classification model problem

goku

Hi everybody,

I'm having a classification problem and I need some help.
Let's say I have a group of school classes, each one consists of students.
I want to examine the writing skills of each class and classify them into 2 cateogies -> use of advanced vocabulary and use of normal vocabulary.

I'll gather a sample of documents for training, so my problem is if it's possible to determine if a class as a whole belongs to the first or the second category, depending on the characterazation of each of the class' student.

Can I create a training model for a school class containing its students or I'll have to find an alternative way using just text classification, let's say determine if a student makes use of advanced vocabulary in his writings and then find an algorithm to determine if he uses advanced vocabulary or normal vocabulary in his writings?

goku

anyone? 

haddock

Hi there,

I think I understand what you are trying to do, so my suggestion would be to make sure you can classify students correctly before you move on to classifying classes, which I suspect is just an aggregation of individual scores.

With regard to classifying a student you might also consider also mistakes in vocabulary and grammar, otherwise nonsense speakers could get misclassified.

Best

H

goku

Hi haddock,
thank you very much for your help. I'll follow your suggestion!