Aspect-gated graph convolutional networks for aspect-based sentiment analysis

Aspect-based sentiment analysis aims to predict the sentiment polarity of each specific aspect term in a given sentence. However, the previous models ignore syntactical constraints and long-range sentiment dependencies and mistakenly identify irrelevant contextual words as clues for judging aspect sentiment. In addition, these models usually use aspect-independent encoders to encode sentences, which can lead to a lack of aspect information. In this paper, we propose an aspect-gated graph convolutional network (AGGCN), that includes a special aspect gate designed to guide the encoding of aspect-specific information from the outset and construct a graph convolution network on the sentence dependency tree to make full use of the syntactical information and sentiment dependencies. The experimental results on multiple SemEval datasets demonstrate the effectiveness of the proposed approach, and our model outperforms the strong baseline models.

[1]  Andrew Y. Ng,et al.  Parsing Natural Scenes and Natural Language with Recursive Neural Networks , 2011, ICML.

[2]  Ravindra Kumar,et al.  Aspect-based sentiment analysis using deep networks and stochastic optimization , 2019, Neural Computing and Applications.

[3]  Haris Papageorgiou,et al.  SemEval-2016 Task 5: Aspect Based Sentiment Analysis , 2016, *SEMEVAL.

[4]  Yoshua Bengio,et al.  A Neural Probabilistic Language Model , 2003, J. Mach. Learn. Res..

[5]  Yue Zhang,et al.  Neural Networks for Open Domain Targeted Sentiment , 2015, EMNLP.

[6]  Hui-Jia Li,et al.  Multi-scale asynchronous belief percolation model on multiplex networks , 2019, New Journal of Physics.

[7]  Jie Zhou,et al.  A Novel Aspect-Guided Deep Transition Model for Aspect Based Sentiment Analysis , 2019, EMNLP.

[8]  Jingquan Li.  Ensuring Privacy in a Personal Health Record System , 2015, Computer.

[9]  Zhigang Zeng,et al.  Memristive LSTM Network for Sentiment Analysis , 2019, IEEE Transactions on Systems, Man, and Cybernetics: Systems.

[10]  Yuexian Hou,et al.  A Position-aware Bidirectional Attention Network for Aspect-level Sentiment Analysis , 2018, COLING.

[11]  Jian Pei,et al.  Optimal Estimation of Low-Rank Factors via Feature Level Data Fusion of Multiplex Signal Systems , 2020, IEEE Transactions on Knowledge and Data Engineering.

[12]  Lidong Bing,et al.  Recurrent Attention Network on Memory for Aspect Sentiment Analysis , 2017, EMNLP.

[13]  Irwin King,et al.  Aspect-level Sentiment Classification with HEAT (HiErarchical ATtention) Network , 2017, CIKM.

[14]  Tao Li,et al.  Aspect Based Sentiment Analysis with Gated Convolutional Networks , 2018, ACL.

[15]  Jordan L. Boyd-Graber,et al.  Grammatical structures for word-level sentiment detection , 2012, NAACL.

[16]  Jie Li,et al.  Aspect Sentiment Classification with both Word-level and Clause-level Attention Networks , 2018, IJCAI.

[17]  Wenchao Xu,et al.  Aspect based fine-grained sentiment analysis for online reviews , 2019, Inf. Sci..

[18]  Xiaocheng Feng,et al.  Effective LSTMs for Target-Dependent Sentiment Classification , 2015, COLING.

[19]  Navneet Kaur,et al.  Opinion mining and sentiment analysis , 2016, 2016 3rd International Conference on Computing for Sustainable Global Development (INDIACom).

[20]  Chen Zhang,et al.  Aspect-based Sentiment Classification with Aspect-specific Graph Convolutional Networks , 2019, EMNLP/IJCNLP.

[21]  Suresh Manandhar,et al.  SemEval-2015 Task 12: Aspect Based Sentiment Analysis , 2015, *SEMEVAL.

[22]  Ting Liu,et al.  Aspect Level Sentiment Classification with Deep Memory Network , 2016, EMNLP.

[23]  Arun Kumar Sangaiah,et al.  Aspect based sentiment analysis by a linguistically regularized CNN with gated mechanism , 2019, J. Intell. Fuzzy Syst..

[24]  Chong Wang,et al.  TopicRNN: A Recurrent Neural Network with Long-Range Semantic Dependency , 2016, ICLR.

[25]  Kam-Fai Wong,et al.  Convolution-based Memory Network for Aspect-based Sentiment Analysis , 2018, SIGIR.

[26]  S. Lee,et al.  A domain transferable lexicon set for Twitter sentiment analysis using a supervised machine learning approach , 2018, Expert Syst. Appl..

[27]  Shuai Wang,et al.  Deep learning for sentiment analysis: A survey , 2018, WIREs Data Mining Knowl. Discov..

[28]  Xiaojun Wan,et al.  Attention-based LSTM Network for Cross-Lingual Sentiment Classification , 2016, EMNLP.

[29]  Erik Cambria,et al.  Targeted Aspect-Based Sentiment Analysis via Embedding Commonsense Knowledge into an Attentive LSTM , 2018, AAAI.

[30]  Hamido Fujita,et al.  Mining weighted subgraphs in a single large graph , 2020, Inf. Sci..

[31]  Flavius Frasincar,et al.  A Hybrid Approach for Aspect-Based Sentiment Analysis Using a Lexicalized Domain Ontology and Attentional Neural Models , 2019, ESWC.

[32]  Christopher D. Manning,et al.  Graph Convolution over Pruned Dependency Trees Improves Relation Extraction , 2018, EMNLP.

[33]  Dianyuan Zhang,et al.  Interactive Rule Attention Network for Aspect-Level Sentiment Analysis , 2020, IEEE Access.

[34]  Kathleen M. Carley,et al.  Aspect Level Sentiment Classification with Attention-over-Attention Neural Networks , 2018, SBP-BRiMS.

[35]  Linlin Hou,et al.  Modeling Sentiment Dependencies with Graph Convolutional Networks for Aspect-level Sentiment Classification , 2020, Knowl. Based Syst..

[36]  Jie Cao,et al.  Dynamical Clustering in Electronic Commerce Systems via Optimization and Leadership Expansion , 2020, IEEE Transactions on Industrial Informatics.

[37]  Tingting Wang,et al.  Deep Learning for Aspect-Level Sentiment Classification: Survey, Vision, and Challenges , 2019, IEEE Access.

[38]  Kiyoaki Shirai,et al.  PhraseRNN: Phrase Recursive Neural Network for Aspect-based Sentiment Analysis , 2015, EMNLP.

[39]  Jie Zhou,et al.  Is position important? deep multi-task learning for aspect-based sentiment analysis , 2020, Applied Intelligence.

[40]  Li Zhao,et al.  Attention-based LSTM for Aspect-level Sentiment Classification , 2016, EMNLP.

[41]  Houfeng Wang,et al.  Interactive Attention Networks for Aspect-Level Sentiment Classification , 2017, IJCAI.

[42]  Xin Li,et al.  Transformation Networks for Target-Oriented Sentiment Classification , 2018, ACL.

[43]  Yue Zhang,et al.  Attention Modeling for Targeted Sentiment , 2017, EACL.

[44]  M. Perc,et al.  Optimization of identifiability for efficient community detection , 2020, New Journal of Physics.

[45]  Max Welling,et al.  Semi-Supervised Classification with Graph Convolutional Networks , 2016, ICLR.

[46]  Mahmoud Al-Ayyoub,et al.  Deep Recurrent neural network vs. support vector machine for aspect-based sentiment analysis of Arabic hotels' reviews , 2017, J. Comput. Sci..

[47]  Ming Zhou,et al.  Adaptive Recursive Neural Network for Target-dependent Twitter Sentiment Classification , 2014, ACL.

[48]  Tao Chen,et al.  Expert Systems With Applications , 2022 .