A method for K-Means seeds generation applied to text mining.

Daniel Vélez Jorge Sueiras Alejandro Ortega José Francisco Vélez

Published in: Stat. Methods Appl. (2016)

Keyphrases

k means
clustering method
text mining
experimental evaluation
machine learning
high accuracy
probabilistic model
cost function
significant improvement
prior knowledge
high precision
information extraction
pairwise
databases
detection method
spectral clustering
unsupervised clustering