Aspect Aware Learning for Aspect Category Sentiment Analysis

Aspect category sentiment analysis (ACSA) is an underexploited subtask in aspect level sentiment analysis. It aims to identify the sentiment of predefined aspect categories. The main challenge in ACSA comes from the fact that the aspect category may not occur in the sentence in most of the cases. For example, the review “they have delicious sandwiches” positively talks about the aspect category “food” in an implicit manner. In this article, we propose a novel aspect aware learning (AAL) framework for ACSA tasks. Our key idea is to exploit the interaction between the aspect category and the contents under the guidance of both sentiment polarity and predefined categories. To this end, we design a two-way memory network for integrating AAL into the framework of sentiment classification. We further present two algorithms to incorporate the potential impacts of aspect categories. One is to capture the correlations between aspect terms and the aspect category like “sandwiches” and “food.” The other is to recognize the aspect category for sentiment representations like “food” for “delicious.” We conduct extensive experiments on four SemEval datasets. The results reveal the essential role of AAL in ACSA by achieving the state-of-the-art performance.

[1]  Jun Yang,et al.  Multi-Entity Aspect-Based Sentiment Analysis With Context, Entity and Aspect Memory , 2018, AAAI.

[2]  Soo-Min Kim,et al.  Crystal: Analyzing Predictive Opinions on the Web , 2007, EMNLP.

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

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

[5]  Xiaokui Xiao,et al.  Recursive Neural Conditional Random Fields for Aspect-based Sentiment Analysis , 2016, EMNLP.

[6]  Maite Taboada,et al.  Lexicon-Based Methods for Sentiment Analysis , 2011, CL.

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

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

[9]  Xuanjing Huang,et al.  Cross-Domain Sentiment Classification with Target Domain Specific Information , 2018, ACL.

[10]  Xin Li,et al.  Deep Multi-Task Learning for Aspect Term Extraction with Memory Interaction , 2017, EMNLP.

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

[12]  Omer Levy,et al.  Improving Distributional Similarity with Lessons Learned from Word Embeddings , 2015, TACL.

[13]  Jeffrey Dean,et al.  Efficient Estimation of Word Representations in Vector Space , 2013, ICLR.

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

[15]  Cheng Li,et al.  Deep Memory Networks for Attitude Identification , 2017, WSDM.

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

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

[18]  Kenneth Ward Church,et al.  Word Association Norms, Mutual Information, and Lexicography , 1989, ACL.

[19]  Shuai Wang,et al.  Target-Sensitive Memory Networks for Aspect Sentiment Classification , 2018, ACL.

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

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

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

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

[24]  Hwee Tou Ng,et al.  An Unsupervised Neural Attention Model for Aspect Extraction , 2017, ACL.

[25]  Hwee Tou Ng,et al.  Exploiting Document Knowledge for Aspect-level Sentiment Classification , 2018, ACL.

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

[27]  Ruifeng Xu,et al.  Stance Classification with Target-specific Neural Attention , 2017, IJCAI.

[28]  Tieyun Qian,et al.  Enhanced Aspect Level Sentiment Classification with Auxiliary Memory , 2018, COLING.

[29]  Kentaro Inui,et al.  Dependency Tree-based Sentiment Classification using CRFs with Hidden Variables , 2010, NAACL.

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

[31]  Jure Leskovec,et al.  Inducing Domain-Specific Sentiment Lexicons from Unlabeled Corpora , 2016, EMNLP.

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

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

[34]  Jeonghee Yi,et al.  Sentiment analysis: capturing favorability using natural language processing , 2003, K-CAP '03.

[35]  Jason Weston,et al.  End-To-End Memory Networks , 2015, NIPS.

[36]  Le Yi Wang,et al.  Sentiment Lexicon Construction with Representation Learning Based on Hierarchical Sentiment Supervision , 2017, EMNLP.

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

[38]  Siu Cheung Hui,et al.  Dyadic Memory Networks for Aspect-based Sentiment Analysis , 2017, CIKM.

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

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

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