Exploiting Document Knowledge for Aspect-level Sentiment Classification

About

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.

Ruidan He, Wee Sun Lee, Hwee Tou Ng, Daniel Dahlmeier · 2018

Related benchmarks

Task	Dataset	Result
Aspect-level sentiment classification	SemEval Laptop 2014 (test)	Accuracy71.91	59
Aspect-based Sentiment Classification	Lap14	Accuracy71.15	37
Aspect-based Sentiment Analysis	SemEval Task 4 Subtask 2 Restaurant domain 2014 (test)	Accuracy78.73	30
Aspect extraction and sentiment classification	res 14	F1 Score—	26
Sentiment Classification	SemEval Twitter Sentiment Analysis 2015 (test)	Average F1—	17
Sentiment Classification	SemEval Twitter Sentiment Analysis 2016 (test)	Avg F1 Score—	17
Aspect-based Sentiment Classification	Res15	Accuracy81.3	10
Aspect-level sentiment classification	D1	Accuracy79.11	9
Aspect-level sentiment classification	D3	Accuracy81.3	9
Aspect-level sentiment classification	D4	Accuracy85.58	9