Text Complexity Classification Data Mining Model Based on Dynamic Quantitative Relationship between Modality and English Context

Table 1

Heuristic functions for estimating sentence reading difficulty.

Terms	Function	Description
Surface	Len(t)	The length of the sentence T
	Ans(t)	The average number of words (Chinese characters) and syllables (strokes) of the sentence T
	Anc(t)	The average number of word letters (Chinese characters) of the sentence T
Lexical	Lv(t)	The average number of parts-of-speech categories of the sentence T
	Art(t)	The proportion of adjectives in the sentence T
	Ntr(t)	The noun ratio of the sentence T
Grammar	Pth(t)	The syntax tree height of the sentence T
	Anp(t)	The average number of phrases (noun phrases, verb phrases, and prepositional phrases) in the sentence T