Type-token ratio showed a non-monotonic relationship with predicted difficulty, with both very low and very high lexical diversity increasing predicted text difficulty¶

Claim · All claims
Evidence · 1 study · associational r2 · q2
Currency · newest study 2025 · not yet checked against its sources · not reviewed by a person

Subclaims¶

q2 i? Both very low and very high lexical diversity appeared to increase text difficulty, suggesting some lexical variation may support reading comprehension of MWPs. → Kole Norberg 2025

Evidence¶

Kole Norberg 2025¶

Kole Norberg, Husni Almoubayyed, and Stephen Fancsali. (2025). Linguistic Features Predicting Math Word Problem Readability Among Less-Skilled Readers. Proceedings of the 18th International Conference on Educational Data Mining, Palermo, Italy. https://doi.org/10.5281/zenodo.15870274

q2 · i? · associational · r2

Partial dependence plot for type-token ratio (Figure 2) from the random forest. The relationship is hedged by the authors ('appeared to') and is a model-derived pattern, not an experimental manipulation; no effect size is printed.

"However, type-token ratio showed a more complex pattern, where both very low and very high lexical diversity appeared to increase text difficulty, suggesting that some lexical variation may support reading comprehension of MWPs."

Discussion¶

Related Claims¶

• Partial dependence plots showed higher word count, more dependent clauses, and higher custom magnitude raised predicted flag probability, with non-linear relationships
• In the random forest, word count was the most important readability feature while traditional readability formulas ranked near the bottom
• Humanization works by systematically suppressing detector-salient surface cues — long-token ratio, AWL density, and lexical diversity — rather than fragmenting syntax — related
• GPT-assisted writing shows higher lexical diversity, richness, and noun/non-stopword ratios, while independently authored writing shows higher adverb ratio and sentence-length variability — related
• AI-assisted journal entries show higher lexical diversity and more emotion-word usage than unassisted entries — related
• Revising texts to improve readability-formula scores often produces nonexistent or insignificant comprehension gains — related