CE-HEAT: An Aspect-Level Sentiment Classification Approach With Collaborative Extraction Hierarchical Attention Network

Aspect-level sentiment classification is a fine-grained sentiment analysis task. It aims to predict the sentiment of a review in different aspects. Recently many works exploit the hierarchical attention network to capture the aspect-specific sentiment information. However, the prior work only attends to use the aspect terms to capture the aspect-specific sentiment information in the text. It may cause the mismatch of sentiment for the aspect-specific when the aspect words are extracted incorrectly. Since the number of aspect words is much more than that sentiment words, some uncommon aspect terms are more difficult to be extracted than uncommon sentiment terms. To solve this problem, we propose a collaborative extraction hierarchical attention network. It consists of two hierarchical attention units, i.e.. One unit extracts the sentiment features by the sentiment attention layer and uses the sentiment features to capture the specific aspect-related sentiment aspect information by the aspect attention layer. The other extracts the aspect features by the aspect attention layer and uses the aspect features to help capture the aspect-specific sentiment information by the sentiment attention layer. Moreover, we use the SemEval competition data set to verify our approach. The experiment shows that our approach achieves better performance than the methods which only use aspect features to extract sentiment feature for aspect-level sentiment classification.

[1]  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..

[2]  Shuting Zhi,et al.  Multi-Attention Network for Aspect Sentiment Analysis , 2019, ICSCA.

[3]  Xiaodong Gu,et al.  Aspect-based Opinion Summarization with Convolutional Neural Networks , 2016, 2016 International Joint Conference on Neural Networks (IJCNN).

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

[5]  Erik Cambria,et al.  Sentic LSTM: a Hybrid Network for Targeted Aspect-Based Sentiment Analysis , 2018, Cognitive Computation.

[6]  Ting Liu,et al.  Document Modeling with Gated Recurrent Neural Network for Sentiment Classification , 2015, EMNLP.

[7]  Mayura Kinikar,et al.  Machine Learning Algorithms for Opinion Mining and Sentiment Classification , 2013 .

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

[9]  Jianfei Yu,et al.  Learning Sentence Embeddings with Auxiliary Tasks for Cross-Domain Sentiment Classification , 2016, EMNLP.

[10]  Hua Xu,et al.  Chinese comments sentiment classification based on word2vec and SVMperf , 2015, Expert Syst. Appl..

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

[12]  Xin Zhang,et al.  Exploring sentiment parsing of microblogging texts for opinion polling on chinese public figures , 2016, Applied Intelligence.

[13]  Lukasz Kaiser,et al.  Attention is All you Need , 2017, NIPS.

[14]  Danushka Bollegala,et al.  Cross-Domain Sentiment Classification Using Sentiment Sensitive Embeddings , 2016, IEEE Transactions on Knowledge and Data Engineering.

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

[16]  Delip Rao,et al.  Semi-Supervised Polarity Lexicon Induction , 2009, EACL.