Wordle data mining based on deep learning

Jia Song; Fangyuan Zhu; Zirong Zhang

doi:10.1117/12.2685595

15 August 2023 Wordle data mining based on deep learning

Jia Song, Fangyuan Zhu, Zirong Zhang

Author Affiliations +

Proceedings Volume 12719, Second International Conference on Electronic Information Technology (EIT 2023); 127193I (2023) https://doi.org/10.1117/12.2685595
Event: Second International Conference on Electronic Information Technology (EIT 2023), 2023, Wuhan, China

Abstract

In just a few months, Wordle has grown from a few players to several million users after "viral spread" by major social platforms. To study the secret of Wordle game success We construct a time-series based model by building a QL-LSTM model to explain the daily variation in the number of reported results and try to predict the game reports on March 1, 2023, which has a prediction interval of [21127, 24093], while we construct features for vowel and consonant digits, wordiness, number of letter repetitions, and word frequency. and assessed the relevance and significance of the percentage of those reporting being in hard mode. Only word frequency and percentage in hard mode had a slightly negative and significant relationship. The mystery of Wordle is unveiled by the above exploration.

Citation Download Citation

Jia Song, Fangyuan Zhu, and Zirong Zhang "Wordle data mining based on deep learning", Proc. SPIE 12719, Second International Conference on Electronic Information Technology (EIT 2023), 127193I (15 August 2023); https://doi.org/10.1117/12.2685595

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

;

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE