Feature selection for text categorization on imbalanced data

By Zhaohui Zheng, Xiaoyun Wu, Rohini K. Srihari. SKDD, 2004

594 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Information Systems

View Paper: https://www.semanticscholar.org/paper/ebe5b9a24275793de12cb367802db19690751f41

How researchers see this paper

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

In Artificial Intelligence

In Information Systems

Citations in the corpus

Outlier Analysis (2013, background): “impact of class imbalance is relevant even for feature selection [335, 511], because it is more desirable to select features which are more indicative of the rare class.”
Classifying Software Changes: Clean or Buggy? (2008, methodology): “Using the chi-square measure, which is commonly used for feature selection [54], each feature is ranked to determine how correlated it is to the buggy and clean classes.”
On the effectiveness of preprocessing methods when dealing with different levels of class imbalance (2012, methodology): “Experiments over 17 real data sets using eight different classifiers, four resampling algorithms and four performance evaluation measures show that over-sampling the minority class consistently outperforms under-sampling the majority class when data sets are strongly imbalanced, whereas there are…”
Editorial: special issue on learning from imbalanced data sets (2004, background): “Zheng and Srihari [62] suggest that existing measures used for feature selection are not very appropriate for imbalanced data sets.”
Classification with class imbalance problem: A review (2015, methodology): “Authors from [64] described a new feature selection method to solve the problem with imbalanced text documents by exploiting the combination of most useful features from both classes, positive and negative.”
Link prediction using supervised learning (2006, background): “Fortunately, there are algorithms [12, 25] that have been adapted for imbalanced datasets, so an approach outlined in these algorithms should be followed in this situation.”
A survey on addressing high-class imbalance in big data (2018, background): “[23] investigate feature selection for text categorization with imbalanced data.”
Long Document Classification From Local Word Glimpses via Recurrent Attention Learning (2019, background): “[21] also proposed a feature selection approach to deal with the imbalanced data problem in multiple categories text classification, this approach is achieved by explicitly combining the features most indicative of membership (e.”
A Survey of Predictive Modeling on Imbalanced Domains (2016, methodology): “Feature selection is recommended [Wasikowski and Chen 2010] and is also pointed as the solution for addressing the class imbalance problem [Mladenic and Grobelnik 1999; Zheng et al. 2004; Chen and Wasikowski 2008; Van Der Putten and Van Someren 2004; Forman 2003].”
Applications of deep learning in stock market prediction: recent progress (2020, methodology): “Chi-square method (Zheng et al., 2004) and maximum relevance and minimum redundancy (MRMR) (Peng et al.”
Feature selection for text classification: A review (2018, background): “Zheng et al. [114] proposed iSIG, an improved IG measure, by taking into account of both positive and negative features for imbalanced text data.”
Handling imbalanced datasets: A review (2006, background): “Zheng et al [35] suggest that existing measures used for feature selection are not very appropriate for imbalanced data sets.”
Combating the Small Sample Class Imbalance Problem Using Feature Selection (2010, methodology): “Thus, unless one has only training samples known to be from one class and no other information, one-class learners are likely not the best approach.”
Application and Comparison of Decision Tree-Based Machine Learning Methods in Landside Susceptibility Assessment at Pauri Garhwal Area, Uttarakhand, India (2017, methodology): “In the present study, the chi-square feature selection method, which is one of the most effective feature selection methods (Jin et al. 2006; Zheng et al. 2004), was applied to evaluate the importance of affecting factors.”
Feature selection for high-dimensional class-imbalanced data sets using Support Vector Machines (2014, methodology): “It is prevalent in many applications, including fraud/churn detection [19], text categorization [43], medical diagnosis [35], detection of software defects [24], and many others.”
On the Class Imbalance Problem (2008, background): “Motivated Zheng and Srihari’s work [23], Castillo and Serrano [24] do not particularly focus on feature selection, but make it a part of their complete framework.”