Aspect-Level Sentiment Analysis Based on Position Features Using Multilevel Interactive Bidirectional GRU and Attention Mechanism

The aim of aspect-level sentiment analysis is to identify the sentiment polarity of a given target term in sentences. Existing neural network models provide a useful account of how to judge the polarity. However, context relative position information for the target terms is adversely ignored under the limitation of training datasets. Considering position features between words into the models can improve the accuracy of sentiment classification. Hence, this study proposes an improved classification model by combining multilevel interactive bidirectional Gated Recurrent Unit (GRU), attention mechanisms, and position features (MI-biGRU). Firstly, the position features of words in a sentence are initialized to enrich word embedding. Secondly, the approach extracts the features of target terms and context by using a well-constructed multilevel interactive bidirectional neural network. Thirdly, an attention mechanism is introduced so that the model can pay greater attention to those words that are important for sentiment analysis. Finally, four classic sentiment classification datasets are used to deal with aspect-level tasks. Experimental results indicate that there is a correlation between the multilevel interactive attention network and the position features. MI-biGRU can obviously improve the performance of classification.

[1]  Masaru Kitsuregawa,et al.  Building Lexicon for Sentiment Analysis from Massive Collection of HTML Documents , 2007, EMNLP.

[2]  Kang Liu,et al.  Book Review: Sentiment Analysis: Mining Opinions, Sentiments, and Emotions by Bing Liu , 2015, CL.

[3]  Siu Cheung Hui,et al.  Learning to Attend via Word-Aspect Associative Fusion for Aspect-based Sentiment Analysis , 2017, AAAI.

[4]  John G. Breslin,et al.  A Hierarchical Model of Reviews for Aspect-based Sentiment Analysis , 2016, EMNLP.

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

[6]  Yoshua Bengio,et al.  Neural Machine Translation by Jointly Learning to Align and Translate , 2014, ICLR.

[7]  Yue Zhang,et al.  Gated Neural Networks for Targeted Sentiment Analysis , 2016, AAAI.

[8]  Kuldip K. Paliwal,et al.  Bidirectional recurrent neural networks , 1997, IEEE Trans. Signal Process..

[9]  Jeffrey Pennington,et al.  Semi-Supervised Recursive Autoencoders for Predicting Sentiment Distributions , 2011, EMNLP.

[10]  Saif Mohammad,et al.  NRC-Canada: Building the State-of-the-Art in Sentiment Analysis of Tweets , 2013, *SEMEVAL.

[11]  Kim Schouten,et al.  Survey on Aspect-Level Sentiment Analysis , 2016, IEEE Transactions on Knowledge and Data Engineering.

[12]  Alex Graves,et al.  Recurrent Models of Visual Attention , 2014, NIPS.

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

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

[15]  Fangzhao Wu,et al.  Aspect-based sentiment analysis via fusing multiple sources of textual knowledge , 2019, Knowl. Based Syst..

[16]  Christopher Potts,et al.  Recursive Deep Models for Semantic Compositionality Over a Sentiment Treebank , 2013, EMNLP.

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

[18]  Pushpak Bhattacharyya,et al.  Feature selection and ensemble construction: A two-step method for aspect based sentiment analysis , 2017, Knowl. Based Syst..

[19]  Christopher D. Manning,et al.  Improved Semantic Representations From Tree-Structured Long Short-Term Memory Networks , 2015, ACL.

[20]  Yoshua Bengio,et al.  Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation , 2014, EMNLP.

[21]  Abeer Alsadoon,et al.  Deep Learning for Aspect-Based Sentiment Analysis: A Comparative Review , 2019, Expert Syst. Appl..

[22]  Jun Zhao,et al.  Recurrent Convolutional Neural Networks for Text Classification , 2015, AAAI.

[23]  Verónica Pérez-Rosas,et al.  Learning Sentiment Lexicons in Spanish , 2012, LREC.

[24]  Themis Palpanas,et al.  Survey on mining subjective data on the web , 2011, Data Mining and Knowledge Discovery.

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

[26]  Jeffrey Pennington,et al.  GloVe: Global Vectors for Word Representation , 2014, EMNLP.

[27]  Joachim Wagner,et al.  DCU: Aspect-based Polarity Classification for SemEval Task 4 , 2014, *SEMEVAL.

[28]  Tiejun Zhao,et al.  Target-dependent Twitter Sentiment Classification , 2011, ACL.

[29]  Jun Zhao,et al.  Relation Classification via Convolutional Deep Neural Network , 2014, COLING.

[30]  Xiao Ma,et al.  Enhancing Attention-Based LSTM With Position Context for Aspect-Level Sentiment Classification , 2019, IEEE Access.

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

[32]  Phil Blunsom,et al.  Teaching Machines to Read and Comprehend , 2015, NIPS.

[33]  Yue Zhang,et al.  Target-Dependent Twitter Sentiment Classification with Rich Automatic Features , 2015, IJCAI.

[34]  Xiangji Huang,et al.  Using Term Location Information to Enhance Probabilistic Information Retrieval , 2015, SIGIR.

[35]  Ting Liu,et al.  Attention-over-Attention Neural Networks for Reading Comprehension , 2016, ACL.

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