Aspect-based Sentiment Analysis based on Graph Convolutional Network

Bo He; Hongqian Zhang; Hao Han; Yunfei Chen

doi:10.62051/ijcsit.v6n3.04

Authors

Bo He
Hongqian Zhang
Hao Han
Yunfei Chen

DOI:

https://doi.org/10.62051/ijcsit.v6n3.04

Keywords:

Aspect-Based Sentiment Analysis, Sentiment Dictionary, Machine Learning, Deep Learning, Graph Convolutional Networks

Abstract

Aspect-based sentiment analysis (ABSA), a critical task in the field of natural language processing, aims to identify and analyze the sentiment orientation towards specific aspects within texts. In recent years, Graph Convolutional Networks (GCN), as a potent type of graph neural network, have demonstrated unique advantages in handling graph-structured data, offering new perspectives and methods for ABSA. In this paper, we provide an overview of the research progress in graph convolution-based ABSA methods. Initially, it introduces three pivotal methods in the ABSA domain, encompassing representative work based on dictionaries, machine learning, and deep learning, while analyzing their strengths and limitations. Subsequently, it elaborates on graph convolution-based ABSA methods, highlighting existing problems and challenges in current research. Finally, we further explore future research directions for ABSA, particularly in achieving more accurate analyses of nuanced emotional expressions within textual content.

Downloads

Download data is not yet available.

References

[1] Degardin, B., Neves, J., Lopes, V., Brito, J., Yaghoubi, E., Proença, H., 2021. Generative Adversarial Graph Convolutional Networks for Human Action Synthesis.

[2] Discrete Opinion Tree Induction for Aspect-based Sentiment Analysis - ACL Anthology [WWW Document], n.d.

[3] Graph Attention Networks over Edge Content-Based Channels | Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining [WWW Document], n.d.

[4] Hu, M., Liu, B., 2004. Mining and summarizing customer reviews, in: Proceedings of the Tenth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD ’04. Association for Computing Machinery, New York, NY, USA, pp. 168–177.

[5] Huang, B., Carley, K.M., 2019. Syntax-Aware Aspect Level Sentiment Classification with Graph Attention Networks.

[6] Jia, K., Li, Z., 2020. Chinese Micro-Blog Sentiment Classification Based on Emotion Dictionary and Semantic Rules, in: 2020 International Conference on Computer Information and Big Data Applications (CIBDA). Presented at the 2020 International Conference on Computer Information and Big Data Applications (CIBDA), pp. 309–312.

[7] Jo, Y., Oh, A.H., 2011. Aspect and sentiment unification model for online review analysis, in: Proceedings of the Fourth ACM International Conference on Web Search and Data Mining, WSDM ’11. Association for Computing Machinery, New York, NY, USA, pp. 815–824.

[8] Kipf, T.N., Welling, M., 2017. Semi-Supervised Classification with Graph Convolutional Networks.

[9] Koncel-Kedziorski, R., Bekal, D., Luan, Y., Lapata, M., Hajishirzi, H., 2022. Text Generation from Knowledge Graphs with Graph Transformers.

[10] Kumar, A., Gupta, P., Balan, R., Neti, L.B.M., Malapati, A., 2021. BERT Based Semi-Supervised Hybrid Approach for Aspect and Sentiment Classification. Neural Process Lett 53, 4207–4224.

[11] Li, N., Chow, C.-Y., Zhang, J.-D., 2020. SEML: A Semi-Supervised Multi-Task Learning Framework for Aspect-Based Sentiment Analysis. IEEE Access 8, 189287–189297.

[12] Liang, B., Su, H., Gui, L., Cambria, E., Xu, R., 2022. Aspect-based sentiment analysis via affective knowledge enhanced graph convolutional networks. Knowledge-Based Systems 235, 107643.

[13] Liang, S., Wei, W., Mao, X.-L., Wang, F., He, Z., 2022. BiSyn-GAT+: Bi-Syntax Aware Graph Attention Network for Aspect-based Sentiment Analysis, in: Muresan, S., Nakov, P., Villavicencio, A. (Eds.), Findings of the Association for Computational Linguistics: ACL 2022. Presented at the Findings 2022, Association for Computational Linguistics, Dublin, Ireland, pp. 1835–1848.

[14] Ma, D., Li, S., Zhang, X., Wang, H., 2017. Interactive Attention Networks for Aspect-Level Sentiment Classification.

[15] Nguyen, T.H., Shirai, K., 2015. PhraseRNN: Phrase Recursive Neural Network for Aspect-based Sentiment Analysis, in: Màrquez, L., Callison-Burch, C., Su, J. (Eds.), Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing. Presented at the EMNLP 2015, Association for Computational Linguistics, Lisbon, Portugal, pp. 2509–2514.