A mathematical model can identify what language a Scrabble game is being played in without looking at a single letter on the board.
Scrabble boards have a geometric entropy that is unique to the grammar and structure of specific languages. Players leave behind a structural fingerprint as they build words across the grid. We usually think of language as a collection of sounds and symbols. The data reveals that the shape of how we think is so distinct that it persists even when the words themselves are removed. You could tell the difference between a French and an English speaker just by looking at the density of their tiles.
Statistical mechanics for Scrabble predicts strategy, entropy and language
arXiv · 2605.00813
The crossword-like patterns of tiles in Scrabble form connected graphs of occupied sites on a square lattice. We find the most structureless description that reproduces means and covariances observed in real Scrabble games by adapting a maximum entropy approach to connected graphs. This pairwise model captures the data well, and predicts word-length statistics and geometric features of the Scrabble graphs correctly; in addition, the parameters of this model are interpretable and allow us to unde