Aspect Level Sentiment Classification with Attention-over-Attention Neural Networks

By Binxuan Huang, Yanglan Ou, Kathleen M. Carley. International Conference on Social, Cultural, and Behavioral Modeling, 2018

359 citations recorded by the source corpus.

Aspect-level sentiment classification aims to identify the sentiment expressed towards some aspects given context sentences. In this paper, we introduce an attention-over-attention (AOA) neural network for aspect level sentiment classification. Our approach models aspects and sentences in a joint way and explicitly captures the interaction between aspects and context sentences. With the AOA module, our model jointly learns the representations for aspects and sentences, and automatically focuses on the important parts in sentences. Our experiments on laptop and restaurant datasets demonstrate our approach outperforms previous LSTM-based architectures.

Subfields: Artificial Intelligence

View Paper: https://www.semanticscholar.org/paper/f201abc6045f79c85ea555bb2ab4abbbe469aa41

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

Citations in the corpus

Aspect-based sentiment analysis via affective knowledge enhanced graph convolutional networks (2021, neutral): “• AOA [57] learns the interaction between aspect words and contextual words, and focuses on the important parts in sentences via an attention-over-attention model.”
A Challenge Dataset and Effective Models for Aspect-Based Sentiment Analysis (2019, methodology): “, 2017) and AOA LSTM (Huang et al., 2018); (2) CNN based model: GCAE (Xue and Li, 2018); (3) Attention based models: MemNet (Tang et al.”
Dependency Graph Enhanced Dual-transformer Structure for Aspect-based Sentiment Classification (2020, methodology): “, 2016b), AOA (Huang et al., 2018), IAN (Ma et al.”
Dual Graph Convolutional Networks for Aspect-based Sentiment Analysis (2021, background): “To judge the sentiment of a particular aspect, previous studies (Wang et al., 2016; Tang et al., 2016a; Ma et al., 2017; Chen et al., 2017; Fan et al., 2018; Huang et al., 2018; Gu et al., 2018) have proposed various recurrent neural networks (RNNs) with attention mechanisms to generate aspect-speci”
Target-Dependent Sentiment Classification With BERT (2019, methodology): “With this design, AOA can learn the important parts in the aspects and context sentences, which generates the final representation of the sentence.”
Syntax-Aware Aspect Level Sentiment Classification with Graph Attention Networks (2019, methodology): “Features generated from the aspect are used to control the information ﬂow in the CNN applied to the sentence (Huang et al., 2018).”
Aspect-based Sentiment Classification with Aspect-specific Graph Convolutional Networks (2019, background): “…attention mechanism coupled with Recurrent Neural Networks (RNNs) (Bahdanau et al., 2014; Luong et al., 2015; Xu et al., 2015) starts to play a critical role in more recent models (Wang et al., 2016; Tang et al., 2016b; Yang et al., 2017; Liu and Zhang, 2017; Ma et al., 2017; Huang et al., 2018).”