隨著網路網路的普及與網路2.0的時代來臨，越來越多使用者傾向在網路上留下評價，是商家掌握市場動向的重要來源，但如果想檢視⽂本中細部的構面與正負面評價，⼈⼯檢視往往要耗費⾼昂的成本，構面和情緒分開自動提取則犧牲精確度。這也使得基於構面的情緒提取技術（ABSA）變的越來越重要。本研究應用領域與情緒的複合學習模型，在不需要標註訓練資料類別的情況下，僅需要提供構面與⼀般情緒的關鍵字，即能以弱監督學習（weakly supervised learning）的⽅式，利用自動編碼器模型（autoencoder）預測出⽂本的構面與情緒分類。
我們基於Tsai et al. (2022) 提出的ABSA整合模型，提出新的流程框架ASSATG，精簡並改進構面情緒關鍵字的⽣成流程。過去建構⽂本卷積網路（GraphConvolutional Networks）時，往往只考慮到⽂本字詞間的順序關係，⽽忽略其他更為深層的資訊，在此利用張量卷積網路（TensorGCN），在萃取各構面的情緒關鍵字時，另外考慮字詞相依（dependency relation）、語意相似度（semantic similarity）等字詞關係，提升情緒關鍵字的質量，以獲得更準確的預測結果。

With the advent of the Internet 2.0, more and more users tend to provide comments on the Internet, which is an important source for businesses to grasp market trends. However, manually extracting the aspect and sentiment of these User-Generated Content data is extremely costly, and deriving aspect and sentiment separately compromises accuracy, thereby making aspect-based sentiment analysis (ABSA) techniques more and more important.

Based on the ABSA approach proposed by (Tsai et al., 2022), we propose a new framework called ASSA-TG, which improves the generation process of aspect-specific sentiment seeds. The original method only considers sequential relations between words. In our approach, TensorGCN is used to extract dependency relation and semantic similarity information to improve the quality of generated keywords.

The experiment result shows that our method can improve the quality of the sentiment seeds and guide the autoencoder to achieve better performance.

論文審定書i
誌謝 ii
摘要iii
Abstractiv
Table of Contentv
CHAPTER 1 – Introduction1
CHAPTER 2 – Related work4
2.1 Aspect Extraction4
2.2 Joint Aspect and Polarity Classification5
2.3 GCN for classification task8
CHAPTER 3 – Our Method10
3.1 ASSA for Aspect Extraction and Sentiment Detection11
3.2 GCN and Sentiment Seed Words Generation15
3.2.1 Text Graph convolutional networks (TextGCN)17
3.2.2 Tensor Graph Structure (TensorGCN)21
3.2.3 Learning Target of Tensor GCN model23
3.3 Iterative aspect sentiment prediction24
CHAPTER 4 – Experimental Results26
4.1 Dataset26
4.1.1 Testing data26
4.1.2 Training data26
4.2 Experiment settings and Preprocessing27
4.2.1 Preprocessing27
4.2.2 Model parameter setting29
4.3 Evaluation measure32
4.3 Compared methods33
4.4 Result33
4.5 Case Study42
Chapter 5 – Conclusion44
Reference45

Angelidis, S., & Lapata, M. (2018). Summarizing opinions: Aspect extraction meets sentiment prediction and they are both weakly supervised. arXiv preprint arXiv:1808.08858.
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2018). Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805.
Huang, J., Meng, Y., Guo, F., Ji, H., & Han, J. (2020). Weakly-supervised aspect-based sentiment analysis via joint aspect-sentiment topic embedding. arXiv preprint arXiv:2010.06705.
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,
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,
Kipf, T. N., & Welling, M. (2017). Semi-supervised classification with graph convolutional networks. 2017. ArXiv abs/1609.02907.
Liu, P., Joty, S., & Meng, H. (2015). Fine-grained opinion mining with recurrent neural networks and word embeddings. Proceedings of the 2015 conference on empirical methods in natural language processing,
Liu, X., You, X., Zhang, X., Wu, J., & Lv, P. (2020). Tensor graph convolutional networks for text classification. Proceedings of the AAAI conference on artificial intelligence,
Mikolov, T., Chen, K., Corrado, G., & Dean, J. (2013). Efficient estimation of word representations in vector space. arXiv preprint arXiv:1301.3781.
Nielsen, F. Å. (2011). A new ANEW: Evaluation of a word list for sentiment analysis in microblogs. arXiv preprint arXiv:1103.2903.
Popescu, A.-M., & Etzioni, O. (2007). Extracting product features and opinions from reviews. In Natural language processing and text mining (pp. 9-28). Springer.
Qiu, G., Liu, B., Bu, J., & Chen, C. (2011). Opinion word expansion and target extraction through double propagation. Computational linguistics, 37(1), 9-27.
Tian, Y., Chen, G., & Song, Y. (2021). Aspect-based sentiment analysis with type-aware graph convolutional networks and layer ensemble. Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies,
Tsai, Y.-H., Chang, C.-M., Chen, K.-H., & Hwang, S.-Y. (2022). An Integration of TextGCN and Autoencoder into Aspect-based Sentiment Analysis, Proc. Of the 24th International Conference on Big Data Analytics and Knowledge Discovery, Vienna, Austria.
Velickovic, P., Cucurull, G., Casanova, A., Romero, A., Lio, P., & Bengio, Y. (2017). Graph attention networks. stat, 1050, 20.
Wu, F., Souza, A., Zhang, T., Fifty, C., Yu, T., & Weinberger, K. (2019). Simplifying graph convolutional networks. International conference on machine learning,
Xue, W., & Li, T. (2018). Aspect-based sentiment analysis with gated convolutional networks. arXiv preprint arXiv:1805.07043.
Yao, L., Mao, C., & Luo, Y. (2019). Graph convolutional networks for text classification. Proceedings of the AAAI conference on artificial intelligence,
Yin, Y., Wei, F., Dong, L., Xu, K., Zhang, M., & Zhou, M. (2016). Unsupervised word and dependency path embeddings for aspect term extraction. arXiv preprint arXiv:1605.07843.
Zhang, C., Li, Q., & Song, D. (2019). Aspect-based sentiment classification with aspect-specific graph convolutional networks. arXiv preprint arXiv:1909.03477.
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,
Zhuang, L., Jing, F., & Zhu, X.-Y. (2006). Movie review mining and summarization. Proceedings of the 15th ACM international conference on Information and knowledge management,