A Comparative Study on Feature Selection in Text Categorization

By Yiming Yang, Jan O. Pedersen. 1997

How researchers see this paper

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

Citations in the corpus

Benchmark and Survey of Automated Machine Learning Frameworks (2019, methodology): “Simple domain-agnostic filtering approaches for feature selection are based on information theory and statistics (Pudil et al., 1994; Yang & Pedersen, 1997; Dash & Liu, 1997; Guyon & Elisseeff, 2003).”
Survey on Automated Machine Learning (2019, background): “By examining the features from an information theoretic or statistics viewpoint (Pudil et al., 1994; Yang and Pedersen, 1997; Dash and Liu, 1997; Guyon and Elisseeff, 2003), no domain knowledge is necessary for feature selection.”
Text Categorization as a Graph Classification Problem (2015, methodology): “Compared to most existing feature selection techniques in the field (Yang and Pedersen, 1997), it is unsupervised and corpus-independent as it does not rely on any labeled data like IG, MI or χ2 nor any collection-wide statistics like IDF, which can be of interest for large-scale text categorization”
Feature selection for text classification: A review (2018, background): “Specifically, the MI value between a term s i and a class label c j is defined as MI performs poorly, as compared to other measures such as IG and CHI, due to its bias toward favoring rare terms and its sensitivity to errors in probability estimation [108].”
Efficient phrase-based document indexing for Web document clustering (2004, methodology): “The TF-IDF weighting is also a widely used term weighting scheme [31].”
A Probabilistic Discriminative Model for Android Malware Detection with Decompiled Source Code (2015, methodology): “We use Information Gain (IG) and Chi-square test (CHI) for feature selection [26], which can be calculated very efficiently (i.”
Social Media Text Classification under Negative Covariate Shift (2015, methodology): “And in order to filter out less useful features for the center vector of the positive class, we performed feature selection in the document space using the classic information gain method (Yang and Pedersen, 1997) to empirically choose the most effective 100 features for the positive class.”
Hypergraph spectral learning for multi-label classification (2008, methodology): “We follow the feature selection methods studied in [23] for text documents and extract different numbers of terms to investigate the performance of algorithms.”
A survey on feature selection methods (2014, methodology): “Earlier comparisons for text classification using ranking methods can be found in [22].”
Feature-based transfer learning with real-world applications (2010, background): “It is a fundamental task for Web mining and has been widely studied in the fields of machine learning, data mining and information retrieval [89, 215].”
Distributional Word Clusters vs. Words for Text Categorization (2003, background): “Table 1 summarizes the results that were discussed in this section.”
Concept-Based Information Retrieval Using Explicit Semantic Analysis (2011, methodology): “Information Gain (IG) was originally suggested in the context of a decision tree induction method for choosing which feature to branch on, but is also used extensively in feature selection [Yang and Pedersen 1997].”
Toward integrating feature selection algorithms for classification and clustering (2005, background): “…[40], [63], [81], [90], machine learning [6], [41], [43], [44], and data mining [17], [18], [42], and widely applied to many fields such as text categorization [50], [70], [94], image retrieval [77], [86], customer relationship management [69], intrusion detection [49], and genomic analysis [91].”
A novel probabilistic feature selection method for text classification (2012, methodology): “Among all those techniques, chi square, information gain, Gini index, and deviation from Poisson distribution have been proven to be much more effective (Ogura, et al., 2009; Shang, et al., 2007; Yang & Pedersen, 1997).”
A novel chaotic salp swarm algorithm for global optimization and feature selection (2018, unknown): “Additionally, they have been successfully applied in many applications including image retrieval [21], text categorization [22], customer relationship management [23] and diagnostic medical support systems [24, 25].”
Social tag prediction (2008, methodology): “We chose mutual information due to discussion in Yang and Pedersen [ 19 ].”