Learning to weight for text classification

In information retrieval (IR) and related tasks, term weighting approaches typically consider the frequency of the term in the document and in the collection in order to compute a score reflecting the importance of the term for the document. In tasks characterized by the presence of training data (such as text classification) it seems logical to design a term weighting function that leverages the distribution (as estimated from training data) of the term across the classes of interest. Although "supervised term weighting" approaches that use this intuition have been described before, they have failed to show consistent improvements. In this article we analyse the possible reasons for this failure, and call consolidated assumptions into question. Following this criticism, we propose a novel supervised term weighting approach that, instead of relying on any predefined formula, learns a term weighting function optimised on the training set of interest; we dub this approach Learning to Weight (LTW). The experiments that we have run on several well-known benchmarks, and using different learning methods, show that our method outperforms previous term weighting approaches in text classification.