. Optimizing the choice of guesses is critical for maximizing success within the limited attempts allowed. In this study, the application of Shannon entropy is explored as a strategy for selecting words that maximize information gain at each step of the game. By quantifying the uncertainty reduction achieved by potential guesses, this method prioritizes words that are likely to narrow the solution space most effectively. The experimental results demonstrate that entropy-based word selection improves performance compared to a heuristic approach based on selecting words by letter distribution, providing a systematic framework for decision-making in Wordle. This study can be used as a baseline for implementing Shannon entropy in different games.
Aladaileh et al. (Mon,) studied this question.