推薦系統被廣泛應用於電子商務及數位媒體等領域中，在評估推薦質量時，先前的推薦方法主要依賴於”評分”作為用戶的反饋，進而改良推薦方法的精確度。雖然項目的評分提供了一定的信息，但是仍無法全面的表達使用者的偏好，與單純的用戶評分資料相比，評論包含更多用戶的情感及對產品更廣的意見資訊，更能夠代表用戶對產品的實際想法。影音串流平台的用戶需求即為更加傾向於尋找具有相似故事情節的電影，有效的分析評論資訊可以為用戶提供更符合需求的推薦。

故本研究以電影推薦為例提出了一種的新的混和推薦方法。首先，透過語法依賴路徑及無監督式聚類演算法提取出描述各電影方面的意見對並進行分類，計算各方面整體情感相似度。並替各方面情感矩陣乘上方面的權重向量，以篩選出更有用的項目資訊，而後再針對劇情方面的意見做多標籤情緒分類。最後利用推薦的平均精確率找出最合適的權重，將情緒分析結果加權融合傳統基於內容過濾形成新的混和推薦方法，以提供更精確的推薦列表。與過去方法相比，本方法利用評論獲得了用戶對項目各方面更深層的意見表示，且可適用於同樣注重項目內容的不同領域產品，例如遊戲、書籍等推薦。

經由實驗結果，本研究方法和現有同樣基於情感之推薦方法相比，推薦精確率可提高4.5%；方法偏好度實驗中精確率獲得9.2%的提升；多樣性實驗中能得到高於22%的偏好比例。

Recommendation systems are widely used in the fields of e-commerce and digital media. When evaluating recommendation quality, previous recommendation methods mainly rely on "rating" as user feedback, improving the accuracy of recommendation methods. Although item ratings provide certain information, they still cannot fully express user preferences. Compared with rating data, reviews contain more users’ emotions and broader opinion information on products, are more representative of users with their thought on the products. Nowadays, users of streaming platforms prefer to find movies with similar storylines. Effective analysis of review information can provide more suitable recommended list to users.

Therefore, this research takes movie recommendation as an example and proposes a new hybrid recommendation method. Firstly, opinion pairs describing each aspect of the movie are extracted and classified through the syntax-dependent path and the K-medoids clustering algorithm. Then, overall emotional similarity of each aspect is calculated, the weighted vector of aspects is multiplied by the sentiment matrix of each aspect to filter more useful item’s information. Secondly, the opinions belong to plot aspect as input to perform Multi-label sentiment classification. Finally, the average accuracy of the recommendation is used to find the most suitable weights. Weighted fusion similarity calculation is performed with the result of sentiment analysis and content-based filtering to form a new hybrid recommendation method to provide a more accurate recommendation list. Compared with previous methods, a deeper opinion representation of users on various aspects of the item is obtained. Also, it can be applied to different fields of products that also pay attention to the content of the item, such as games or books recommendation.

According to the experimental results, the method proposed in this dissertation can improve the accuracy rate of recommendation by 4.5% compared with the existing method that also uses the analysis of review sentiment; The accuracy rate can be improved by 9.2% in the experiment of user method preference; The experiment of diversity evaluate can be higher than 22%.

[1]A. Adhikari, A. Ram, R. Tang, and J. Lin, “Docbert: Bert for document classification,” arXiv preprint arXiv:1904.08398, 2019.
[2]H. Ahn, “A new similarity measure for collaborative filtering to alleviate the new user cold-starting problem,” Information Sciences, Vol. 178, No. 1, pp. 37-51, 2008.
[3]E. Aslanian, M. Radmanesh, and M. Jalili, “Hybrid recommender systems based on content feature relationship,” IEEE transactions on industrial informatics, 2016.
[4]S. Baccianella, A. Esuli, and F. Sebastiani, “Sentiwordnet 3.0: an enhanced lexical resource for sentiment analysis and opinion mining,” in Lrec, 2010.
[5]M. Balabanović and Y. Shoham, “Fab: content-based, collaborative recommendation,” Communications of the ACM, Vol. 40, No. 3, pp. 66-72, 1997.
[6]W. Bancken, D. Alfarone, and J. Davis, “Automatically detecting and rating product aspects from textual customer reviews,” in Proceedings of the 1st international workshop on interactions between data mining and natural language processing at ECML/PKDD, 2014.
[7]S. Bird, “NLTK: the natural language toolkit,” in Proceedings of the COLING/ACL 2006 Interactive Presentation Sessions, 2006.
[8]R. Burke, “Hybrid recommender systems: Survey and experiments,” User Modeling and User-Adapted Interaction, Vol. 12, No. 4, pp. 331-370, 2002.
[9]E. Cambria, D. Das, S. Bandyopadhyay, and A. Feraco, “Affective Computing and Sentiment Analysis,” Springer International Publishing, pp. 1-10, 2017.
[10]D. Chen and C. Manning, “A fast and accurate dependency parser using neural networks,” in Proceedings of the 2014 conference on empirical methods in natural language processing (EMNLP), 2014.
[11]C. Dang, M. Moreno-García, and F. Prieta, “An approach to integrating sentiment analysis into recommender systems,” Sensors, Vol. 21, No. 16 pp. 5666, 2021.
[12]J. Devlin, M. W. Chang, K. Lee, K. Toutanova, and L. Assoc, “BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding,” in Conference of the North-American-Chapter of the Association-for-Computational-Linguistics - Human Language Technologies (NAACL-HLT), MN: Assoc Computational Linguistics-Acl, Minneapolis, 2021.
[13]V. Dixit and P. Jain, “Weighted Percentile-Based Context-Aware Recommender System,” in 1st International Conference on Signals, Machines and Automation (SIGMA), INDIA: Springer International Publishing Ag, Netaji Subhas Inst Technol, New Delhi, 2018.
[14]H. Do, P. Prasad, A. Maag, and A. Alsadoon, “Deep learning for aspect-based sentiment analysis: a comparative review,” Expert systems with applications, Vol. 118, pp. 272-299, 2019.
[15]M. Elahi, D. Kholgh, M. Kiarostami, M. Oussalah, and S. Saghari, “Hybrid recommendation by incorporating the sentiment of product reviews,” Information Sciences, Vol. 625, pp. 738-756, 2013.
[16]D. Goldberg, D. Nichols, B. Oki, and D. Terry, “Using collaborative filtering to weave an information tapestry,” Communications of the Acm, Vol. 35, No. 12, pp. 61-70, 1992.
[17]M. Goyani and N. Chaurasiya, “A review of movie recommendation system: Limitations, Survey and Challenges,” ELCVIA: electronic letters on computer vision and image analysis, Vol. 19, No. 3, pp. 18-37, 2020.
[18]Z. Gulzar, A. Leema, and G. Deepak, “Pcrs: Personalized course recommender system based on hybrid approach,” Procedia Computer Science, Vol. 125, pp. 518-524, 2018.
[19]R. Harakawa, D. Takehara, T. Ogawa, and M. Haseyama, “Sentiment-aware personalized tweet recommendation through multimodal FFM,” Multimedia Tools and Applications, Vol. 77, pp. 18741-18759, 2018.
[20]H. He and R. Xia, “Joint binary neural network for multi-label learning with applications to emotion classification,” in Natural Language Processing and Chinese Computing: 7th CCF International Conference, NLPCC 2018, Hohhot, China, August 26–30, Part I 7, Springer, 2018.
[21]N. Ifada and E. H. Prasetyo, “Employing sparsity removal approach and Fuzzy C-Means clustering technique on a movie recommendation system,” in 2018 International Conference on Computer Engineering, Network and Intelligent Multimedia (CENIM), IEEE, 2018.
[22]N. Ifada, T. Rahman, and M. Sophan, “Comparing collaborative filtering and hybrid based approaches for movie recommendation,” in 2020 6th information technology international seminar (ITIS), IEEE, 2020.
[23]U. Javed, K. Shaukat, I. Hameed, F. Iqbal, T. Alam, and S. Luo, “A review of content-based and context-based recommendation systems,” International Journal of Emerging Technologies in Learning (iJET), Vol. 16, No. 3, pp. 274-306, 2021.
[24]J. Jiang and D. Conrath. “Semantic similarity based on corpus statistics and lexical taxonomy,” in In Proceedings of the 10th Research on Computational Linguistics International Conference, Taipei, Taiwan, 1997.
[25]L. Kaufman and P. Rousseeuw, “Finding groups in data: an introduction to cluster analysis,” John Wiley & Sons, 2009.
[26]H. Khatter, N. Goel, N. Gupta, and M. Gulati, “Movie recommendation system using cosine similarity with sentiment analysis,” in 2021 Third International Conference on Inventive Research in Computing Applications (ICIRCA), IEEE, 2021.
[27]J. Konstan, J. Riedl, “Recommender systems: from algorithms to user experience,” User Model User-Adap Inter, Vol. 22, pp. 101-123, 2012.
[28]Y. Koren, “Factorization meets the neighborhood: a multifaceted collaborative filtering model,” in Proceedings of the 14th ACM SIGKDD international conference on Knowledge discovery and data mining, 2008.
[29]S. Kumar, K. De, and P. Roy, “Movie Recommendation System Using Sentiment Analysis From Microblogging Data,” Ieee Transactions on Computational Social Systems, Vol. 7, No. 4, pp. 915-923, 2020.
[30]T. Lehinevych, N. Kokkinis-Ntrenis, G. Siantikos, A. Dogruöz, T. Giannakopoulos, and S. Konstantopoulos, “Discovering similarities for content-based recommendation and browsing in multimedia collections,” in 2014 Tenth International Conference on Signal-Image Technology and Internet-Based Systems, IEEE, 2014.
[31]P. Lops, M. Gemmis, and G. Semeraro, “Content-based recommender systems: State of the art and trends,” Recommender Systems Handbook. Springer, pp. 73-105, 2011.
[32]W. Medhat, A. Hassan, and H. Korashy, “Sentiment analysis algorithms and applications: A survey,” Ain Shams Engineering Journal, Vol. 5, No. 4, pp. 1093-1113, 2014.
[33]G. Miller, “WordNet: a lexical database for English,” Communications of the ACM, Vol. 38, No. 11, pp. 39-41, 1995.
[34]D. Mladenic, “Text-learning and related intelligent agents: a survey,” IEEE intelligent systems and their applications, Vol. 14, No. 4, pp. 44-54, 1999.
[35]S. Mohammad, F. Marquez, M. Salameh, and S. Kiritchenko. “Semeval-2018 task 1: Affect in tweets,” in Proceedings of the 12th international workshop on semantic evaluation, 2018.
[36]A. Nazir, Y. Rao, L. Wu, and L. Sun, “Issues and challenges of aspect-based sentiment analysis: A comprehensive survey,” IEEE Transactions on Affective Computing, Vol. 13, No. 2, pp. 845-863, 2020.
[37]S. Philip, P. Shola, and A. Ovye, “Application of content-based approach in research paper recommendation system for a digital library,” International Journal of Advanced Computer Science and Applications, Vol. 5, No. 10, 2014.
[38]A. Romadhony, S. Faraby, and B. Pudjoatmodjo, “Online Shopping Recommender System Using Hybrid Method,” in International Conference of Information and Communication Technology (ICoICT), Ieee, Bandung, INDONESIA, 2013.
[39]S. Sahu, R. Kumar, M. S. Pathan, J. Shafi, Y. Kumar, and M. Ijaz, “Movie popularity and target audience prediction using the content-based recommender system”. IEEE Access, Vol. 10, pp. 42044-42060, 2022.
[40]M. Sharma, and S. Mann, “A survey of recommender systems: approaches and limitations,” International journal of innovations in engineering and technology, Vol. 2, No. 2, pp. 8-14, 2013.
[41]T. Singh, A. Nayyar, and A. Solanki, “Multilingual opinion mining movie recommendation system using RNN,” in Proceedings of first international conference on computing, communications, and cyber-security (IC4S 2019), Springer, 2020.
[42]B. Sinha and R. Dhanalakshmi, “Evolution of recommender paradigm optimization over time,” Journal of King Saud University-Computer and Information Sciences, Vol. 34, No. 4, pp. 1047-1059, 2022.
[43]S. and T. Telecommunications, “A hybrid approach to recommender systems based on matrix factorization,” Department for Agent Technologies and Telecommunications, 2009.
[44]X. Su and T. Khoshgoftaar, “A survey of collaborative filtering techniques,” Advances in artificial intelligence, 2009.
[45]T. Thet, J. Na, and C. Khoo, “Aspect-based sentiment analysis of movie reviews on discussion boards,” Journal of information science, Vol. 36, No. 6, pp. 823-848, 2010.
[46]P. Thorat, R. Goudar, and S. Barve, “Survey on collaborative filtering, content-based filtering and hybrid recommendation system,” International Journal of Computer Applications, Vol. 110, No. 4, pp. 31-36, 2015.
[47]A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A. Gomez, Ł. Kaiser, and I. Polosukhin, “Attention is all you need,” Advances in neural information processing systems, 2017.
[48]H. Wang and W. Li, “Relational Collaborative Topic Regression for Recommender Systems,” Ieee Transactions on Knowledge and Data Engineering, Vol. 27, No. 5, pp. 1343-1355, 2015.
[49]Y. Wang, M. Wang, and W. Xu, “A sentiment-enhanced hybrid recommender system for movie recommendation: a big data analytics framework,” Wireless Communications and Mobile Computing, 2018.
[50]T. Wolf, L. Debut, V. Sanh, J. Chaumond, C. Delangue, A. Moi, P. Cistac, T. Rault, R. Louf, and M. Funtowicz, “Transformers: State-of-the-art natural language processing,” in Proceedings of the 2020 conference on empirical methods in natural language processing: system demonstrations, 2020.
[51]A. Yadav and D. Vishwakarma, “Sentiment analysis using deep learning architectures: a review,” Artificial Intelligence Review, Vol. 53, No. 6, pp. 4335-4385, 2020.
[52]C. Yang, B. Wei, J. Wu, Y. Zhang, and L. Zhang, “CARES: A Ranking-Oriented CADAL Recommender System,” in 9th Annual International ACM/IEEE Joint Conference on Digital Libraries, Austin, 2009.
[53]Y. Yang, D. Zhou, and Y. He, “An interpretable neural network with topical information for relevant emotion ranking,” in Proceedings of the 2018 conference on empirical methods in natural language processing, 2018.
[54]J. Yu, J. Shi, Y. Chen, D. Ji, W. Liu, Z. Xie, K. Liu, and X. Feng, “Collaborative filtering recommendation with fluctuations of user’preference,” in 2021 IEEE International conference on information communication and software engineering (ICICSE), IEEE, 2021.
[55]L. Zhang, S. Wang, B. Liu, and K. Discovery, “Deep learning for sentiment analysis: A survey,” Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery, Vol. 8, No. 4, pp. e1253, 2018.
[56]Y. Zhang and L. Zhang, “Movie Recommendation Algorithm Based on Sentiment Analysis and LDA,” Procedia Computer Science, Vol. 199, pp. 871-878, 2021.
[57]W. Zhao, J. Ye, M. Yang, Z. Lei, S. Zhang, and Z. Zhao, “Investigating capsule networks with dynamic routing for text classification,” in Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, Brussels, Belgium, 2018.
[58]Z. Zhao, Q. Yang, H. Lu, T. Weninger, D. Cai, X. He, and Y. Zhuang, “Social-aware movie recommendation via multimodal network learning,” IEEE Transactions on Multimedia, Vol. 20, No. 2, pp. 430-440, 2017.
[59]D. Zhou, Y. Yang, and Y. He, “Relevant emotion ranking from text constrained with emotion relationships,” in Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers), 2018.
[60]P. Zhou, W. Shi, J. Tian, Z. Hao, and B. Xu, “Attention-based bidirectional long short-term memory networks for relation classification ” in Proceedings of the 54th annual meeting of the association for computational linguistics (volume 2: Short papers), 2016.