隨著資訊通訊技術持續蓬勃發展，資訊的傳播和共享變得更加方便，因而使得推薦系統的出現來幫助使用者從龐大的網際網路中找到有興趣的資源，其中，個人化推薦的出現又更佳的改善資訊過載的問題，提高被推薦者的滿意度。然而，當使用者偏好數據不足，將會造成個人化推薦的困難，於是便有協作過濾推薦技術的出現欲解決此問題，但當產品或服務有資料稀疏的特性時，資料稀疏性便成為協作過濾方法的主要限制，因此便有研究提出了可能的解決方案，透過轉移不同類別的產品或服務間偏好資訊，稱為跨領域(cross-domain)推薦。
近年來，跨域推薦的研究漸漸改善單域推薦系統中資料稀疏性的問題，從而提高了推薦的品質。而有別於以往研究都是以評分矩陣、基本屬性或潛在向量進行轉換映射，並僅給予項目的預測評分，而本研究考量到最終推薦結果呈現若可以解釋給予此預測評分的原因，會更符合實際需求，且有學者指出消費者會從不同Aspect對產品或服務進行評論，細粒度特徵為對產品或服務有價值的針對性資訊，故本研究欲提出一個自評論文字中提取項目較細部的語義資訊作為跨映射的特徵向量的跨域推薦方法。首先，利用神經網路與注意力機制針對評論中的不同方面提取特徵向量，再透過多層感知機映射各使用者在不同域之特徵向量，獲得預測評分並透過情感分析檢視該項目在使用者在意的各方面之表現，最後，將不僅提供項目預測評分，還包含簡單表示項目各方面表現的推薦結果，期望能獲得可解釋且更符合實際需求的跨域推薦結果。
本研究透過實驗檢視研究方法的有效性，實驗結果顯示本研究和過去方法相比，能自評論文字中提取更多評分以外使用者對項目評價的語義特徵資訊，並且透過不同領域間的不同語義特徵進行跨域評分預測，在自動評估指標中獲得較好的表現。證實本研究以跨領域評論進行個人化推薦的方法不僅能給予使用者滿意的評分預測結果，且提供使用者個人偏好的項目細部資訊以獲得可解釋的結果。

With the development of Information and Communication Technology has made the sharing of information more convenient, personalized recommendations have emerged to help users quickly find preferred information from the Internet in the face of information overload. Then, the Collaborative Filtering recommendation improves the Cold Start problem of insufficient user data for personalized recommendation. However, some products or services have problem of Data Sparsity, sparsity of data becomes the main limitation of the Collaborative Filtering method. Therefore, some researches have proposed possible solutions, called "Cross-Domain Recommendation", transferring or mapping information between different types of products or services.

Cross-domain recommendations have improved the problem of data sparsity in single-domain recommendation. Previous researches which are based on a rating, basic attributes or latent vectors for mapping, and only give the predicted rating result of items. We consider that if we can extract more and the fine-grained semantic information from reviews, it will be more realistic. And some scholars pointed out that consumers may comment from different aspects, the fine-grained features are targeted information that is valuable for products or services. Therefore, we propose a cross-domain recommendation method, which extracts aspect-based feature from the reviews by the neural network, and then the feature vectors in different domains are mapped through MLP to obtain predicted ratings and check the performance of the item by aspect-based sentiment analysis.

We conducted several experiments to examine the effectiveness of our method. The experimental results show that we can extract semantic information more than rating about the item from reviews. Our method provides not only correct predicted rating of an item, but also the performance of aspects to obtain an explainable and more in line with actual needs result.

Al-Ghossein, M., Abdessalem, T., & Barré, A. (2018). Cross-Domain Recommendation in the Hotel Sector. Proceedings of RecTour, 1-6.
Bahdanau, D., Cho, K., & Bengio, Y. (2014). Neural Machine Translation by Jointly Learning to Align and Translate. arXiv preprint arXiv:1409.0473.
Bengio, Y., Simard, P., & Frasconi, P. (1994). Learning Long-Term Dependencies with Gradient Descent is Difficult. IEEE Transactions on Neural Networks, 5(2), 157-166.
Chen, Z., Zhan, Z., Shi, W., Chen, W., & Zhang, J. (2016). When Neural Network Computation Meets Evolutionary Computation: A Survey. Paper presented at the International Symposium on Neural Networks, St. Petersburg, Russia.
Chin, J. Y., Zhao, K., Joty, S., & Cong, G. (2018). ANR: Aspect-Based Neural Recommender. Paper presented at the Proceedings of the 27th ACM International Conference on Information and Knowledge Management, Torino, Italy.
Chung, J., Gulcehre, C., Cho, K., & Bengio, Y. (2014). Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling. arXiv preprint arXiv:1412.3555.
Cui, Y., Huang, C., & Wang, Y. (2019). Research on Personalized Tourist Attraction Recommendation Based on Tag and Collaborative Filtering. Paper presented at the 2019 Chinese Control And Decision Conference (CCDC), Nanchang, China.
Elman, J. L. (1990). Finding Structure in Time. Cognitive Science, 14(2), 179-211.
Fu, W., Peng, Z., Wang, S., Xu, Y., & Li, J. (2019). Deeply Fusing Reviews and Contents for Cold Start Users in Cross-Domain Recommendation Systems. Paper presented at the Proceedings of the AAAI Conference on Artificial Intelligence, Hilton Hawaiian Village, Honolulu,Hawaii, USA.
Hochreiter, S., & Schmidhuber, J. (1997). Long Short-Term Memory. Neural Computation, 9(8), 1735-1780.
Hu, Z., Wang, J., Yan, Y., Zhao, P., Chen, J., & Huang, J. (2020). Neural Graph Personalized Ranking for Top-N Recommendation. Knowledge-Based Systems, 106426.
Jain, A. K., Mao, J., & Mohiuddin, K. M. (1996). Artificial Neural Networks: A Tutorial. Computer, 29(3), 31-44.
Lauren, P., Qu, G., Yang, J., Watta, P., Huang, G.-B., & Lendasse, A. (2018). Generating Word Embeddings From an Extreme Learning Machine for Sentiment Analysis and Sequence Labeling Tasks. Cognitive Computation, 10(4), 625-638.
Levy, O., Goldberg, Y., & Dagan, I. (2015). Improving Distributional Similarity with Lessons Learned From Word Embeddings. Transactions of the Association for Computational Linguistics, 3, 211-225.
Li, J., Li, J., Fu, X., Masud, M. A., & Huang, J. Z. (2016). Learning Distributed Word Representation with Multi-Contextual Mixed Embedding. Knowledge-Based Systems, 106, 220-230.
Lin, T., (2019, Feb 8). How to Train Word2vec and FastText Embedding on Wikipedia Corpus. Retrieved from https://medium.com/@black_swan/how-to-train-word2vec-and-fasttext-embedding-on-wikipedia-corpus-9e8ac45a0c0a
Man, T., Shen, H., Jin, X., & Cheng, X. (2017). Cross-Domain Recommendation : An Embedding and Mapping Approach. Paper presented at the IJCAI, Melbourne, Australia.
Marcheggiani, D., Täckström, O., Esuli, A., & Sebastiani, F. (2014). Hierarchical multi-label conditional random fields for aspect-oriented opinion mining. In European conference on information retrieval (pp. 273-285). Springer, Cham.
Menk, A., Sebastia, L., & Ferreira, R. (2019). Recommendation Systems for Tourism Based on Social Networks : A Survey. arXiv preprint arXiv:1903.12099.
Mikolov, T., Chen, K., Corrado, G., & Dean, J. (2013). Efficient Estimation of Word Representations in Vector Space. arXiv preprint arXiv:1301.3781.
Naili, M., Chaibi, A. H., & Ghezala, H. H. B. (2017). Comparative Study of Word Embedding Methods in Topic Segmentation. Procedia Computer Science, 112, 340-349.
Pan, S. J., Tsang, I. W., Kwok, J. T., & Yang, Q. (2010). Domain Adaptation via Transfer Component Analysis. IEEE transactions on neural networks, 22(2), 199-210.
Pennington, J., Socher, R., & Manning, C. D. (2014). Glove: Global Vectors for Word Representation. Paper presented at the Proceedings of The 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), Doha, Qatar.
Qi, Q., Cao, J., Tan, Y., & Xiao, Q. (2018). Cross-Domain Recommendation Method in Tourism. Paper presented at the 2018 IEEE International Conference on Progress in Informatics and Computing (PIC), Suzhou, China.
Qiang, Y., Li, X., & Zhu, D. (2020). Toward Tag-free Aspect Based Sentiment Analysis: A Multiple Attention Network Approach. Paper presented at the 2020 International Joint Conference on Neural Networks (IJCNN), Glasgow, UK.
Ruck, D. W., Rogers, S. K., Kabrisky, M., Oxley, M. E., & Suter, B. W. (1990). The Multilayer Perceptron as an Approximation to a Bayes Optimal Discriminant Function. IEEE Transactions on Neural Networks, 1(4), 296-298.
Schuster, M., & Paliwal, K. K. (1997). Bidirectional recurrent neural networks. IEEE transactions on Signal Processing, 45(11), 2673-2681.
Tan, S., Bu, J., Qin, X., Chen, C., & Cai, D. (2014). Cross Domain Recommendation Based on Multi-Type Media Fusion. Neurocomputing, 127, 124-134.
Tarwani, K. M., & Edem, S. (2017). Survey on Recurrent Neural Network in Natural Language Processing. Int. J. Eng. Trends Technol, 48, 301-304.
UNWTO. (2019). International Tourism Highlights (2019 ed.).
Valliyammai, C., & Thendral, S. E. (2019). Ontology Matched Cross Domain Personalized Recommendation of Tourist Attractions. Wireless Personal Communications, 107(1), 589-602.
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., . . . Polosukhin, I. (2017). Attention is All You Need. arXiv preprint arXiv:1706.03762.
Wang, Y., Huang, M., Zhu, X., & Zhao, L. (2016). Attention-Based LSTM for Aspect-Level Sentiment Classification. Paper presented at the Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, Austin, Texas, USA.
Wang, Y., Yu, H., Wang, G., & Xie, Y. (2020). Cross-Domain Recommendation Based on Sentiment Analysis and Latent Feature Mapping. Entropy, 22(4), 473.
Wang, W., Zhang, G., & Lu, J. (2016). Member Contribution-Based Group Recommender System. Decision Support Systems, 87, 80-93.
Xin, X., Liu, Z., Lin, C.-Y., Huang, H., Wei, X., & Guo, P. (2015). Cross-Domain Collaborative Filtering with Review Text. Paper presented at the Twenty-Fourth International Joint Conference on Artificial Intelligence, Buenos Aires, Argentina.
Yepes, A. J. (2017). Word Embeddings and Recurrent Neural Networks Based on Long-Short Term Memory Nodes in Supervised Biomedical Word Sense Disambiguation. Journal of Biomedical Informatics, 73, 137-147.
Zhang, Q., Wu, D., Lu, J., Liu, F., & Zhang, G. (2017). A Cross-Domain Recommender System with Consistent Information Transfer. Decision Support Systems, 104, 49-63.
Zheng, L., Noroozi, V., & Yu, P. S. (2017). Joint Deep Modeling of Users and Items Using Reviews for Recommendation. Paper presented at the Proceedings of the Tenth ACM International Conference on Web Search and Data Mining, Cambridge, United Kingdom.
Zhou, X., Wang, M., & Li, D. (2017). From Stay to Play – A Travel Planning Tool Based on Crowdsourcing User-Generated Contents. Applied geography, 78, 1-11.
交通部觀光局 (2018)。中華民國 107 年臺灣旅遊狀況調查。台北市：交通部觀光局。