Feature selection based on supervised topic modeling for boosting-based multi-label text categorization

Abstract

The text representation model Bag-Of-Words is a simple and typical model which uses the single words as elements to represent the texts in the feature space. However, using the single words as features will produce a high dimensional feature space, which result in the learning computational cost, particularly for ensemble learning algorithms, such as the boosting algorithm AdaBoost.MH. The straightforward solution of this matter can be managed by using a feature selection method capable of reducing the features space effectively. This work describes how to utilize the supervised topic model Labeled Latent Dirichlet Allocation for feature selection, as well accelerating AdaBoost.MH learning for multi-label text categorization. The experimental results on three benchmarks demonstrated that using Labeled Latent Dirichlet Allocation for feature selection improves and accelerates AdaBoost.MH and exceeds the performance of three existing methods.