This page is a demonstration of a text classification approach to estimating the reading difficulty of text.
Accuracy generally improves with text length. The software will provide estimates for texts of any length, but a minimum length of 30 words is recommended. Also, the system is generally more accurate for grade levels above 2.
Type or paste your text into the box below and press "Submit" to obtain an estimate of the difficulty of your text.
The details of this approach are currently being written up for publication. The method for predicting readability based on grammatical features improves upon the one described in the following paper:
Heilman, M., Collins-Thompson, K., Callan, J., and Eskenazi, M. (To Appear). Combining Lexical and Grammatical Features to Improve Readability Measures for First and Second Language Texts. Proceedings of the Human Language Technology Conference. Rochester, NY.
For more information, on the REAP project, visit reap.cs.cmu.edu.
|
|
This research was sponsored by the National Science Foundation and the U.S. Department of Education's Institute for Education Sciences. Any opinions, findings, conclusions or recommendations expressed on this Web site are those of the author(s), and do not necessarily reflect those of the sponsors. | |
Updated on July 24, 2007.
http://www.cs.cmu.edu/~mheilman/