Multi-Channel Lexicon Integrated CNN-BiLSTM Models for Sentiment Analysis

We improved sentiment classifier for predicting document-level sentiments from Twitter by using multi-channel lexicon embedidngs. The core of the architecture is based on CNNBiLSTM that can capture high level features and long term dependency in documents. We also applied multi-channel method on lexicon to improve lexicon features. The macroaveraged F1 score of our model outperformed other classifiers in this paper by 1-4%. Our model achieved F1 score of 64% in SemEval Task 4 (2013-2016) datasets when multichannel lexicon embedding was applied with 100 dimensions of word embedding.

[1]  Nitish Srivastava,et al.  Improving neural networks by preventing co-adaptation of feature detectors , 2012, ArXiv.

[2]  Matthijs Douze,et al.  FastText.zip: Compressing text classification models , 2016, ArXiv.

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

[4]  Xuejie Zhang,et al.  YNU-HPCC at SemEval 2017 Task 4: Using A Multi-Channel CNN-LSTM Model for Sentiment Classification , 2017, SemEval@ACL.

[5]  Diyi Yang,et al.  Hierarchical Attention Networks for Document Classification , 2016, NAACL.

[6]  Jeffrey Dean,et al.  Distributed Representations of Words and Phrases and their Compositionality , 2013, NIPS.

[7]  Aurélien Lucchi,et al.  SwissCheese at SemEval-2016 Task 4: Sentiment Classification Using an Ensemble of Convolutional Neural Networks with Distant Supervision , 2016, *SEMEVAL.

[8]  Thomas Hofmann,et al.  Leveraging Large Amounts of Weakly Supervised Data for Multi-Language Sentiment Classification , 2017, WWW.

[9]  Saif Mohammad,et al.  Sentiment Analysis of Short Informal Texts , 2014, J. Artif. Intell. Res..

[10]  Saif Mohammad,et al.  Generating High-Coverage Semantic Orientation Lexicons From Overtly Marked Words and a Thesaurus , 2009, EMNLP.

[11]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

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

[13]  Yoshua Bengio,et al.  Show, Attend and Tell: Neural Image Caption Generation with Visual Attention , 2015, ICML.

[14]  Bonggun Shin,et al.  Lexicon Integrated CNN Models with Attention for Sentiment Analysis , 2016, WASSA@EMNLP.

[15]  Saif Mohammad,et al.  CROWDSOURCING A WORD–EMOTION ASSOCIATION LEXICON , 2013, Comput. Intell..

[16]  Kevin Skadron,et al.  Scalable parallel programming , 2008, 2008 IEEE Hot Chips 20 Symposium (HCS).

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

[18]  John Tran,et al.  cuDNN: Efficient Primitives for Deep Learning , 2014, ArXiv.

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

[20]  Preslav Nakov,et al.  SemEval-2015 Task 10: Sentiment Analysis in Twitter , 2015, *SEMEVAL.

[21]  Yoon Kim,et al.  Convolutional Neural Networks for Sentence Classification , 2014, EMNLP.

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