Improving Text Classification Performance with Random Forests-Based Feature Selection

Feature selection (FS) is employed to make text classification (TC) more effective. Well-known FS metrics like information gain (IG) and odds ratio (OR) rank terms without considering term interactions. Building classifiers with FS algorithms considering term interactions can yield better performance. But their computational complexity is a concern. This has resulted in two-stage algorithms such as information gain-principal component analysis (IG–PCA). Random forests-based feature selection (RFFS), proposed by Breiman, has demonstrated outstanding performance while capturing gene–gene relations in bioinformatics, but its usefulness for TC is less explored. RFFS has fewer control parameters and is found to be resistant to overfitting and thus generalizes well to new data. It does not require use of a test dataset to report accuracy and does not use conventional cross-validation. This paper investigates the working of RFFS for TC and compares its performance against IG, OR and IG–PCA. We carry out experiments on four widely used text data sets using naive Bayes’ and support vector machines as classifiers. RFFS achieves macro-F1 values higher than other FS algorithms in 73 % of the experimental instances. We also analyze the performance of RFFS for TC in terms of its parameters and class skews of the data sets and yield interesting results.