This intends to improve on the Flesch-Kincaid reading level scoring system by replacing the syllables per word with an equation based on word frequency in an English corpus.
Very much a work in progress.
- Plot out frequency - syllables finding.
- Use better syllables program.
- Make program that takes in a tokenized corpus and outputs an equation for calculating syllables.
- Write program that takes in a text file and outputs a grade level.
- Improve program to identify problem sentances and problem words.