由於近年來使用者社交網絡或新聞創建的用戶生成的內容（UGC）資料上升快速，並且具有極高的價值，可以為公司的決策提供大量有價值的信息。為了深入研究UGC，基於構面的情感分析（ABSA）可以對與句子中各個構面的情緒（負面，中性或正面）進行分類。在本篇論文中，我們提出了一個ASBA整合模型。我們的方法包括三個步驟。第一步，我們使用基於構面的多種子自動編碼器（MATE）模型提取句子中的構面。然後，我們使用圖卷積網絡(GCN)來擴充情感詞典。最後，我們匯總從前兩個步驟學到的構面資訊和情感詞典，以確定給定句子的構面和情感。我們對金融新聞數據集進行了實驗，實驗結果表明，我們提出的模型優於其他比較方法。

Due to explosion of user-generated content(UGC) data, that was created by user on online platforms such as microblogs, social networks and news, it can provide a lot of valuable information for the company decision making. In order to dig into the UGC, Aspect-based sentiment analysis (ABSA) can classify the sentiment polarity (i.e., negative, neutral, or positive) pertaining to a certain aspect in a sentence. For instance, this sentence “The battery life is short”, “Battery life” is the aspect term and “short” is the sentiment term. The aspect “battery” is positive in this sentence. In this paper, we propose an ASBA integrated model in the finance domain. Three steps in our method. First, we extract aspect in the sentence using Multi-seed Aspect-Based Autoencoder (MATE) model. Secondly, we employ graph convolutional network to populate the sentiment lexicons. Finally, we aggregate the aspect information and the sentiment lexicons learned from the previous two steps to determine the aspect and sentiment of a given sentence. We conduct experiments on financial news datasets and The experimental results show that our proposed model outperforms the other compared methods.

CHAPTER 1 - Introduction 1
1.1 Background and Motivation 1
1.2 Contribution 2
1.3 Thesis Organization 3
CHAPTER 2 – Related Work 4
2.1 Aspect Classification 4
2.2 Aspect-based Sentiment Analysis 5
2.3 Financial Text Sentiment Analysis 7
CHAPTER 3 – Methodology 8
3.1 Task description 9
3.2 Aspect classification 10
3.3 Sentiment Lexicon Construction 12
3.4 sentiment sentence tagging 15
CHAPTER 4 – Experiment 18
4.1 Dataset 18
4.2 Experiment setting 18
4.3 Evaluation 19
4.3.1 Aspect classification method 19
4.3.2 sentiment lexicon between aspects 21
4.3.3 sentence-level sentiment lexicon tagging 24
CHAPTER 5 – Conclusion 25
References 25

Angelidis, S., & Lapata, M. (2018). Summarizing Opinions: Aspect Extraction Meets Sentiment Prediction and They Are Both Weakly Supervised. ArXiv:1808.08858 [Cs]. http://arxiv.org/abs/1808.08858
Brody, S., & Elhadad, N. (2010). An Unsupervised Aspect-Sentiment Model for Online Reviews. HLT-NAACL.
Chen, P., Sun, Z., Bing, L., & Yang, W. (2017). Recurrent Attention Network on Memory for Aspect Sentiment Analysis. Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, 452–461. https://doi.org/10.18653/v1/D17-1047
Chen, Z., Mukherjee, A., & Liu, B. (2014). Aspect Extraction with Automated Prior Knowledge Learning. Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 347–358. https://doi.org/10.3115/v1/P14-1033
Ding, X., Liu, B., & Yu, P. S. (2008). A holistic lexicon-based approach to opinion mining. Proceedings of the International Conference on Web Search and Web Data Mining - WSDM ’08, 231. https://doi.org/10.1145/1341531.1341561
Fan, Z., Wu, Z., Dai, X.-Y., Huang, S., & Chen, J. (2019). Target-oriented Opinion Words Extraction with Target-fused Neural Sequence Labeling. Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), 2509–2518. https://doi.org/10.18653/v1/N19-1259
García-Pablos, A., Cuadros, M., & Rigau, G. (2018). W2VLDA: Almost unsupervised system for Aspect Based Sentiment Analysis. Expert Systems with Applications, 91, 127–137. https://doi.org/10.1016/j.eswa.2017.08.049
He, R., Lee, W. S., Ng, H. T., & Dahlmeier, D. (2017). An Unsupervised Neural Attention Model for Aspect Extraction. Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 388–397. https://doi.org/10.18653/v1/P17-1036
Hu, M., & Liu, B. (2004). Mining and Summarizing Customer Reviews. Proceedings of the Tenth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 168–177. https://doi.org/10.1145/1014052.1014073
Jakob, N., & Gurevych, I. (2010). Extracting Opinion Targets in a Single and Cross-Domain Setting with Conditional Random Fields. Proceedings of the 2010 Conference on Empirical Methods in Natural Language Processing, 1035–1045. https://www.aclweb.org/anthology/D10-1101
Ji, Y., Shi, C., Zhuang, F., & Yu, P. S. (2019). Integrating Topic Model and Heterogeneous Information Network for Aspect Mining with Rating Bias. In Q. Yang, Z.-H. Zhou, Z. Gong, M.-L. Zhang, & S.-J. Huang (Eds.), Advances in Knowledge Discovery and Data Mining (pp. 160–171). Springer International Publishing. https://doi.org/10.1007/978-3-030-16148-4_13
Jo, Y. (n.d.). 2011. Aspect and sentiment unification model for online review analysis. In Proceedings of the 4th International Conference of WSDM, 815–824.
Kazemian, S., Zhao, S., & Penn, G. (2016). Evaluating Sentiment Analysis in the Context of Securities Trading. Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2094–2103. https://doi.org/10.18653/v1/P16-1197
Kipf, T. N., & Welling, M. (2017). Semi-Supervised Classification with Graph Convolutional Networks. ArXiv:1609.02907 [Cs, Stat]. http://arxiv.org/abs/1609.02907
Klinger, R., & Cimiano, P. (2013). Joint and Pipeline Probabilistic Models for Fine-Grained Sentiment Analysis: Extracting Aspects, Subjective Phrases and their Relations. 2013 IEEE 13th International Conference on Data Mining Workshops, 937–944. https://doi.org/10.1109/ICDMW.2013.13
Lazaridou, A., Titov, I., & Sporleder, C. (2013). A Bayesian Model for Joint Unsupervised Induction of Sentiment, Aspect and Discourse Representations. Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 1630–1639. https://www.aclweb.org/anthology/P13-1160
Li, X., Bing, L., Lam, W., & Shi, B. (2018). Transformation Networks for Target-Oriented Sentiment Classification. Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 946–956. https://doi.org/10.18653/v1/P18-1087
Ma, D., Li, S., Zhang, X., & Wang, H. (2017). Interactive Attention Networks for Aspect-Level Sentiment Classification. Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence, 4068–4074. https://doi.org/10.24963/ijcai.2017/568
Nopp, C., & Hanbury, A. (2015). Detecting Risks in the Banking System by Sentiment Analysis. Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, 591–600. https://doi.org/10.18653/v1/D15-1071
Popescu, A.-M., & Etzioni, O. (2005). Extracting Product Features and Opinions from Reviews. Proceedings of the Conference on Human Language Technology and Empirical Methods in Natural Language Processing, 339–346. https://doi.org/10.3115/1220575.1220618
Qiu, G., Liu, B., Bu, J., & Chen, C. (2011). Opinion Word Expansion and Target Extraction through Double Propagation. Computational Linguistics, 37, 9–27. https://doi.org/10.1162/coli_a_00034
Rekabsaz, N., Lupu, M., Baklanov, A., Dür, A., Andersson, L., & Hanbury, A. (2017). Volatility Prediction using Financial Disclosures Sentiments with Word Embedding-based IR Models. Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 1712–1721. https://doi.org/10.18653/v1/P17-1157
Scaffidi, C., Bierhoff, K., Chang, E., Felker, M., Ng, H., & Jin, C. (2007). Red Opal: Product-feature scoring from reviews. Proceedings of the 8th ACM Conference on Electronic Commerce - EC ’07, 182. https://doi.org/10.1145/1250910.1250938
Shu, L., Xu, H., & Liu, B. (2017). Lifelong Learning CRF for Supervised Aspect Extraction.
Sun, C., Huang, L., & Qiu, X. (2019). Utilizing BERT for Aspect-Based Sentiment Analysis via Constructing Auxiliary Sentence. Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), 380–385. https://doi.org/10.18653/v1/N19-1035
Tang, J., Lu, Z., Su, J., Ge, Y., Song, L., Sun, L., & Luo, J. (2019). Progressive Self-Supervised Attention Learning for Aspect-Level Sentiment Analysis. Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, 557–566. https://doi.org/10.18653/v1/P19-1053
Zhao, W. X., Jiang, J., Yan, H., & Li, X. (n.d.). Jointly modeling aspects and opinions with a MaxEnt-LDA hybrid. 10.