ML-MDLText: An efficient and lightweight multilabel text classifier with incremental learning

Marciele M. Bittencourt, Renato Moraes Silva, Tiago A. Almeida

Abstract: Highlights•A multilabel text classification method based on the minimum description length principle is proposed.•The method does not require problem transformation tricks and supports incremental learning.•The method can naturally manipulate multilabel data and exploit the dependence between labels.•Experiments were performed using fifteen datasets on three online learning scenarios.•The performance achieved is very competitive with state-of-the-art algorithms.