Weakly-Supervised Deep Embedding for Product Review Sentiment Analysis

IEEE Transactions on Knowledge and Data Engineering - Tập 30 Số 1 - Trang 185-197 - 2018
Wei Zhao1, Ziyu Guan1,2, Long Chen2, Xiaofei He3, Deng Cai3, Beidou Wang4, Quan Wang1
1School of Computer Science and Technology, Xidian University, Xi'an, CN, China
2School of Information and Technology, Northwest University of China, Xi'an, CN, China
3State Key Lab of CAD&CG, Zhejiang University, Hangzhou, CN, China
4School of Computing Science, Simon Fraser University, Burnaby, BC, Canada

Tóm tắt

Từ khóa


Tài liệu tham khảo

socher, 2012, Semantic compositionality through recursive matrix-vector spaces, Proc Joint Conf Empirical Methods Natural Language Process Comput Natural Language Learn, 1201

10.1145/2661829.2661935

10.18653/v1/D15-1298

mullen, 2004, Sentiment analysis using support vector machines with diverse information sources, Proc Conf Empirical Methods Natural Language Process, 4, 412

mikolov, 2013, Distributed representations of words and phrases and their compositionality, Proc Advances Neural Inf Process Syst, 3111

mikolov, 2013, Efficient estimation of word representations in vector space, Proc Workshop Int Conf Learn Represent

qu, 2012, A weakly supervised model for sentence-level semantic orientation analysis with multiple experts, Proc Joint Conf Empirical Methods Natural Language Process Comput Natural Language Learn, 149

qiu, 2015, Convolutional neural tensor network architecture for community-based question answering, Proc 24th Int Conf Artif Intell, 1305

10.3115/1118693.1118704

10.1561/1500000011

maaten, 2008, Visualizing data using t-SNE, J Mach Learn Res, 9, 2579

maas, 2011, Learning word vectors for sentiment analysis, Proc Annu Meeting Assoc Comput Linguist Conf Human Lang Technol, 142

10.1145/2783258.2783381

10.1109/TPAMI.2013.50

10.1561/2200000006

10.3115/v1/P14-1062

kiros et, 2015, Skip-thought vectors, Proc 28th Int Conf Neural Inf Process Syst, 3294

10.3115/v1/D14-1181

le, 2014, Distributed representations of sentences and documents, Proc Int Conf Mach Learn, 14, 1188

lakkaraju, 2014, Aspect specific sentiment analysis using hierarchical deep learning, Proc Neural Inf Process Syst Workshop Deep Learn Representation Learn

10.1145/1060745.1060797

liu, 2012, Sentiment Analysis and Opinion Mining, 10.1007/978-3-031-02145-9

10.1145/1390156.1390303

wieting, 2015, Towards universal paraphrastic sentence embeddings

zhu, 2011, Aspect-based opinion polling from customer reviews, IEEE Trans Affect Comput, 2, 37, 10.1109/T-AFFC.2011.2

zhang, 2015, Character-level convolutional networks for text classification, Proc 28th Int Conf Neural Inf Process Syst, 649

zhang, 2011, Identifying noun product features that imply opinions, Proc 32nd Ann Meeting Assoc for Computational Linguistics, 575

duchi, 2011, Adaptive subgradient methods for online learning and stochastic optimization, J Mach Learn Res, 12, 2121

fan, 2008, Liblinear: A library for large linear classification, J Mach Learn Res, 9, 1871

socher, 2011, Semi-supervised recursive autoencoders for predicting sentiment distributions, Proc Conf Empirical Methods Natural Language Process, 151

10.1145/2436256.2436274

10.1037/h0031619

glorot, 2011, Domain adaptation for large-scale sentiment classification: A deep learning approach, Proc 28th Int Conf Mach Learn, 513

10.1016/j.neunet.2005.06.042

10.1109/TNNLS.2016.2582924

10.1145/1242572.1242602

10.1162/neco.1997.9.8.1735

10.1145/1014052.1014073

10.18653/v1/N16-1093

bishop, 2006, Pattern Recognition and Machine Learning

10.1145/775224.775226

collobert, 2011, Natural language processing (almost) from scratch, J Mach Learn Res, 12, 2493

10.1145/1341531.1341561

10.1002/(SICI)1097-4571(199009)41:6<391::AID-ASI1>3.0.CO;2-9

10.18653/v1/D16-1058

10.3115/v1/P14-2009

10.3115/v1/P14-1146

10.18653/v1/D16-1021

wang, 2012, Baselines and bigrams: Simple, good sentiment and topic classification, Proc 32nd Ann Meeting Assoc for Computational Linguistics, 90

turney, 2002, Thumbs up or thumbs down?: Semantic orientation applied to unsupervised classification of reviews, Proc 32nd Ann Meeting Assoc for Computational Linguistics, 417

täckström, 2011, Semi-supervised latent variable models for sentence-level sentiment analysis, Proc 46th Annu Meeting Assoc for Comput Linguist Human Lang Technol Short Papers, 569

socher, 2013, Recursive deep models for semantic compositionality over a sentiment treebank, Proc Conf Empirical Methods Natural Language Process, 1631

10.1002/widm.1171

tang, 2016, Effective LSTMs for target-dependent sentiment classification, Proc 26th Int Conf Comput Linguistics, 3298