---
title: "Aspect-Level Sentiment Analysis Via Convolution — Sun 2019"
description: "The paper addresses aspect-based sentiment classification: deciding whether a sentence conveys a positive, negative or neutral opinion toward one aspect…"
authors: ["Kai Sun", "Richong Zhang", "Samuel Mensah", "Yongyi Mao", "Xudong Liu"]
year: 2019
venue: "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)"
source: "https://aclanthology.org/D19-1569/"
doi: "10.18653/v1/d19-1569"
licence: "CC BY 4.0 (ACL Anthology)"
licence_url: "https://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/sun-2019-aspect-level-sentiment-analysis-convolution/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/sun-2019-aspect-level-sentiment-analysis-convolution/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2019](https://md.research.elamur.ai/free/en/papers/2019/) / Aspect-Level Sentiment Analysis Via Convolution over Dependency Tree

# Aspect-Level Sentiment Analysis Via Convolution over Dependency Tree

**Authors:** [Kai Sun](https://md.research.elamur.ai/free/en/authors/kai-sun/), [Richong Zhang](https://md.research.elamur.ai/free/en/authors/richong-zhang/), Samuel Mensah, Yongyi Mao, Xudong Liu · **Year:** 2019 · **Venue:** Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/D19-1569/) · [PDF](https://aclanthology.org/D19-1569.pdf) · [DOI 10.18653/v1/d19-1569](https://doi.org/10.18653/v1/d19-1569) · [OpenAlex](https://openalex.org/W2970748008)

**Citations:** 430 citations (openalex-snapshot · 2026-10-14) · [67](#cited-by) in our library, of the 140884 papers whose bibliographies we read

## Summary
The paper addresses aspect-based sentiment classification: deciding whether a sentence conveys a positive, negative or neutral opinion toward one aspect term. The authors argue that dependency trees bring aspect terms and their opinion words close together, even in long sentences, and that this structure suits graph neural networks. Their model, CDT (convolution over dependency tree), works in three steps. A Bi-LSTM first produces contextual word vectors. A GCN then refines these vectors over the sentence's dependency graph, using self-loops and degree normalisation. Finally, only the aspect-token vectors are pooled into the representation passed to the softmax classifier. Stacking GCN layers lets information from opinion words reach the aspect nodes. This design follows earlier work that placed a GCN on top of an LSTM for relation extraction. The authors report that CDT is a new state of the art, although the excerpt omits the datasets and scores. They support the aspect-only pooling choice with masking experiments and attention visualisations. The study shows that a fairly simple model with syntax information can outperform more complex ones.

## Key points
- **Architecture:** Bi-LSTM encoder, then k GCN layers over the dependency adjacency matrix, then pooling over aspect tokens only, then softmax.
  - Each GCN layer uses ReLU and normalisation c_i = 1/degree.
  - k layers reach the k-th order neighbourhood of each word.
- **Pooling inconsistency:** Figure 2 labels the aggregation step "Average Pool", but the analysis section describes max pooling.
- **Masking test:** Inputs are zeroed one word at a time with the ASP-GCN variant to score each word's relevance. Opinion words score higher as more GCN layers are added.
- **Case studies:** The aspects 'Sangria', 'paratha' and 'LASAGNA' are used to compare ASP-BiLSTM, TNet and CDT. Only CDT finds the right opinion words, such as 'FRESH' and 'BEST'.
- **Missing results:** The provided text omits the benchmark names and accuracy/F1 figures, so check the original paper before citing numbers.

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

Fields: [Natural language processing](https://md.research.elamur.ai/free/en/shelves/nlp/)

Topics: [Dependency parsing](https://md.research.elamur.ai/free/en/topics/dependency-parsing/)

## Cited by

Cited by

67 papers of our library cite it (of the 140884 whose bibliographies we read); 1 of them have a page here, 66 not yet.

- [Relational Graph Attention Network for Aspect-based Sentiment Analysis](https://md.research.elamur.ai/free/en/papers/wang-2020-relational-graph-attention-network-aspect/)

## Cite

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@inproceedings{sun2019aspect,
  title = {{Aspect-Level Sentiment Analysis Via Convolution over Dependency Tree}},
  author = {Sun, Kai and Zhang, Richong and Mensah, Samuel and Mao, Yongyi and Liu, Xudong},
  booktitle = {Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)},
  year = {2019},
  doi = {10.18653/v1/d19-1569},
  url = {https://doi.org/10.18653/v1/d19-1569}
}
```

- [← previous Aspect-based Sentiment Classification with Aspect-specific Graph Convolutional Networks](https://md.research.elamur.ai/free/en/papers/zhang-2019-aspect-based-sentiment-classification-aspect/)
- [next → Assessing BERT's Syntactic Abilities](https://md.research.elamur.ai/free/en/papers/goldberg-2019-assessing-bert-s-syntactic-abilities/)
- [↑ back to papers of 2019](https://md.research.elamur.ai/free/en/papers/2019/)

## References

34 references, 10 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Peng Chen, Zhongqian Sun, Lidong Bing, and Wei Yang. 2017. Recurrent attention network on memory for aspect sentiment analysis. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 452–461. [find](https://scholar.google.com/scholar?q=Peng+Chen%2C+Zhongqian+Sun%2C+Lidong+Bing%2C+and+Wei+Yang%2E+2017%2E+Recurrent+attention+network+on+memory+for+aspect+sentiment+analysis%2E+In+Proceedings+of+the+2017+Conference+on+Empirical+Methods+in+Natural+La) [our card](https://md.research.elamur.ai/free/en/papers/chen-2017-recurrent-attention-network-memory-aspect/)
2. Jiajun Cheng, Shenglin Zhao, Jiani Zhang, Irwin King, Xin Zhang, and Hui Wang. 2017. Aspect-level sentiment classification with heat (hierarchical attention) network. In Proceedings of the 2017 ACM on Conference on Information and Knowledge Management, pages 97–106. [find](https://scholar.google.com/scholar?q=Jiajun+Cheng%2C+Shenglin+Zhao%2C+Jiani+Zhang%2C+Irwin+King%2C+Xin+Zhang%2C+and+Hui+Wang%2E+2017%2E+Aspect%2Dlevel+sentiment+classification+with+heat+%28hierarchical+attention%29+network%2E+In+Proceedings+of+the+2017+ACM+on)
3. Xiaowen Ding, Bing Liu, and Philip S. Yu. 2008. A holistic lexicon-based approach to opinion mining. In Proceedings of the 2008 International Conference on Web Search and Data Mining, pages 231–240. [find](https://scholar.google.com/scholar?q=Xiaowen+Ding%2C+Bing+Liu%2C+and+Philip+S%2E+Yu%2E+2008%2E+A+holistic+lexicon%2Dbased+approach+to+opinion+mining%2E+In+Proceedings+of+the+2008+International+Conference+on+Web+Search+and+Data+Mining%2C+pages+231%E2%80%93240%2E)
4. Li Dong, Furu Wei, Chuanqi Tan, Duyu Tang, Ming Zhou, and Ke Xu. 2014. Adaptive recursive neural network for target-dependent twitter sentiment classification. In Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), volume 2, pages 49–54. [find](https://scholar.google.com/scholar?q=Li+Dong%2C+Furu+Wei%2C+Chuanqi+Tan%2C+Duyu+Tang%2C+Ming+Zhou%2C+and+Ke+Xu%2E+2014%2E+Adaptive+recursive+neural+network+for+target%2Ddependent+twitter+sentiment+classification%2E+In+Proceedings+of+the+52nd+Annual+Meetin) [our card](https://md.research.elamur.ai/free/en/papers/dong-2014-adaptive-recursive-neural-network-target/)
5. Feifan Fan, Yansong Feng, and Dongyan Zhao. 2018a. Multi-grained attention network for aspect-level sentiment classification. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 3433–3442. [find](https://scholar.google.com/scholar?q=Feifan+Fan%2C+Yansong+Feng%2C+and+Dongyan+Zhao%2E+2018a%2E+Multi%2Dgrained+attention+network+for+aspect%2Dlevel+sentiment+classification%2E+In+Proceedings+of+the+2018+Conference+on+Empirical+Methods+in+Natural+Lang)
6. Feifan Fan, Yansong Feng, and Dongyan Zhao. 2018b. Multi-grained attention network for aspect-level sentiment classification. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, Brussels, Belgium, October 31 -November 4, 2018, pages 3433–3442. [find](https://scholar.google.com/scholar?q=Feifan+Fan%2C+Yansong+Feng%2C+and+Dongyan+Zhao%2E+2018b%2E+Multi%2Dgrained+attention+network+for+aspect%2Dlevel+sentiment+classification%2E+In+Proceedings+of+the+2018+Conference+on+Empirical+Methods+in+Natural+Lang)
7. Shuqin Gu, Lipeng Zhang, Yuexian Hou, and Yin Song. 2018. A position-aware bidirectional attention network for aspect-level sentiment analysis. In Proceedings of the 27th International Conference on Computational Linguistics, pages 774–784. [find](https://scholar.google.com/scholar?q=Shuqin+Gu%2C+Lipeng+Zhang%2C+Yuexian+Hou%2C+and+Yin+Song%2E+2018%2E+A+position%2Daware+bidirectional+attention+network+for+aspect%2Dlevel+sentiment+analysis%2E+In+Proceedings+of+the+27th+International+Conference+on+C)
8. Ruidan He, Wee Sun Lee, Hwee Tou Ng, and Daniel Dahlmeier. 2018a. Effective attention modeling for aspect-level sentiment classification. In Proceedings of the 27th International Conference on Computational Linguistics, COLING 2018, Santa Fe, New Mexico, USA, August 20-26, 2018, pages 1121– 1131. [find](https://scholar.google.com/scholar?q=Ruidan+He%2C+Wee+Sun+Lee%2C+Hwee+Tou+Ng%2C+and+Daniel+Dahlmeier%2E+2018a%2E+Effective+attention+modeling+for+aspect%2Dlevel+sentiment+classification%2E+In+Proceedings+of+the+27th+International+Conference+on+Computa)
9. Ruidan He, Wee Sun Lee, Hwee Tou Ng, and Daniel Dahlmeier. 2018b. Exploiting document knowledge for aspect-level sentiment classification. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics, ACL 2018, Melbourne, Australia, July 15-20, 2018, Volume 2: Short Pap… [find](https://scholar.google.com/scholar?q=Ruidan+He%2C+Wee+Sun+Lee%2C+Hwee+Tou+Ng%2C+and+Daniel+Dahlmeier%2E+2018b%2E+Exploiting+document+knowledge+for+aspect%2Dlevel+sentiment+classification%2E+In+Proceedings+of+the+56th+Annual+Meeting+of+the+Association+)
10. Minqing Hu and Bing Liu. 2004. Mining and summarizing customer reviews. In Proceedings of the tenth ACM SIGKDD international conference on Knowledge discovery and data mining, pages 168–177. [find](https://scholar.google.com/scholar?q=Minqing+Hu+and+Bing+Liu%2E+2004%2E+Mining+and+summarizing+customer+reviews%2E+In+Proceedings+of+the+tenth+ACM+SIGKDD+international+conference+on+Knowledge+discovery+and+data+mining%2C+pages+168%E2%80%93177%2E)
11. Binxuan Huang and Kathleen Carley. 2018. Parameterized convolutional neural networks for aspect level sentiment classification. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 1091–1096. [find](https://scholar.google.com/scholar?q=Binxuan+Huang+and+Kathleen+Carley%2E+2018%2E+Parameterized+convolutional+neural+networks+for+aspect+level+sentiment+classification%2E+In+Proceedings+of+the+2018+Conference+on+Empirical+Methods+in+Natural+La)
12. Thomas N Kipf and Max Welling. 2016. Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907. [find](https://scholar.google.com/scholar?q=Thomas+N+Kipf+and+Max+Welling%2E+2016%2E+Semi%2Dsupervised+classification+with+graph+convolutional+networks%2E+arXiv+preprint+arXiv%3A1609%2E02907%2E) [our card](https://md.research.elamur.ai/free/en/papers/kipf-2016-semi-supervised-classification-graph-convolutional/)
13. Fanshuang Kong, Richong Zhang, Hongyu Guo, Samuel Mensah, Zhiyuan Hu, and Yongyi Mao. 2019. A neural bag-of-words modelling framework for link prediction in knowledge bases with sparse connectivity. In WWW 2019 : The Web Conference. [find](https://scholar.google.com/scholar?q=Fanshuang+Kong%2C+Richong+Zhang%2C+Hongyu+Guo%2C+Samuel+Mensah%2C+Zhiyuan+Hu%2C+and+Yongyi+Mao%2E+2019%2E+A+neural+bag%2Dof%2Dwords+modelling+framework+for+link+prediction+in+knowledge+bases+with+sparse+connectivity%2E+I)
14. Zeyang Lei, Yujiu Yang, Min Yang, Wei Zhao, Jun Guo, and Yi Liu. 2019. A human-like semantic cognition network for aspect-level sentiment classification. AAAI. [find](https://scholar.google.com/scholar?q=Zeyang+Lei%2C+Yujiu+Yang%2C+Min+Yang%2C+Wei+Zhao%2C+Jun+Guo%2C+and+Yi+Liu%2E+2019%2E+A+human%2Dlike+semantic+cognition+network+for+aspect%2Dlevel+sentiment+classification%2E+AAAI%2E)
15. Xin Li, Lidong Bing, Wai Lam, and Bei Shi. 2018a. Transformation networks for target-oriented sentiment classification. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics, ACL 2018, Melbourne, Australia, July 15-20, 2018, Volume 1: Long Papers, pages 946– 956. [find](https://scholar.google.com/scholar?q=Xin+Li%2C+Lidong+Bing%2C+Wai+Lam%2C+and+Bei+Shi%2E+2018a%2E+Transformation+networks+for+target%2Doriented+sentiment+classification%2E+In+Proceedings+of+the+56th+Annual+Meeting+of+the+Association+for+Computational+L) [our card](https://md.research.elamur.ai/free/en/papers/li-2018-transformation-networks-target-oriented-sentiment/)
16. Zheng Li, Ying Wei, Yu Zhang, Xiang Zhang, Xin Li, and Qiang Yang. 2018b. Exploiting coarse-to-fine task transfer for aspect-level sentiment classification. CoRR, abs/1811.10999. — [arXiv:1811.10999](https://arxiv.org/abs/1811.10999) [find](https://scholar.google.com/scholar?q=Zheng+Li%2C+Ying+Wei%2C+Yu+Zhang%2C+Xiang+Zhang%2C+Xin+Li%2C+and+Qiang+Yang%2E+2018b%2E+Exploiting+coarse%2Dto%2Dfine+task+transfer+for+aspect%2Dlevel+sentiment+classification%2E+CoRR%2C+abs%2F1811%2E10999%2E+%E2%80%94+%5BarXiv%3A1811%2E10999%5D%28)
17. Navonil Majumder, Soujanya Poria, Alexander Gelbukh, Md Shad Akhtar, Erik Cambria, and Asif Ekbal. 2018. Iarm: Inter-aspect relation modeling with memory networks in aspect-based sentiment analysis. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 3402… [find](https://scholar.google.com/scholar?q=Navonil+Majumder%2C+Soujanya+Poria%2C+Alexander+Gelbukh%2C+Md+Shad+Akhtar%2C+Erik+Cambria%2C+and+Asif+Ekbal%2E+2018%2E+Iarm%3A+Inter%2Daspect+relation+modeling+with+memory+networks+in+aspect%2Dbased+sentiment+analysis%2E+I)
18. Diego Marcheggiani and Ivan Titov. 2017. Encoding sentences with graph convolutional networks for semantic role labeling. arXiv preprint arXiv:1703.04826. [find](https://scholar.google.com/scholar?q=Diego+Marcheggiani+and+Ivan+Titov%2E+2017%2E+Encoding+sentences+with+graph+convolutional+networks+for+semantic+role+labeling%2E+arXiv+preprint+arXiv%3A1703%2E04826%2E) [our card](https://md.research.elamur.ai/free/en/papers/marcheggiani-2017-encoding-sentences-graph-convolutional-networks/)
19. Lili Mou, Hao Peng, Ge Li, Yan Xu, Lu Zhang, and Zhi Jin. 2015. Discriminative neural sentence modeling by tree-based convolution. arXiv preprint arXiv:1504.01106. [find](https://scholar.google.com/scholar?q=Lili+Mou%2C+Hao+Peng%2C+Ge+Li%2C+Yan+Xu%2C+Lu+Zhang%2C+and+Zhi+Jin%2E+2015%2E+Discriminative+neural+sentence+modeling+by+tree%2Dbased+convolution%2E+arXiv+preprint+arXiv%3A1504%2E01106%2E)
20. Zhifan Ouyang and Jindian Su. 2018. Dependency parsing and attention network for aspect-level sentiment classification. In CCF International Conference on Natural Language Processing and Chinese Computing, pages 391–403. [find](https://scholar.google.com/scholar?q=Zhifan+Ouyang+and+Jindian+Su%2E+2018%2E+Dependency+parsing+and+attention+network+for+aspect%2Dlevel+sentiment+classification%2E+In+CCF+International+Conference+on+Natural+Language+Processing+and+Chinese+Compu)
21. Jeffrey Pennington, Richard Socher, and Christopher Manning. 2014. Glove: Global vectors for word representation. In Proceedings of the 2014 conference on empirical methods in natural language processing (EMNLP), pages 1532–1543. [find](https://scholar.google.com/scholar?q=Jeffrey+Pennington%2C+Richard+Socher%2C+and+Christopher+Manning%2E+2014%2E+Glove%3A+Global+vectors+for+word+representation%2E+In+Proceedings+of+the+2014+conference+on+empirical+methods+in+natural+language+process)
22. Maria Pontiki, Dimitris Galanis, John Pavlopoulos, Harris Papageorgiou, Ion Androutsopoulos, and Suresh Manandhar. 2014. Semeval-2014 task 4: Aspect based sentiment analysis. In Proceedings of the 8th International Workshop on Semantic Evaluation (SemEval 2014), pages 27–35. [find](https://scholar.google.com/scholar?q=Maria+Pontiki%2C+Dimitris+Galanis%2C+John+Pavlopoulos%2C+Harris+Papageorgiou%2C+Ion+Androutsopoulos%2C+and+Suresh+Manandhar%2E+2014%2E+Semeval%2D2014+task+4%3A+Aspect+based+sentiment+analysis%2E+In+Proceedings+of+the+8th) [our card](https://md.research.elamur.ai/free/en/papers/pontiki-2014-semeval-2014-task-4-aspect/)
23. Ana Maria Popescu and Orena Etzioni. 2005. Extracting product features and opinions from reviews. In Proceedings of Human Language Technology Conference and Conference on Empirical Methods in Natural Language Processing, pages 339–346. [find](https://scholar.google.com/scholar?q=Ana+Maria+Popescu+and+Orena+Etzioni%2E+2005%2E+Extracting+product+features+and+opinions+from+reviews%2E+In+Proceedings+of+Human+Language+Technology+Conference+and+Conference+on+Empirical+Methods+in+Natural+) [our card](https://md.research.elamur.ai/free/en/papers/popescu-2005-extracting-product-features-opinions-reviews/)
24. Shiliang Zheng and Rui Xia. 2018. Left-center-right separated neural network for aspect-based sentiment analysis with rotatory attention. arXiv preprint arXiv:1802.00892. — [arXiv:1802.00892](https://arxiv.org/abs/1802.00892) [find](https://scholar.google.com/scholar?q=Shiliang+Zheng+and+Rui+Xia%2E+2018%2E+Left%2Dcenter%2Dright+separated+neural+network+for+aspect%2Dbased+sentiment+analysis+with+rotatory+attention%2E+arXiv+preprint+arXiv%3A1802%2E00892%2E+%E2%80%94+%5BarXiv%3A1802%2E00892%5D%28https%3A%2F%2F)
25. Marinka Zitnik, Monica Agrawal, and Jure Leskovec. 2018. Modeling polypharmacy side effects with graph convolutional networks. Bioinformatics, 34(13):i457–i466. [find](https://scholar.google.com/scholar?q=Marinka+Zitnik%2C+Monica+Agrawal%2C+and+Jure+Leskovec%2E+2018%2E+Modeling+polypharmacy+side+effects+with+graph+convolutional+networks%2E+Bioinformatics%2C+34%2813%29%3Ai457%E2%80%93i466%2E)
26. Michael Schlichtkrull, Thomas N Kipf, Peter Bloem, Rianne Van Den Berg, Ivan Titov, and Max Welling. 2018. Modeling relational data with graph convolutional networks. In European Semantic Web Conference, pages 593–607. Springer. [find](https://scholar.google.com/scholar?q=Michael+Schlichtkrull%2C+Thomas+N+Kipf%2C+Peter+Bloem%2C+Rianne+Van+Den+Berg%2C+Ivan+Titov%2C+and+Max+Welling%2E+2018%2E+Modeling+relational+data+with+graph+convolutional+networks%2E+In+European+Semantic+Web+Conferen)
27. Kim Schouten and Flavius Frasincar. 2015. Survey on aspect-level sentiment analysis. IEEE Transactions on Knowledge and Data Engineering, 28(3):813– 830. [find](https://scholar.google.com/scholar?q=Kim+Schouten+and+Flavius+Frasincar%2E+2015%2E+Survey+on+aspect%2Dlevel+sentiment+analysis%2E+IEEE+Transactions+on+Knowledge+and+Data+Engineering%2C+28%283%29%3A813%E2%80%93+830%2E)
28. Kai Sheng Tai, Richard Socher, and Christopher D Manning. 2015. Improved semantic representations from tree-structured long short-term memory networks. arXiv preprint arXiv:1503.00075. [find](https://scholar.google.com/scholar?q=Kai+Sheng+Tai%2C+Richard+Socher%2C+and+Christopher+D+Manning%2E+2015%2E+Improved+semantic+representations+from+tree%2Dstructured+long+short%2Dterm+memory+networks%2E+arXiv+preprint+arXiv%3A1503%2E00075%2E)
29. Duyu Tang, Bing Qin, and Ting Liu. 2015. Document modeling with gated recurrent neural network for sentiment classification. In Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, pages 1422–1432. [find](https://scholar.google.com/scholar?q=Duyu+Tang%2C+Bing+Qin%2C+and+Ting+Liu%2E+2015%2E+Document+modeling+with+gated+recurrent+neural+network+for+sentiment+classification%2E+In+Proceedings+of+the+2015+Conference+on+Empirical+Methods+in+Natural+Langu) [our card](https://md.research.elamur.ai/free/en/papers/tang-2015-document-modeling-gated-recurrent-neural/)
30. Bailin Wang and Wei Lu. 2018. Learning latent opinions for aspect-level sentiment classification. In Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence, (AAAI-18), the 30th innovative Applications of Artificial Intelligence (IAAI-18), and the 8th AAAI Symposium on Educationa… [find](https://scholar.google.com/scholar?q=Bailin+Wang+and+Wei+Lu%2E+2018%2E+Learning+latent+opinions+for+aspect%2Dlevel+sentiment+classification%2E+In+Proceedings+of+the+Thirty%2DSecond+AAAI+Conference+on+Artificial+Intelligence%2C+%28AAAI%2D18%29%2C+the+30th+in)
31. Yanyan Wang, Qun Chen, Xin Liu, Murtadha H. M. Ahmed, Zhanhuai Li, Wei Pan, and Hailong Liu. 2018. Senhint: A joint framework for aspect-level sentiment analysis by deep neural networks and linguistic hints. In WWW ’18 Companion Proceedings of the The Web Conference 2018, pages 207–210. [find](https://scholar.google.com/scholar?q=Yanyan+Wang%2C+Qun+Chen%2C+Xin+Liu%2C+Murtadha+H%2E+M%2E+Ahmed%2C+Zhanhuai+Li%2C+Wei+Pan%2C+and+Hailong+Liu%2E+2018%2E+Senhint%3A+A+joint+framework+for+aspect%2Dlevel+sentiment+analysis+by+deep+neural+networks+and+linguistic)
32. Yequan Wang, Minlie Huang, xiaoyan zhu, and Li Zhao. 2016. Attention-based lstm for aspect-level sentiment classification. In Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, pages 606–615. [find](https://scholar.google.com/scholar?q=Yequan+Wang%2C+Minlie+Huang%2C+xiaoyan+zhu%2C+and+Li+Zhao%2E+2016%2E+Attention%2Dbased+lstm+for+aspect%2Dlevel+sentiment+classification%2E+In+Proceedings+of+the+2016+Conference+on+Empirical+Methods+in+Natural+Languag) [our card](https://md.research.elamur.ai/free/en/papers/wang-2016-attention-based-lstm-aspect-level/)
33. Wei Xue and Tao Li. 2018. Aspect based sentiment analysis with gated convolutional networks. arXiv preprint arXiv:1805.07043. [find](https://scholar.google.com/scholar?q=Wei+Xue+and+Tao+Li%2E+2018%2E+Aspect+based+sentiment+analysis+with+gated+convolutional+networks%2E+arXiv+preprint+arXiv%3A1805%2E07043%2E)
34. Yuhao Zhang, Peng Qi, and Christopher D. Manning. 2018. Graph convolution over pruned dependency trees improves relation extraction. empirical methods in natural language processing, pages 2205– 2215. [find](https://scholar.google.com/scholar?q=Yuhao+Zhang%2C+Peng+Qi%2C+and+Christopher+D%2E+Manning%2E+2018%2E+Graph+convolution+over+pruned+dependency+trees+improves+relation+extraction%2E+empirical+methods+in+natural+language+processing%2C+pages+2205%E2%80%93+2215%2E) [our card](https://md.research.elamur.ai/free/en/papers/zhang-2018-graph-convolution-over-pruned-dependency/)