High-performing feature selection for text classification
By Monica Rogati, Yiming Yang. International Conference on Information and Knowledge Management, 2002
385 citations recorded by the source corpus.
Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition
View Paper: https://www.semanticscholar.org/paper/e792a3353996dd43f2e0744baadf6b7157ace6ac
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
- Arjun Mukherjee
- Ioannis P. Vlahavas
- Grigorios Tsoumakas
- B. Liu
- David D. Lewis
- Fan Li
- Tony G. Rose
- Baharum bin Baharudin
In Computer Vision and Pattern Recognition
- Grigorios Tsoumakas
- Ioannis P. Vlahavas
- David D. Lewis
- Fan Li
- Tony G. Rose
- Baharum bin Baharudin
- Lam Hong Lee
- Khairullah Khan
Citations in the corpus
- SourceFinder: Finding Malware Source-Code from Publicly Available Repositories (2020, methodology): “To improve the effectiveness of our approach using BoW, we conduct a feature selection process, χ2 statistic following best practices [53].”
- Random k -Labelsets: An Ensemble Method for Multilabel Classification (2007, result): “A similar approach was found to have high performance in previous experimental work on textual datasets [20].”
- A Review of Machine Learning Algorithms for Text-Documents Classification (2010, methodology): “A performance compression in [115] presented a controlled study on a large number of filter feature selection methods for text classification.”
- RCV1: A New Benchmark Collection for Text Categorization Research (2004, methodology): “The feature set for a combination was chosen by first ranking the 47,152 features by their 2 max score (Yang and Pedersen, 1997; Rogati and Yang, 2002) with respect to the category set.”
- Improving Gender Classification of Blog Authors (2010, result): “This trend is consistent with the prior findings in (Mladenic, 1998; Rogati and Yang, 2002; Forman 2003; Riloff et al., 2006; Houvardas and Stamatatos, 2006).”
- Feature selection for text classification: A review (2018, background): “DFS shows competitive performance with respect to some well-known metrics such as CHI and IG. χ 2 (CHI): CHI can measure the degree of independence between a term and a category and has been widely used for text categorization [76, 108].”