Back to Search
Start Over
BMS: An improved Dunn index for Document Clustering validation
- Source :
- Communications in Statistics - Theory and Methods. 48:5036-5049
- Publication Year :
- 2018
- Publisher :
- Informa UK Limited, 2018.
-
Abstract
- Document Clustering aims at organizing a large quantity of unlabeled documents into a smaller number of meaningful and coherent clusters. One of the main unsolved problems in the literature is the lack of a reliable methodology to evaluate the results, although a wide variety of validation measures has been proposed. Validation measures are often unsatisfactory with numerical data, and even underperforming with textual data. Our attention focuses on the use of cosine similarity into the clustering process. A new measure based on the same criterion is here proposed. The effectiveness of the proposal is shown by an extensive comparative study.
- Subjects :
- Statistics and Probability
021103 operations research
business.industry
Cosine similarity
0211 other engineering and technologies
k-means clustering
Pattern recognition
Dunn index
02 engineering and technology
Document clustering
01 natural sciences
010104 statistics & probability
ComputingMethodologies_PATTERNRECOGNITION
cosine similarity
Artificial intelligence
0101 mathematics
cluster validation
Cluster analysis
business
K-means
Mathematics
Subjects
Details
- ISSN :
- 1532415X and 03610926
- Volume :
- 48
- Database :
- OpenAIRE
- Journal :
- Communications in Statistics - Theory and Methods
- Accession number :
- edsair.doi.dedup.....dc4469a11a643e1fcd2e0e9d1f303121