Adversarial Training for a Hybrid Approach to Aspect-Based Sentiment Analysis

TL;DR

This paper introduces an adversarial training approach to enhance the robustness and accuracy of a state-of-the-art aspect-based sentiment analysis algorithm, showing significant improvements on benchmark datasets.

Contribution

It applies adversarial training to aspect-based sentiment analysis, a novel approach that improves model robustness and out-of-sample accuracy.

Findings

Accuracy improved from 81.7% to 82.5% on SemEval 2015

Accuracy improved from 84.4% to 87.3% on SemEval 2016

Adversarial training enhances model robustness in sentiment analysis

Abstract

The increasing popularity of the Web has subsequently increased the abundance of reviews on products and services. Mining these reviews for expressed sentiment is beneficial for both companies and consumers, as quality can be improved based on this information. In this paper, we consider the state-of-the-art HAABSA++ algorithm for aspect-based sentiment analysis tasked with identifying the sentiment expressed towards a given aspect in review sentences. Specifically, we train the neural network part of this algorithm using an adversarial network, a novel machine learning training method where a generator network tries to fool the classifier network by generating highly realistic new samples, as such increasing robustness. This method, as of yet never in its classical form applied to aspect-based sentiment analysis, is found to be able to considerably improve the out-of-sample accuracy of HAABSA++: for the SemEval 2015 dataset, accuracy was increased from 81.7% to 82.5%, and for the SemEval 2016 task, accuracy increased from 84.4% to 87.3%.