Abstract
Wordle is an online word puzzle game that gained viral popularity in January 2022. The goal is to guess a hidden five letter word. In order to study the distribution of the reported results and the difficulty of the words, based on BP neural network theory, combined with the advantages of Genetic Algorithm in Stability and speed, a neural network prediction model is constructed and the model can be used to predict the percentage distribution of the number of player guesses for a given word on a given number of days. In addition, a Canopy-Kmeans-based word difficulty classification model was further developed. It can be combined with the previous neural network model to determine whether the difficulty of guessing a given word is easy, normal or hard.
Publisher
Darcy & Roy Press Co. Ltd.
Reference10 articles.
1. Anderson B J, Meyer J G. Finding the optimal human strategy for wordle using maximum correct letter probabilities and reinforcement learning [J]. arXiv preprint arXiv:2202.00557, 2022.
2. Brown K A. MODEL, GUESS, CHECK: Wordle as a primer on active learning for materials research [J]. npj Computational Materials, 2022, 8(1): 97.
3. Han J X, Ma M Y, Wang K. Product modeling design based on genetic algorithm and BP neural network [J]. Neural Computing and Applications, 2021, 33: 4111-4117.
4. Ahmed M, Seraj R, Islam S M S. The k-means algorithm: A comprehensive survey and performance evaluation [J]. Electronics, 2020, 9(8): 1295.
5. Cui Y, Liu H, Wang Q, et al. Investigation on the ignition delay prediction model of multi-component surrogates based on back propagation (BP) neural network [J]. Combustion and Flame, 2022, 237: 111852.