RAG-TCGCN: Aspect Sentiment Analysis Based on Residual Attention Gating and Three-Channel Graph Convolutional Networks
Source abstract
Abstract
Aspect-based sentiment analysis (ABSA) is a fine-grained sentiment analysis task that mainly judges the polarity of a given aspect word in a review. Current methods mainly use graph networks to do aspect-level sentiment classification tasks, most of which use syntactic or semantic graphs, and utilize attention mechanisms to interact and correlate aspect terms and contexts to obtain more useful feature representations. However, these methods may ignore some insignificant syntactic structures and some implicit information in some sentences. The attention mechanism then easily loses the original information, which eventually leads to inaccurate sentiment analysis. In order to solve this problem, this paper proposes a model based on residual attention gating and three-channel graph convolutional network (RAG-TCGCN). Firstly, the model uses a three-channel network composed of syntactic information, semantic information, and public information to simultaneously optimize and fuse through the multi-head attention mechanism to solve the problem of sentences without significant syntactic structure and with implicit information. Through the residual attention gating mechanism the problem of loss of original information is solved. Experimental verification shows that the accuracy and F1 value of the model are improved on the three public datasets.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Sentiment Analysis and Opinion Mining · Text and Document Classification Technologies · Advanced Text Analysis Techniques
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
College of Information Science and Engineering, Xinjiang University, Urumqi 830046, China
Funding
National Natural Science Foundation of China · Natural Science Foundation of Xinjiang Uygur Autonomous Region Project
References (47)
Show source-provided references
1. Opinion mining and sentiment analysis10.1561/1500000011 ↗
2. Sentiment Analysis and Opinion Mining
3. Sentiment analysis algorithms and applications: A survey10.1016/j.asej.2014.04.011 ↗
4. Coarse- and fine-grained sentiment analysis of social media text
5. Aspect extraction in sentiment analysis: Comparativeanalysis and survey10.1007/s10462-016-9472-z ↗
6. Tang, H., Ji, D.H., Li, C.L., and Zhou, Q. (2020, January 5–10). Dependency graph enhanced dual-transformer structure for aspect-based sentiment classification. Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, Association for Computational Linguistics, Online.10.18653/v1/2020.acl-main.588 ↗
7. Fine-grained emotion classification of chinese microblogs based on graph convolution networks10.1007/s11280-020-00803-0 ↗
8. Modeling sentiment dependencies with graph convolutional networks for aspect-level sentiment classification
9. Target-aspect-sentiment joint detection for aspect-based sentiment analysis
10. Schmitt, M., Steinheber, S., Schreiber, K., and Roth, B. (November, January 31). Joint aspect and polarity classification for aspect-based sentiment analysis with end-to-end neural networks. Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, Brussels, Belgium.10.18653/v1/D18-1139 ↗
11. Attention-based lstm for aspect-level sentiment classification
12. Ma, D., Li, S., Zhang, X., and Wang, H. (2017, January 19–25). Interactive attention networks for aspect-level sentiment classification. Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence, Melbourne, Australia.10.24963/ijcai.2017/568 ↗
13. Multi-head attention model for aspect level sentiment analysis10.3233/JIFS-179383 ↗
14. Liu, P., Liu, T., and Shi, J. (April, January 30). Aspect level sentiment classification with unbiased attention and target enhanced representations. Proceedings of the 35th Annual ACM Symposium on Applied Computing, Virtual.
15. Zhang, C., Li, Q.C., and Song, D.W. (2019, January 3–7). Aspect-based sentiment classification with aspect-specific graph convolutional networks. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), Hong Kong, China.10.18653/v1/D19-1464 ↗
16. Sun, K., Zhang, R.C., Samuel, M., Mao, Y.Y., and Liu, X.D. (2019, January 3–7). Aspect-level sentiment analysis via convolution over dependency tree. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), Hong Kong, China.10.18653/v1/D19-1569 ↗
17. Huang, B.X., and Kathleen, M.C. (2019, January 3–7). Syntactic-aware aspect level sentiment classification with graph attention networks. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), Hong Kong, China.10.18653/v1/D19-1549 ↗
18. Wang, X., Zhu, M.Q., Bo, D., Cui, P., Shi, C., and Pei, J. (2020, January 6–10). Am-gcn: Adaptive multichannel graph convolutional networks. Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, Virtual.10.1145/3394486.3403177 ↗
19. Replicate, walk, and stop on syntactic: An effective neural network model for aspectlevel sentiment classification
20. Neural machine translation by jointly learning to align and translate
21. Baccianella, S., Esuli, A., and Sebastiani, F. (2010, January 17–23). Senti-WordNet 3.0: An enhanced lexical resource for sentiment analysis and opinion mining. Proceedings of the International Conference on Language Resources and Evaluation (LREC 2010), Valletta, Malta.
22. Mining opinions from the Web: Beyond relevance retrieval10.1002/asi.20630 ↗
23. (2007, October 22). Hownet Sentiment Dictionary. Available online: https://cidian.cnki.net.
24. Nguyen, T.H., and Shirai, K. (2015). Aspect-based sentiment anslysis using tree kernel based relation. Lecture Notes in Computer Science, Proceedings of the International Conference on Intelligent Text Processing and Computational Linguistics, Cairo, Egypt, 14–20, April 2015, Springer.10.1007/978-3-319-18117-2_51 ↗
25. Ding, X., Liu, B., and Yu, P. (2008, January 11–12). A holist lexicon-based approach to opinion mining. Proceedings of the 2008 International Conference on Web Search and Data Mining, Palo Alto, CA, USA.10.1145/1341531.1341561 ↗
26. Pang, B., Lee, L., and Shivakumar, V. (2002, January 6–7). Thumbs up? Sentiment classification usingmachine learning techniques. Proceedings of the Conference on Empirical Methods in Natural Language Professing (EMNLP), Philadelphia, PA, USA.
27. Waila, P., Singh, V.K., and Singh, M.K. (2012, January 18–20). Evaluating Machine Learning and Unsupervised Semantic Orientation approaches for sentiment analysis of textual reviews. Proceedings of the 2012 IEEE International Conference on Computational Intelligence and Computing Research, Coimbatore, India.10.1109/ICCIC.2012.6510235 ↗
28. Research on sentiment analysis model of commodity reviews based on machine learning
29. Chen, Y.H. (2015). Convolutional Neural Networks for Sentence Classification. [Master’s Thesis, University of Waterloo].
30. Study of sentiment classification for Chinese microblog based on recurrent neural network10.1049/cje.2016.07.002 ↗
31. Nowak, J., Taspinar, A., and Scherer, R. (2017). LSTM recurrent neural networks for short text and sentiment classification. Lecture Notes in Computer Science, Proceedings of the International Conference on Artificial Intelligence and Soft Computing, Zakopane, Poland, 11–15 June 2017, Springer.10.1007/978-3-319-59060-8_50 ↗
32. Wang, Y.Q., Huang, M., Zhu, X.Y., and Zhao, L. (2016, January 1–5). Attention-based lstm for aspect-level sentiment classification. Proceedings of the 2016 conference on empirical methods in natural language processing, Austin, TX, USA.10.18653/v1/D16-1058 ↗
33. Song, Y., Wang, J.H., Tao, J., Liu, Z.Y., and Rao, Y. (2019). Attentional encoder network for targeted sentiment classification. arXiv.10.1007/978-3-030-30490-4_9 ↗
34. Chen, P., Sun, Z.Q., Bing, L.D., and Yang, W. (2017, January 7–11). Recurrent attention network on memory for aspect sentiment analysis. Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, Copenhagen, Denmark.10.18653/v1/D17-1047 ↗
35. Li, C., Guo, X., and Mei, Q. (2017, January 6–10). Deep Memory Networks for Attitude Identifification. Proceedings of the Tenth ACM International Conference on Web Search and Data Mining, Cambridge, UK.10.1145/3018661.3018714 ↗
36. Kipf, T.N., and Welling, M. (2017, January 24–26). Semi-Supervised Classifification with Graph Convolutional Networks. Proceedings of the 2017 International Conference on Learning Representations (ICLR), Toulon, France.
37. Wang, K., Shen, W., Yang, Y.Y., Quan, X.J., and Wang, R. (2020, January 5–10). Relational Graph Attention Network for Aspect-based Sentiment Analysis. Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, Online.10.18653/v1/2020.acl-main.295 ↗
38. Huang, B.X., and Carley, K.M. (2019). Parameterized convolutional neural net-works for aspect level sentiment classification. arXiv.10.18653/v1/D18-1136 ↗
39. Li, R.F., Chen, H., Feng, F.X., Ma, Z.Y., Wang, X.J., and Eduard, H. (2021, January 1–6). Dual Graph Convolutional Networks for Aspect-based Sentiment Analysis. Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, Period, Online.10.18653/v1/2021.acl-long.494 ↗
40. Pennington, J., Socher, R., and Manning, C. (2014, January 25–29). Glove: Global vectors for word representation. Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), Doha, Qatar.10.3115/v1/D14-1162 ↗
41. Attention is all you need
42. The neural basis of combinatory syntactic and semantics10.1126/science.aax0050 ↗
43. Li, D., Wei, F., Tan, C.Q., Tang, D.Y., Zhou, M., and Xu, K. (2014, January 23–24). Adaptive recursive neural network for target-dependent Twitter sentiment classification. Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics, Baltimore, MI, USA.
44. Maria, P., Dimitris, G., John, P., Harris, P., Ion, A., and Suresh, M. (2014, January 23–24). SemEval-2014 task 4: Aspect based sentiment analysis. Proceedings of the 8th International Workshop on Semantic Evaluation (SemEval 2014), Dublin, Ireland.
45. Huang, B., Ou, Y., and Carley, K.M. (2018). Aspect level sentiment classification with attention-over-attention neural networks. Lecture Notes in Computer Science, Proceedings of the International Conference on Social Computing, Behavioral-Cultural Modeling and Prediction and Behavior Representation in Modeling and Simulation, Washington, DC, USA, 10–13 July 2018, Springer.10.1007/978-3-319-93372-6_22 ↗
46. Fan, F.F., Feng, Y.S., and Zhao, D.Y. (November, January 31). Multi-grained attention network for aspect-level sentiment classification. Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, Brussels, Belgium.10.18653/v1/D18-1380 ↗
47. Zhang, M., and Qian, T.Y. (2020, January 16–18). Convolution over hierarchical syntactic and lexical graphs for aspect level sentiment analysis. Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), Online.10.18653/v1/2020.emnlp-main.286 ↗