Exploiting Document Knowledge for Aspect-level Sentiment Classification

TL;DR

This paper proposes methods to transfer knowledge from document-level sentiment data to improve aspect-level sentiment classification, addressing data scarcity issues and enhancing model performance.

Contribution

It introduces two novel approaches for leveraging document-level data to boost aspect-level sentiment analysis, validated on multiple public datasets.

Findings

Knowledge transfer improves aspect-level sentiment classification accuracy.

Attention-based LSTM benefits significantly from document-level knowledge.

Proposed methods outperform baseline models on four benchmark datasets.

Abstract

Attention-based long short-term memory (LSTM) networks have proven to be useful in aspect-level sentiment classification. However, due to the difficulties in annotating aspect-level data, existing public datasets for this task are all relatively small, which largely limits the effectiveness of those neural models. In this paper, we explore two approaches that transfer knowledge from document- level data, which is much less expensive to obtain, to improve the performance of aspect-level sentiment classification. We demonstrate the effectiveness of our approaches on 4 public datasets from SemEval 2014, 2015, and 2016, and we show that attention-based LSTM benefits from document-level knowledge in multiple ways.