Recurrent Attention Network on Memory for Aspect Sentiment Analysis

TLDR

The study proposes a neural‑network framework to determine sentiment toward opinion targets in comments and reviews. The framework employs a multiple‑attention mechanism combined nonlinearly with a recurrent neural network and a weighted‑memory module to capture distant sentiment features and tailor memory per target, and is evaluated on four datasets including SemEval2014 restaurant and laptop reviews, Twitter, and Chinese news comments. Experimental results show that the model consistently outperforms state‑of‑the‑art methods across all evaluated datasets.

Abstract

We propose a novel framework based on neural networks to identify the sentiment of opinion targets in a comment/review. Our framework adopts multiple-attention mechanism to capture sentiment features separated by a long distance, so that it is more robust against irrelevant information. The results of multiple attentions are non-linearly combined with a recurrent neural network, which strengthens the expressive power of our model for handling more complications. The weighted-memory mechanism not only helps us avoid the labor-intensive feature engineering work, but also provides a tailor-made memory for different opinion targets of a sentence. We examine the merit of our model on four datasets: two are from SemEval2014, i.e. reviews of restaurants and laptops; a twitter dataset, for testing its performance on social media data; and a Chinese news comment dataset, for testing its language sensitivity. The experimental results show that our model consistently outperforms the state-of-the-art methods on different types of data.