Latent Semantic Ananlysis for Document Categorization

Vote count:

0

I'm working on a document categorization project wherein I have some crawled text documents on different topics which I want to categorize into pre-decided categories like travel,sports,education etc. Currently the approach I've used is of building a Naive Bayes Classification model in mahout which has given good accuracy result of 70%-75%. But would still like to improve the accuracy by retrieving the semantic dependencies between words of the documents.

I've read about Latent Semantic Analysis(LSA) which creates a term-document matrix and subjects it to mathematical transformation called Singular Value Decomposition(SVD). I'd thought of firstly subjecting the raw documents to LSA followed by k-means clustering on LSA output and then giving the clustered output as input to the Naive Bayes Classifier. But on trying out LSA in Mahout and SemanticVectors the end result seemed to be in numerical format and which after clustering was not acceptable by the Naive Bayes classifier.

Is anything wrong with my approach? Could someone help me with the implementation of LSA or suggest any other approach or method for semantic analysis of text documents.

Thanks

-Hersheeta

asked 46 secs ago

Hersheeta

1

Latent Semantic Ananlysis for Document Categorization