Human-Like Decision Making: Document-level Aspect Sentiment Classification via Hierarchical Reinforcement Learning

TL;DR

This paper introduces a hierarchical reinforcement learning method for document-level aspect sentiment classification that mimics human analysis steps, improving interpretability and effectiveness over existing neural network approaches.

Contribution

The paper proposes a novel HRL framework with clause and word selection strategies, enhancing transparency and noise handling in DASC tasks.

Findings

Outperforms state-of-the-art baselines in DASC accuracy

Demonstrates improved interpretability of sentiment analysis process

Effectively filters noise at clause and word levels

Abstract

Recently, neural networks have shown promising results on Document-level Aspect Sentiment Classification (DASC). However, these approaches often offer little transparency w.r.t. their inner working mechanisms and lack interpretability. In this paper, to simulating the steps of analyzing aspect sentiment in a document by human beings, we propose a new Hierarchical Reinforcement Learning (HRL) approach to DASC. This approach incorporates clause selection and word selection strategies to tackle the data noise problem in the task of DASC. First, a high-level policy is proposed to select aspect-relevant clauses and discard noisy clauses. Then, a low-level policy is proposed to select sentiment-relevant words and discard noisy words inside the selected clauses. Finally, a sentiment rating predictor is designed to provide reward signals to guide both clause and word selection. Experimental results demonstrate the impressive effectiveness of the proposed approach to DASC over the state-of-the-art baselines.