Turkish Journal of Computer and Mathematics Education
Journal license

Journal

Turkish Journal of Computer and Mathematics Education


Volume
& Issue

Volume 9, Issue 3


Published
on


Pages

766-775


DOI

Article

Concepts Identification in Large Scale Datasets for Efficient Text Categorization


Authors

Y. Sri Lalitha Affiliation:
Department of IT, Gokaraju Rangaraju Institute of Engineering and Technology
and Lohitha Bhogapati Affiliation:
M.Tech Student, GRIET, Hyderabad


Abstract

Concept Based Document removal is an increasing modern Research with the intention of activities in the direction of gather important in sequence as of normal words processing term. It might be there uncertainly eminent because the path of investigative texts toward takes out in sequence with the intention to be realistic happening exacting purposes. In this case, the mining representation capable of detain provisions that identify the concepts of the ruling or document, which tends toward notice the theme of the document. In an vacant job, the concept-based taking out representation be utilized merely intended for usual transcript credentials clustering in accumulation to clustered the transcript parts of the credentials in count to capably discovers important the same concepts between credentials, according toward the semantics sentence. however the negative aspect of the job be with the intention of the accessible job cannot subsist connected toward net credentials clustering along with the transcript categorization intended for the credentials be an undependable lone. Concept-Based drawing out representation used for attractive transcript Clustering.


Keywords

Concept-based drawing out form, Concept-based similarity, Text clustering, Document clustering, Hadoop


Citation

Lalitha, Y. S. & Bhogapati, L. (2018). Concepts identification in large scale datasets for efficient text categorization. Turkish Journal of Computer and Mathematics Education, 9(3), 766–775.

Published by: Engineering Journals

Engineering Journals Logo