Deep Refinement: capsule network with attention mechanism-based system for text classification

Abstract

Most of the text in the questions of community question–answering systems does not consist of a definite mechanism for the restriction of inappropriate and insincere content. A given piece of text can be insincere if it asserts false claims or assumes something which is debatable or has a non-neutral or exaggerated tone about an individual or a group. In this paper, we propose a pipeline called Deep Refinement which utilizes some of the state-of-the-art methods for information retrieval from highly sparse data such as capsule network and attention mechanism. We have applied the Deep Refinement pipeline to classify the text primarily into two categories, namely sincere and insincere. Our novel approach ‘Deep Refinement’ provides a system for the classification of such questions in order to ensure enhanced monitoring and information quality. The database used to understand the real concept of what actually makes up sincere and insincere includes quora insincere question dataset. Our proposed question classification method outperformed previously used text classification methods, as evident from the F1 score of 0.978.