A Survey of Sentiment Analysis Based on Deep Learning
Commenced in January 2007
Frequency: Monthly
Edition: International
Paper Count: 32918
A Survey of Sentiment Analysis Based on Deep Learning

Authors: Pingping Lin, Xudong Luo, Yifan Fan

Abstract:

Sentiment analysis is a very active research topic. Every day, Facebook, Twitter, Weibo, and other social media, as well as significant e-commerce websites, generate a massive amount of comments, which can be used to analyse peoples opinions or emotions. The existing methods for sentiment analysis are based mainly on sentiment dictionaries, machine learning, and deep learning. The first two kinds of methods rely on heavily sentiment dictionaries or large amounts of labelled data. The third one overcomes these two problems. So, in this paper, we focus on the third one. Specifically, we survey various sentiment analysis methods based on convolutional neural network, recurrent neural network, long short-term memory, deep neural network, deep belief network, and memory network. We compare their futures, advantages, and disadvantages. Also, we point out the main problems of these methods, which may be worthy of careful studies in the future. Finally, we also examine the application of deep learning in multimodal sentiment analysis and aspect-level sentiment analysis.

Keywords: Natural language processing, sentiment analysis, document analysis, multimodal sentiment analysis, deep learning.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1945

References:


[1] K. Coffman and A. Odlyzko, Internet Growth: Is there a “Moore’s law” for data traffic? Handbook of Massive Data Sets, 2002, pp. 47–93.
[2] S. F. Pengnate and F. J. Riggins, “The role of emotion in p2p microfinance funding: A sentiment analysis approach,” International Journal of Information Management, vol. 54, p. 102138, 2020.
[3] C.-M. Yu, “Mining opinions from product review: Principles and algorithm analysis,” Information Studies: Theory & Application, vol. 32, no. 7, pp. 124–128, 2009, (In Chinese).
[4] B. Liu and L. Zhang, A Survey of opinion mining and sentiment analysis. Mining Text Data, 2012, pp. 415–463.
[5] T. Nasukawa and J. Yi, “Sentiment analysis: Capturing favorability using natural language processing,” in Proceedings of the 2nd International Conference on Knowledge Capture, 2003, pp. 70–77.
[6] B. Pang and L. Lee, “Opinion mining and sentiment analysis,” Foundations and Trends in Information Retrieval, vol. 2, no. 1-2, pp. 1–135, 2008.
[7] B. Liu, “Sentiment analysis and opinion mining,” Synthesis lectures on human language technologies, vol. 5, no. 1, pp. 1–167, 2012.
[8] C. Alfaro, J. Cano-Montero, J. Gomez, J. M. Moguerza, and F. Ortega, “A multi-stage method for content classification and opinion mining on weblog comments,” Annals of Operations Research, vol. 236, no. 1, pp. 197–213, 2016.
[9] L. Zhang, S. Wang, and B. Liu, “Deep learning for sentiment analysis: A survey,” Data Mining and Knowledge Discovery, vol. 8, no. 4, pp. 1–25, 2018.
[10] I. Prabha M and G. Umarani Srikanth, “Survey of sentiment analysis using deep learning techniques,” in Proceedings of the 1st International Conference on Innovations in Information and Communication Technology, 2019, pp. 1–9.
[11] M. Soleymani, D. Garcia, B. Jou, B. Schuller, S.-F. Chang, and M. Pantic, “A survey of multimodal sentiment analysis,” Image and Vision Computing, vol. 65, pp. 3–14, 2017.
[12] D. Stojanovski, G. Strezoski, G. Madjarov, and et al., “Deep neural network architecture for sentiment analysis and emotion identification of twitter messages,” Multimedia Tools Applications, vol. 77, no. 24, pp. 32 213–32 242, 2018.
[13] X.-L. Yang, S.-J. Xu, H. Wu, and R.-F. Bie, “Sentiment analysis of weibo comment texts based on extended vocabulary and convolutional neural network,” in Proceedings of the 2018 International Conference on Identification, Information and Knowledge in the Internet of Things, 2018, pp. 9.361–368.
[14] H.-Y. He, J. Zheng, and Z.-P. Zhang, “Text sentiment analysis combined with part of speech features and convolutional neural network,” Computer Engineering, vol. 44, no. 11, pp. 209–214, 2018.
[15] Z.-F. Sun and J. Wang, “Rcnn-bgru-hn network model for aspect-based sentiment analysis,” Computer Science, vol. 46, no. 9, pp. 223–228, 2018, (In Chinese).
[16] S. Chen, Y. Ding, Z. Xie, S. Liu, and H. Ding, “Chinese Weibo sentiment analysis based on character embedding with dual-channel convolutional neural network,” in Proceedings of 2018 IEEE 3rd International Conference on Cloud Computing and Big Data Analysis, 2018, pp. 107–111.
[17] A. Shenoy and A. Sardana, “Multilogue-net: A context aware rnn for multi-modal emotion detection and sentiment analysis in conversation,” in Proceedings of the 2020 Computing Research Repository, 2020, pp. 1–9.
[18] Z.-F. Hao, H. Huang, R.-C. Cai, and W. Wen, “Fine-grained opinion analysis based on multi-feature fusion and bidirectional RNN,” Computer Engineering, vol. 44, no. 7, pp. 199–2049, 2018, (In Chinese).
[19] S.-W. Pei and L.-L. Wang, “Text sentiment analysis based on attention mechanism,” Computer Engineering & Science, vol. 41, no. 02, pp. 343–353, 2019, (In Chinese).
[20] S. Hochreiter and J. Schmidhuber, “Long short-term memory,” Neural computation, vol. 9, no. 8, p. 17351780, 1997.
[21] G.-H. Chen, “Text sentiment analysis based on polarity transfer and bidirectional long-short term memory,” Information Technology, no. 2, pp. 149–152, 2018.
[22] H.-Y. Peng, L. Xu, L.-D. Bing, F. Huang, W. Lu, and L. Si, “Knowing what, how and why: A near complete solution for aspect-based sentiment analysis,” in Proceedings of the Thirty-Fourth AAAI Conference on Artificial Intelligence, 2020, pp. 1–9.
[23] Y. Tay, L.-A. Tuan, and S.-C. Hui, “Learning to attend via word-aspect associative fusion for aspect-based sentiment analysis,” in Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence, vol. 18, 2018, pp. 5956–5963.
[24] Z. Xu, B. Liu, B. Wang, S. C., and X. Wang, “Incorporating loose-structured knowledge into lstm with recall gate for conversation modeling,” in Proceedings of the 2016 Computing Research Repository, 2016, pp. 1–10.
[25] Y.-K. Ma, H.-Y. Peng, and E. Cambria, “Targeted aspect-based sentiment analysis via embedding commonsense knowledge into an attentive lstm,” in Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence, 2018, pp. 5876–5883.
[26] B.-W. Xing, L.-J. Liao, D.-D. Song, J.-G. Wang, F.-Z. Zhang, and H.-Y. Huang, “Earlier attention? aspect-aware lstm for aspect-based sentiment analysis,” in Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence, 2019, pp. 5313–5319.
[27] Y. Wang, Q. Chen, M. Ahmed, Z. Li, W. Pan, and H. Liu, “Joint inference for aspect-level sentiment analysis by deep neural networks and linguistic hints,” IEEE Transactions on Knowledge and Data Engineering, 2019.
[28] C. Aydin and T. Gungor, “Combination of recursive and recurrent neural networks for aspect-based sentiment analysis using inter-aspect relations,” IEEE Access, vol. 8, pp. 77 820–77 832, 2020.
[29] A. Ishaq, S. Asghar, and S. Gillani, “Aspect-based sentiment analysis using a hybridized approach based on CNN and GA,” IEEE Access, vol. 8, pp. 135 499–135 512, 2020.
[30] Z.-B. Jia, X.-X. Bai, and S.-M. Pang, “Hierarchical gated deep memory network with position-aware for aspect-based sentiment analysis,” IEEE Access, vol. 8, pp. 136 340–136 347, 2020.
[31] G.-F. Liu, X.-Y. Huang, X.-Y. Liu, and A.-Z. Yang, “A novel aspect-based sentiment analysis network model based on multilingual hierarchy in online social network,” Computer Journal, vol. 63, no. 3, pp. 410–424, 2020.
[32] y.-W. Zheng, R.-C. Zhang, S. Mensah, and Y.-Y. Mao, “Replicate, walk, and stop on syntax: An effective neural network model for aspect-level sentiment classification,” in Proceedings of the Thirty-Fourth AAAI Conference on Artificial Intelligence, 2020, pp. 9685–9692.
[33] X. Wang, W. Jiang, and Z. Luo, “Combination of convolutional and recurrent neural network for sentiment analysis of short texts,” in Proceedings of the 26th International Conference on Computational Linguistics, 2016, pp. 2428–2437.
[34] F. Luo and H.-F. Wang, “Chinese text sentiment classification by h-rnn-cnn,” Acta Scientiarum Naturalium Universitatis Pekinensis, vol. 54, no. 3, pp. 459–465, 2018.
[35] K. Kwaik, M. Saad, S. Chatzikyriakidis, and S. Dobnik, “LSTM-CNN deep learning model for sentiment analysis of dialectal Arabic,” in Arabic Language Processing: From Theory to Practice, ser. Communications in Computer and Information Science, vol. 1108, 2019, pp. 108–121.
[36] A. Rehman, A. Malik, B. Raza, and W. Ali, “A hybrid CNN-LSTM model for improving accuracy of movie reviews sentiment analysis,” Multimedia Tools and Applications, vol. 78, no. 18, pp. 26 597–26 613, 2019.
[37] D. Jain, A. Kumar, and G. Garg, “Sarcasm detection in mash-up language using soft-attention based bi-directional lstm and feature-rich cnn,” Applied Soft Computing, vol. 91, p. 106198, 2020.
[38] M.-D. Wang and G.-M. Hu, “A novel method for twitter sentiment analysis based on attentional-graph neural network,” Information, vol. 11, no. 2, p. 92, 2020.
[39] Z.-L. Wu, J. Ming, and M. Zhang, “Transformer based memory network for sentiment analysis of chinese weibo texts,” in Proceedings of the 2019 International Conference on Mobile Computing, Applications, and Services, 2019, pp. 44–56.
[40] M.-J. Ling, Q.-H. Chen, Q. Sun, and Y.-B. Jia, “Hybrid neural network for sina weibo sentiment analysis,” IEEE Transactions on Computational Social Systems, vol. 7, no. 4, pp. 983–990, 2020.
[41] S. Kumar, M. Yadava, and P. Roy, “Fusion of eeg response and sentiment analysis of products review to predict customer satisfaction,” Information Fusion, vol. 52, pp. 41–52, 2019.
[42] A. Mukherjee, S. Mukhopadhyay, P. Panigrahi, and S. Goswami, “Utilization of oversampling for multiclass sentiment analysis on amazon review dataset,” in Proceedings of the IEEE 10th International Conference on Awareness Science and Technology, 2019, pp. 1–6.
[43] N. Shrestha and F. Nasoz, “Deep learning sentiment analysis of amazon.com reviews and ratings,” International Journal on Soft Computing, Artificial Intelligence and Applications, vol. 8, no. 1, pp. 1–15, 2019.
[44] X. Fang and J. Zhan, “Sentiment analysis using product review data,” Journal of Big Data, vol. 2, no. 1, p. 5, 2015.
[45] U. Chauhan, M. Afzal, A. Shahid, M. Abdar, M. Basiri, and X.-J. Zhou, “A comprehensive analysis of adverb types for mining user sentiments on amazon product reviews,” World Wide Web, vol. 23, no. 3, pp. 1811–1829, 2020.
[46] Y. Cheng, L.-B. Yao, G.-X. Xiang, and et al., “Text sentiment orientation analysis based on multi-channel CNN and bidirectional GRU with attention mechanism,” IEEE Access, vol. 8, pp. 134 964–134 975, 2020.
[47] T. Tran, H. Ba, and V. Huynh, “Measuring hotel review sentiment: An aspect-based sentiment analysis approach,” in Proceedings of the 2019 International Symposium on Integrated Uncertainty in Knowledge Modelling and Decision Making, 2019, pp. 393–405.
[48] M. Al-Smadi, O. Qawasmeh, M. Al-Ayyoub, Y. Jararweh, and B. Gupta, “Deep recurrent neural network vs. support vector machine for aspect-based sentiment analysis of arabic hotels’ reviews,” Journal of Computational Science, vol. 27, pp. 386–393, 2018.
[49] J. Shen, M. Ma, R. Xiang, Q. Lu, E. P. Vallejos, G. Xu, C.-R. Huang, and Y. Long, “Dual memory network model for sentiment analysis of review text,” Knowledge-Based Systems, vol. 188, p. 105004, 2020.
[50] Z.-x. Liu, D.-g. Zhang, G.-z. Luo, M. Lian, and B. Liu, “A new method of emotional analysis based on CNN–BiLSTM hybrid neural network,” Cluster Computing, pp. 1–13, 2020.
[51] J. Yang, Y.-Q. Yang, C.-J. Wang, and J.-Y. Xie, “Multi-entity aspect-based sentiment analysis with context, entity and aspect memory,” in Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence, 2018, pp. 6029–6036.
[52] K.-S. Song, W. Gao, L.-J. Zhao, C.-L. Sun, and X.-Z. Liu, “Cold-start aware deep memory network for multi-entity aspect-based sentiment analysis,” in Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence, 2019, pp. 5179–5203.
[53] Y. Xiao, D.-Y.Wang, and L.-G. Hou, “Unsupervised emotion recognition algorithm based on improved deep belief model in combination with probabilistic linear discriminant analysis,” Personal and Ubiquitous Computing, vol. 23, no. 3-4, pp. 553–562, 2019, (In Chinese).
[54] F. Nian, X. Chen, S. Yang, and G. Lv, “Facial attribute recognition with feature decoupling and graph convolutional networks,” IEEE Access, vol. 7, pp. 85 500–85 512, 2019.
[55] M. Zhang, Y. Liang, and H. Ma, “Context-aware affective graph reasoning for emotion recognition,” in Proceedings of the IEEE International Conference on Multimedia and Expo, 2019, p. 151156.
[56] Z.-H. Wu, S.-R. Pan, F.-W. Chen, and et al., “A comprehensive survey on graph neural networks,” in arXiv:1901.00596, 2020.
[57] E. Mansouri-Benssassi and J. Ye, “Synch-graph: Multisensory emotion recognition through neural synchrony via graph convolutional networks,” in Proceedings of the Thirty-Fourth AAAI Conference on Artificial Intelligence, 2020, pp. 1351–1358.
[58] ——, “Speech emotion recognition with early visual cross-modal enhancement using spiking neural networks,” in Proceedings of 2019 International Joint Conference on Neural Networks, 2019, pp. 1–8.
[59] Q.-M. Xue, W. Zhang, and H.-Y. Zha, “Improving domain-adapted sentiment classification by deep adversarial mutual learning,” in Proceedings of the Thirty-Fourth AAAI Conference on Artificial Intelligence, 2020, pp. 9362–9369.
[60] Y. Dai, J. Liu, X.-C. Ren, and Z.-L. Xu, “Adversarial training based multi-source unsupervised domain adaptation for sentiment analysis,” in Proceedings of the Thirty-Fourth AAAI Conference on Artificial Intelligence, 2020, pp. 7618–7625.
[61] C. Lin, S.-C. Zhao, L. Meng, and T.-S. Chua, “Multi-source domain adaptation for visual sentiment classification,” in Proceedings of the Thirty-Fourth AAAI Conference on Artificial Intelligence, 2020, pp. 2661–2668.
[62] H. Wan, Y.-F. Yang, J.-F. Du, and et al., “Target-aspect-sentiment joint detection for aspect-based sentiment analysis,” in Proceedings of the Thirty-Fourth AAAI Conference on Artificial Intelligence, 2020, pp. 9122–9129.
[63] H. Fei, Y. Zhang, Y.-F. Ren, and D.-H. Ji, “Latent emotion memory for multi-label emotion classification,” in Proceedings of the Thirty-Fourth AAAI Conference on Artificial Intelligence, 2020, pp. 7692–7699.
[64] F.-R. Huang, X.-M. Zhang, Z.-H. Zhao, and et al., “Image-text sentiment analysis via deep multimodal attentive fusion,” Knowledge- Based Systems, vol. 167, pp. 26–37, 2019.
[65] G. Mahesh, S. S. Huddar, and V. S. R. Sannakki, “Multi-level feature optimization and multimodal contextual fusion for sentiment analysis and emotion classification,” Computational Intelligence, vol. 36, no. 2, pp. 861–881, 2020.
[66] ——, “Multi-level context extraction and attention-based contextual inter-modal fusion for multimodal sentiment analysis and emotion classification,” International Journal of Multimedia Information Retrieval, vol. 9, no. 2, pp. 103–112, 2020.
[67] Y.-Z. Zhang, D.-W. Song, X. Li, and et al., “A quantum-like multimodal network framework for modeling interaction dynamics in multiparty conversational sentiment analysis,” Information Fusion, vol. 62, pp. 14–31, 2020.
[68] A. Harish and F. Sadat, “Trimodal attention module for multimodal sentiment analysis,” in Proceedings of the Thirty-Fourth AAAI Conference on Artificial Intelligence, 2020, pp. 13 803–13 804.
[69] X. Chen, G.-M. Lu, and J.-J. Yan, “Multimodal sentiment analysis based on multi-head attention mechanism,” in Proceedings of the 4th International Conference on Machine Learning and Soft Computing, 2020, pp. 34–39.
[70] T. Kim and B. Lee, “Multi-attention multimodal sentiment analysis,” in Proceedings of the 2020 on International Conference on Multimedia Retrieval, 2020, pp. 436–441.
[71] T. Mittal, U. Bhattacharya, R. Chandra, A. Bera, and D. Manocha, “M3er: Multiplicative multimodal emotion recognition using facial, textual, and speech cues,” in Proceedings of the Thirty-Fourth AAAI Conference on Artificial Intelligence, 2020, pp. 1359–1367.
[72] T. Baltrusaitis, C. Ahuja, and L. Morency, “Multimodal machine learning: A survey and taxonomy,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 41, no. 2, pp. 423–443, 2019.
[73] N. Xu, W.-J. Mao, and G.-D. Chen, “Multi-interactive memory network for aspect based multimodal sentiment analysis,” in Procedings of The Thirty-Third AAAI Conference on Artificial Intelligence, 2019, pp. 371–378.
[74] G.-Y. Cai and B.-B. Xia, “Multimedia sentiment analysis based on convolutional neural network,” Journal of Computer Applications, vol. 36, no. 2, pp. 428–431, 2016, (In Chinese).
[75] D. Cao, R. Ji, and D. Lin, “A cross-media public sentiment analysis system for microblog,” Multimedia Systems, vol. 22, no. 4, pp. 479–486, 2016.
[76] Y. Yu, H. Lin, and J. Meng, “Visual and textual sentiment analysis of a microblog using deep convolutional neural networks,” Algorithms, vol. 9, no. 2, pp. 41–51, 2016.
[77] Q. Truong and H. Lauw, “Vistanet: Visual aspect attention network for multimodal sentiment analysis,” in Procedings of The Thirty-Third AAAI Conference on Artificial Intelligence, 2019, pp. 305–312.
[78] L. Itti and C. Koch, “A model of saliency-based visual attention for rapid scene analysis,” IEEE Transactions on Pattern Analysis & Machine Intelligence, vol. 20, no. 11, p. 1254, 1998.
[79] Q.-Y. Liu, D. Zhang, L.-Q. Wu, and S.-S. Li, “Multi-modal sentiment analysis with context-augmented lstm,” Computer Science, vol. 46, no. 11, pp. 181–185, 2019, (In Chinese).
[80] L. Kaushik, A. Sangwan, and J. Hansen, “Automatic sentiment detection in naturalistic audio,” IEEE/ACM Transactions on Audio, Speech, and Language Processing, vol. 25, no. 8, pp. 1668–1679, 2017.
[81] S. Verma, C. Wang, L.-M. Zhu, and W. Liu, “Deepcu: Integrating both common and unique latent information for multimodal sentiment analysis,” in Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence, 2019, pp. 3627–3634.
[82] J.-F. Yu and J. Jiang, “Adapting bert for target-oriented multimodal sentiment classification,” in Proceedings of the Thirty-Fourth AAAI Conference on Artificial Intelligence, 2020, pp. 5408–5414.
[83] J. Devlin and et al., “Bert: Pre-training of deep bidirectional transformers for language understanding,” in Proceedings of the 2019 North American Chapter of the Association for Computational Linguistics, 2019, p. 41714186.
[84] V. Perez-Rosas, R. Mihalcea, and L. Morency, “Utterance-level multimodal sentiment analysis,” in Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics, 2013, pp. 973–982.
[85] S. Poria, E. Cambria, N. Howard, G.-B. Huang, and A. Hussain, “Fusing audio, visual and textual clues for sentiment analysis from multimodal content,” Neurocomputing, vol. 174, pp. 50–59, 2016a.
[86] W.-M. Yu, H. Xu, F.-Y. Meng, and et al., “Ch-sims: A chinese multimodal sentiment analysis dataset with fine-grained annotation of modality,” in Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, 2020, pp. 3718–3727.
[87] A. Zadeh, M. Chen, S. Poria, E. Cambria, and L. Morency, “Tensor fusion network for multimodal sentiment analysis,” in Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, 2017, pp. 1103–1114.
[88] Z.-L. Wang, Z.-H. Wan, and X.-J. Wan, “Transmodality: An end2end fusion method with transformer for multimodal sentiment analysis,” in Proceedings of the 29th World Wide Web, 2020, pp. 2514–2520.
[89] C. Xi, G.-M. Lu, and J.-J. Yan, “Multimodal sentiment analysis based on multi-head attention mechanism,” in Proceedings of the 4th International Conference on Machine Learning and Soft Computing, 2020, pp. 34–39.
[90] X. Wu, T. Zhang, L.-J. Zang, and et al., “Mask and infill: Applying masked language model for sentiment transfer,” in Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence, 2019, pp. 5271–5277.
[91] Z. Yang and et al., “Xlnet: Generalized autoregressive pretraining for language understanding,” in Proceedings of 33rd Conference on Neural Information Processing Systems, 2019, pp. 5754–5764.
[92] T. B. Brown and et al., “Language models are few-shot learners,” arXiv preprint arXiv:2005.14165, 2020.