Information gain and divergence-based feature selection for machine learning-based text categorization

By Changki Lee, G. G. Lee. Information Processing & Management, 2006

386 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Hybrid attribute reduction based on a novel fuzzy-rough model and information granulation (2007, background): “The other is called filter, which selects attributes with a significance measure, independent of learning algorithms, such as distance [6], information gain [7], consistency [8], similarity [9] [10] and dependency [11].”
Character Recognition Systems: A Guide for Students and Practitioners (2007, background): “Although the filters are more efficient and generic than the wrappers, especially in high-dimensional spaces, they are criticized by another school of researchers [1, 47, 71] in that they may yield a bias that is completely different from that required by a specific classifier.”
Positive approximation: An accelerator for attribute reduction in rough set theory (2010, methodology): “The former employs a learning algorithm to evaluate the selected attribute subsets, and the latter selects attributes by being guided by some significance measures such as information gain [23,46], consistency [6,41], distance [15], dependency [30], and others.”
A novel probabilistic feature selection method for text classification (2012, background): “…2003), document frequency (Yang & Pedersen, 1997), mutual information (Liu, et al., 2009), chi-square (Chen & Chen, 2011), information gain (Lee & Lee, 2006), improved Gini index (Shang, et al., 2007), measure of deviation from Poisson distribution (Ogura, et al., 2009), minimum class…”