Abstract
This paper investigated the popularity and difficulty level of Wordle, an online daily puzzle game. The study examined the number of players reporting scores, the number of players on hard mode, and the percentage of players who guessed the word. After removing outliers and misspelling words, the study used time series analysis to predict future numbers of reported results. We found that Wordle had entered the decline period and recommended the last 150 days' smooth data for more accurate prediction interval results. Furthermore, the study developed the Wordle Word n-tries Percentage Prediction Model, which accurately predicts the associated percentages of tries required to solve a given word. The model uses the Regressor Chain algorithm to correlate independent variables such as word frequency, lexical properties, number of common letter combinations, and date with dependent variables. Based on the Decision Tree, the model predicts the associated percentages of tries required to solve a given word.
Publisher
Darcy & Roy Press Co. Ltd.
Reference16 articles.
1. Bonthron M. Rank one approximation as a strategy for Wordle [J]. arXiv preprint arXiv: 2204.06324, 2022.
2. de Silva N. Selecting seed words for wordle using character statistics [J]. arXiv preprint arXiv: 2202.03457, 2022.
3. Kalpakis K, Gada D, Puttagunta V. Distance measures for effective clustering of ARIMA time-series [C]//Proceedings 2001 IEEE international conference on data mining. IEEE, 2001: 273 - 280.
4. Li I. Analyzing difficulty of Wordle using linguistic characteristics to determine average success of Twitter players [J]. 2022
5. Melki G, Cano A, Kecman V, et al. multi-target support vector regression via correlation regressor chains [J]. Information Sciences, 2017, 415: 53 - 69.