I want to find the readability of texts. Can I use a classification method for that? For example, by collecting some basic, intermediate, and advanced texts as training sets and then finding the readability. or using different topics

I found a few topics:

  • fleschKincaidReadingEase
  • fleschKincaidGradeLevel
  • gunningFogScore
  • colemanLiauIndex
  • smogIndex
  • spacheScore
  • daleChallGrade

Using any one these defines a score for the text and we need set the readability point to the text according to the requirement. Please suggest to me which is the best way to find the readability of text.(i.e by using classification or readability topics)

  • $\begingroup$ It might help if you say a little bit more about what this is for. You mentioned something about requirements. What are your requirements exactly? $\endgroup$ – Russell Richie Oct 30 '16 at 0:23
  • $\begingroup$ @Russell Richie I need to define text as basic or intermediate or advanced one.which method should I use 1) classification or 2) using any one of those topics. $\endgroup$ – Dilip Bobby Oct 30 '16 at 13:59
  • $\begingroup$ Why do you need to do a classification method? Why not just use one of those readability indexes to give the readability? Job done. $\endgroup$ – Spacedman Oct 30 '16 at 19:50

I'm going to assume you are also talking about the ability of the person to discern what is being read. This might not be the case.

The question is ill defined.

Depends on the Audience. example: For a medical professional medical texts are much easier.

Depends on the Subject. example: Most people can relate to having a family but without explanation a book about living on the streets could be readable but not relatable.

Depends on the Language: example: in Chinese difficult words can be one character on a page. Looks innocent but students who study the language for 6 years or more may not know the symbol.

Depends on the Form (poem, novel, etc..)

Depends on the Intent. if the intent is to be vague or steganographic then you might never discern what the true intent is.

Language fluency of the writer. Transliterations from another language are difficult to discern the intent.

These aren't all but a few that I've come up off the top of my head. Let me know more in the comments.

I think another way to go is a vocabulary score and it's common usage in subject specific areas. But I would refrain from using terms like Beginner, Intermediate, Advanced. Try nailing difference down a little.


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.