由於近年來由社交網路使用者所產生的用戶生成內容(UGC)資料快速增加，如何快速且正確的處理這些資料已成為一個重要課題。為了妥善利用UGC，基於文本構面的情感分析(ABSA)被用來提取句子中提到的構面與情緒，以更準確的掌握構面和構面上的情緒。
在本篇論文中，我們提出一個ABSA的整合模型，透過引入文本圖卷積網路(Text GCN)，來加強模型之效能。模型一共分為以下三個步驟，第一步，使用多種子構面提取器(MATE)模型來提取句子的構面。接者，使用文本之圖卷積網路來根據第一步驟提取的構面，產生各構面的情緒種子詞。最後，將產生的種子詞帶入我們提出的特定構面情緒自動編碼器(ASSA)，來對輸入的句子同步進行構面與此構面上情緒的提取。根據對餐廳與筆記型電腦兩種類型資料集的測試，我們的方法與單純使用通用情緒詞的方法相比較，在情緒分類的準確率上皆有更佳的表現。

Due to the rapid increase in User-Generated Content (UGC) data, how to process those data quickly and correctly has become an important topic. To dig into the UGC, Aspect-Based Sentiment Analysis (ABSA) is used to extract the aspect and sentiment mentioned in sentences.
In this thesis, we propose an integrated ABSA model to improve the performance by incorporating Text Graph Convolutional Network (Text GCN). The model is divided into three steps. In the first step, the Multi-Seed Aspect Extractor (MATE) model is used to extract the aspect of the sentence. Then, the Text GCN is used to generate aspect-specific sentiment seed words according to the aspect extracted in the first step. Finally, the generated seed words are fed into the aspect-specific sentiment autoencoder (ASSA) to extract the aspect and the corresponding sentiment of the given sentence. We conduct experiments on the restaurant and laptop datasets. Experimental results show that our proposed approach has better performance in sentiment classification when compared the previous work which simply used general sentiment seed words.

論文審定書 i
誌 謝 ii
摘 要 iii
Abstract iv
Table of Contents v
List of Figures vi
List of Tables vii
CHAPTER 1 - Introduction 1
CHAPTER 2 - Related Work 5
2.1 Aspect Extraction 5
2.2 Sentiment Prediction 7
2.3 Aspect-based Sentiment Analysis 8
CHAPTER 3 - Methodology 10
3.1 Notation Description 11
3.2 Aspect Extraction 12
3.3 Aspect-based Sentiment Words Generation 15
3.4 Aspect Sentiment Detection 19
CHAPTER 4 – Experiments 22
4.1 Datasets 22
4.2 Parameter Setting 24
4.3 Four Evaluation Metrics 26
4.4 Results 27
CHAPTER 5 – Conclusion 34
References 35

Angelidis, S., & Lapata, M. (2018). Summarizing Opinions: Aspect Extraction Meets Sentiment Prediction and They Are Both Weakly Supervised. Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, 3675–3686. https://doi.org/10.18653/v1/D18-1403
Brody, S., & Elhadad, N. (2010). An unsupervised aspect-sentiment model for online reviews. Human Language Technologies: The 2010 Annual Conference of the North American Chapter of the Association for Computational Linguistics, 804–812.
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
Choi, Y., & Cardie, C. (2009). Adapting a polarity lexicon using integer linear programming for domain-specific sentiment classification. Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing Volume 2 - EMNLP ’09, 2, 590. https://doi.org/10.3115/1699571.1699590
Dong, L., Wei, F., Tan, C., Tang, D., Zhou, M., & Xu, K. (2014). Adaptive Recursive Neural Network for Target-dependent Twitter Sentiment Classification. Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), 49–54. https://doi.org/10.3115/v1/P14-2009
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
He, R., & McAuley, J. (2016). Ups and Downs: Modeling the Visual Evolution of Fashion Trends with One-Class Collaborative Filtering. Proceedings of the 25th International Conference on World Wide Web, 507–517. https://doi.org/10.1145/2872427.2883037
Hu, M., & Liu, B. (2004). Mining and summarizing customer reviews. Proceedings of the 2004 ACM SIGKDD International Conference on Knowledge Discovery and Data Mining - KDD ’04, 168. 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
Jo, Y., & Oh, A. H. (2011). Aspect and sentiment unification model for online review analysis. Proceedings of the Fourth ACM International Conference on Web Search and Data Mining, 815–824. https://doi.org/10.1145/1935826.1935932
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. 946–956. https://doi.org/10.18653/v1/P18-1087
Ma, D., Li, S., & Wang, H. (2018). Joint Learning for Targeted Sentiment Analysis. Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, 4737–4742. https://doi.org/10.18653/v1/D18-1504
Ma, D., Li, S., Zhang, X., & Wang, H. (2017). Interactive Attention Networks for Aspect-Level Sentiment Classification. ArXiv:1709.00893 [Cs]. http://arxiv.org/abs/1709.00893
McAuley, J., Targett, C., Shi, Q., & van den Hengel, A. (2015). Image-Based Recommendations on Styles and Substitutes. Proceedings of the 38th International ACM SIGIR Conference on Research and Development in Information Retrieval, 43–52. https://doi.org/10.1145/2766462.2767755
Mei, Q., Ling, X., Wondra, M., Su, H., & Zhai, C. (2007). Topic sentiment mixture: Modeling facets and opinions in weblogs. Proceedings of the 16th International Conference on World Wide Web, 171–180. https://doi.org/10.1145/1242572.1242596
Pontiki, M., Galanis, D., Papageorgiou, H., Androutsopoulos, I., Manandhar, S., AL-Smadi, M., Al-Ayyoub, M., Zhao, Y., Qin, B., De Clercq, O., Hoste, V., Apidianaki, M., Tannier, X., Loukachevitch, N., Kotelnikov, E., Bel, N., Jiménez-Zafra, S. M., & Eryiğit, G. (2016). SemEval-2016 Task 5: Aspect Based Sentiment Analysis. Proceedings of the 10th International Workshop on Semantic Evaluation (SemEval-2016), 19–30. https://doi.org/10.18653/v1/S16-1002
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(1), 9–27. https://doi.org/10.1162/coli_a_00034
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. ArXiv:1705.00251 [Cs]. http://arxiv.org/abs/1705.00251
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. 557–566. https://doi.org/10.18653/v1/P19-1053
Wang, H., Lu, Y., & Zhai, C. (2010). Latent aspect rating analysis on review text data: A rating regression approach. Proceedings of the 16th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 783–792. https://doi.org/10.1145/1835804.1835903
Xue, W., & Li, T. (2018). Aspect Based Sentiment Analysis with Gated Convolutional Networks. Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2514–2523. https://doi.org/10.18653/v1/P18-1234
Yao, L., Mao, C., & Luo, Y. (2018). Graph Convolutional Networks for Text Classification. ArXiv:1809.05679 [Cs]. http://arxiv.org/abs/1809.05679
Zhang, L., Liu, B., Lim, S. H., & O’Brien-Strain, E. (2010). Extracting and ranking product features in opinion documents. Proceedings of the 23rd International Conference on Computational Linguistics: Posters, 1462–1470.
Zhao, Y., Qin, B., Hu, S., & Liu, T. (2010). Generalizing Syntactic Structures for Product Attribute Candidate Extraction. Human Language Technologies: The 2010 Annual Conference of the North American Chapter of the Association for Computational Linguistics, 377–380. https://www.aclweb.org/anthology/N10-1059
Zhuang, H., Guo, F., Zhang, C., Liu, L., & Han, J. (2020). Joint Aspect-Sentiment Analysis with Minimal User Guidance. Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval, 1241–1250. https://doi.org/10.1145/3397271.3401179
Zhuang, H., Hanratty, T., & Har, J. (2019). Aspect-Based Sentiment Analysis with Minimal Guidance. In Proceedings of the 2019 SIAM International Conference on Data Mining (Vol. 1–0, pp. 253–261). Society for Industrial and Applied Mathematics. https://doi.org/10.1137/1.9781611975673.29