Classifying textual data: shallow, deep and ensemble methods

TL;DR

This paper compares shallow, deep, and ensemble methods for text classification on high-dimensional, sparse data, showing deep learning's superiority and the ensemble's potential to enhance accuracy and robustness.

Contribution

It provides a comprehensive evaluation of modern text classification techniques, highlighting the benefits of combining shallow and deep learning methods in ensembles.

Findings

Deep learning outperforms classical methods

Ensemble classifiers improve accuracy and robustness

Combination of methods is effective for sparse, high-dimensional data

Abstract

This paper focuses on a comparative evaluation of the most common and modern methods for text classification, including the recent deep learning strategies and ensemble methods. The study is motivated by a challenging real data problem, characterized by high-dimensional and extremely sparse data, deriving from incoming calls to the customer care of an Italian phone company. We will show that deep learning outperforms many classical (shallow) strategies but the combination of shallow and deep learning methods in a unique ensemble classifier may improve the robustness and the accuracy of "single" classification methods.