A Survey on Improving the Clustering Performance in Text Mining for Efficient Information Retrieval
Journal Title: INTERNATIONAL JOURNAL OF ENGINEERING TRENDS AND TECHNOLOGY - Year 2014, Vol 8, Issue 5
Abstract
In recent years, the development of information systems in every field such as business, academics and medicine has led to increase in the amount of stored data year by year. A vast majority of data are stored in documents that are virtually unstructured. Text mining technology is very helpful for people to process huge information by imposing structure upon text. Clustering is a popular technique for automatically organizing a large collection of text. However, in real application domains, the experimenter possesses some background knowledge that helps in clustering the data. Traditional clustering techniques are rather unsuitable of multiple data types and cannot handle sparsity and high dimensional data. Co-clustering techniques are adopted to overcome the traditional clustering technique by simultaneously performing document and word clustering handling both deficiencies. Semantic understanding has become essential ingredient for information extraction, which is made by adopting constraints as a semi-supervised learning strategy. This survey reviews on the constrained co-clustering strategies adopted by researchers to boost the clustering performance. Experimental results using 20-Newsgroups dataset shows that the proposed method is effective for clustering textual documents. Furthermore, the proposed algorithm consistently outperformed all the existing constrained clustering and coclustering methods under different conditions.
Authors and Affiliations
S. Saranya , R. Munieswari
Keywords
Related Articles
- EP ID EP131614
- DOI -
- Views 107
- Downloads 0
Design of Remote Intelligent Smart Home System Based on Zigbee and GSM Technology
Based on ZIGBEE and GPRS technology a wireless remote and smart home security system has developed. Wireless remote systems for smart home application is developed to analysis and detect the status of home equipm...
Face Recognition using LBP Coefficient Vectors with SVM Classifier
The development of automatic visual control system is a very important research topic in computer vision. In many application including texture based, face recognition system, in this paper we analysis for the face recog...
A New Paradigm on Experimental Investigation of Concrete for E- Plastic Waste Management
This research paper seeks to optimize the benefits of using E Plastic Waste in the fiber form in concrete. The E Plastic waste (insulation wires) is shredded into fibers of specific size and shape. Several design concret...
A Simulator To Estimate The Cancellations In YM
In case of Yield Management (YM), even if the yield is optimized using some technique, it is not guaranteed that the final revenue obtained will be maximum or optimized. Since in almost all the industries where YM can be...
Fingerprint Based Gender Classification Using 2D Discrete Wavelet Transforms and Principal Component Analysis
Fingerprint evidence is undoubtedly the most reliable and acceptable evidence till date in the court of law. Fingerprints are obtained at the site of crime and in many old monuments and in excavated things. Estimat...