Feature-enhanced attention network for target-dependent sentiment classification

Abstract In this paper, we propose a Feature-enhanced Attention Network to improve the performance of target-dependent Sentiment classification (FANS). Specifically, we first learn the feature-enhanced word representations by leveraging the unigram features, part of speech features and word position features. Second, we develop an multi-view co-attention network to learn a better multi-view sentiment-aware and target-specific sentence representation via interactively modeling the context words, target words and sentiment words. We conduct experiments to verify the effectiveness of our model on two real-world datasets in both English and Chinese. The experimental results demonstrate that FANS has robust superiority over competitors and sets state-of-the-art.

[1]  Hua Yuan,et al.  Exploring performance of clustering methods on document sentiment analysis , 2015, J. Inf. Sci..

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

[3]  Arun Kumar Sangaiah,et al.  Feature-based Compositing Memory Networks for Aspect-based Sentiment Classification in Social Internet of Things , 2017, Future Gener. Comput. Syst..

[4]  Dan Klein,et al.  Feature-Rich Part-of-Speech Tagging with a Cyclic Dependency Network , 2003, NAACL.

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

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

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

[8]  Suresh Manandhar,et al.  SemEval-2014 Task 4: Aspect Based Sentiment Analysis , 2014, *SEMEVAL.

[9]  Bing Liu,et al.  Mining and summarizing customer reviews , 2004, KDD.

[10]  Lillian Lee,et al.  Opinion Mining and Sentiment Analysis , 2008, Found. Trends Inf. Retr..

[11]  Yoram Singer,et al.  Adaptive Subgradient Methods for Online Learning and Stochastic Optimization , 2011, J. Mach. Learn. Res..

[12]  Bo Pang,et al.  A Sentimental Education: Sentiment Analysis Using Subjectivity Summarization Based on Minimum Cuts , 2004, ACL.

[13]  Yong Qi,et al.  Information Processing and Management , 1984 .

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

[15]  Bing Liu,et al.  Sentiment Analysis and Opinion Mining , 2012, Synthesis Lectures on Human Language Technologies.

[16]  Bo Pang,et al.  Thumbs up? Sentiment Classification using Machine Learning Techniques , 2002, EMNLP.

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

[18]  Long Chen,et al.  Weakly-Supervised Deep Embedding for Product Review Sentiment Analysis , 2018, IEEE Transactions on Knowledge and Data Engineering.

[19]  Saif Mohammad,et al.  NRC-Canada-2014: Detecting Aspects and Sentiment in Customer Reviews , 2014, *SEMEVAL.

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

[21]  Sameena Shah,et al.  Learning Stock Market Sentiment Lexicon and Sentiment-Oriented Word Vector from StockTwits , 2017, CoNLL.

[22]  Muhammad Abdul-Mageed,et al.  Subjectivity and Sentiment Analysis of Modern Standard Arabic , 2011, ACL.

[23]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

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

[25]  Zhi Liu,et al.  Sentiment recognition of online course reviews using multi-swarm optimization-based selected features , 2016, Neurocomputing.

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

[27]  Anh-Cuong Le,et al.  Learning multiple layers of knowledge representation for aspect based sentiment analysis , 2017, Data Knowl. Eng..

[28]  Zongkai Yang,et al.  Adaptive multi-view selection for semi-supervised emotion recognition of posts in online student community , 2014, Neurocomputing.

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

[30]  Laizhong Cui,et al.  Combine HowNet lexicon to train phrase recursive autoencoder for sentence-level sentiment analysis , 2017, Neurocomputing.

[31]  Guang Chen,et al.  Dependency-Attention-Based LSTM for Target-Dependent Sentiment Analysis , 2017, SMP.

[32]  Hamido Fujita,et al.  A hybrid approach to the sentiment analysis problem at the sentence level , 2016, Knowl. Based Syst..

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