Volume 10 Issue 2 - April 2018

  • 1. Survey on the principal challenge of text mining

    Authors : Shweta Ganiger

    Pages : 381-386

    DOI : http://dx.doi.org/10.21172/1.102.60

    Keywords : Dimensionality Reduction, Feature selection, Feature extraction, SVD

    Abstract :

    Text mining is in a loosely systemized set of competing technologies that function as analytical with no clear dominance. It is the processing of unstructured text data. One of the main challenges is Dimensionality reduction, the dimensionality reduction is a process of reducing the number of random variables under consideration in a text document. It consists of two types feature selection and feature extraction. In this paper, the singular value decomposition(SVD) and random forest technique of the dimensionality reduction are elaborated to know the how the dimensionality is reduced using these techniques. The survey on dimensionality reduction problem proves that the random forest gives better accuracy and performs well for documents. There are many other dimensionality reduction algorithms available to reduce the dimension of documents.

    Citing this Journal Article :

    Shweta Ganiger, "Survey on the principal challenge of text mining", Volume 10 Issue 2 - April 2018, 381-386