隨著網路與科技的蓬勃發展，產生了愈來愈多的數據與資料，就文字方面，評論方面占著一個很大一定的比例，這些評論的對象大多是人、產品、服務或活動等。其中線上旅遊論壇的興起使網路成為尋求旅行資訊的主要手段。旅行者在社交網站上相互交流並分享他們的觀點和經驗，每天產生大量評論，以至於產生在線酒店評論信息過載的問題。將近95％的旅行者在做出預訂決定之前先閱讀了在線酒店評論，並且超過三分之一的旅行者認為在網上選擇飯時，評論中表達的觀點是最關鍵的因素。因此，有效識別有益性的評論已成為重要的研究課題。
本文藉由擷取歐洲飯店515,000條客戶評論的資料做情緒分析，除了做一般的情緒分析，另外抽取詞性當作特徵，分別為完整資料集，只有形容詞跟副詞的形容詞，以及名詞還有動詞的資料集，經過卷積神經網路的訓練，並觀察實驗結果，效能的評估方式以精準率 (Precision)、召回率 (Recall) 和 F1 分數 (F1-measure, F1)作比較。

With the vigorous development of the Internet and technology, more and more data and information have been generated, so that the research on text inquiry is very popular. In terms of text, comments account for a large proportion of these comments. The rise of online travel forums has made the Internet the main means of seeking travel information. Travelers communicate with each other and share their views and experiences on social networking sites, generating a large number of comments every day, leading to the problem of excessive online hotel review information. Nearly 95% of travelers read online hotel reviews before making a booking decision, and more one third the travelers believe that the opinions expressed in the reviews are the most critical factor when choosing a hotel online. Therefore, effective identification of useful reviews becomes an important research issue.
This thesis makes sentiment analysis by extracting data from 515,000 customer reviews of European hotels. In addition to word embedding, sentiment analysis, it also extracts the part-of-speech targeted features. The experiments include (1) using complete data set, (2) only using adjectives and adverbs, and (3) only using nouns and verbs. The convolutional neural network is applied to get the experimental results. The performance evaluation method is compared with the precision rate (Precision), the recall rate (Recall) and the F1 score (F1-measure, F1).

Ady, M., & Quadri-Felitti, D. (2015). Consumer research identifies how to present travel review content for more bookings. Retrieved form http://webcache. googleusercontent. com/search.
Kim, Y. (2014). Convolutional neural networks for sentence classification. arXiv preprint arXiv:1408.5882.
Lu, B., & Tsou, B. K. (2010, July). Combining a large sentiment lexicon and machine learning for subjectivity classification. In 2010 international conference on machine learning and cybernetics (Vol. 6, pp. 3311-3316). IEEE.
Melville, P., Gryc, W., & Lawrence, R. D. (2009, June). Sentiment analysis of blogs by combining lexical knowledge with text classification. In Proceedings of the 15th ACM SIGKDD international conference on Knowledge discovery and data mining (pp. 1275-1284).
Pang, B., Lee, L., & Vaithyanathan, S. (2002). Thumbs up? Sentiment classification using machine learning techniques. arXiv preprint cs/0205070.
Pang, B., & Lee, L. (2004). A sentimental education: Sentiment analysis using subjectivity summarization based on minimum cuts. arXiv preprint cs/0409058.
Pang, B., & Lee, L. (2005). Seeing stars: Exploiting class relationships for sentiment categorization with respect to rating scales. arXiv preprint cs/0506075.
Prabowo, R., & Thelwall, M. (2009). Sentiment analysis: A combined approach. Journal of Informetrics, 3(2), 143-157.
Snyder, B., & Barzilay, R. (2007, April). Multiple aspect ranking using the good grief algorithm. In Human Language Technologies 2007: The Conference of the North American Chapter of the Association for Computational Linguistics; Proceedings of the Main Conference (pp. 300-307).
Su, F., & Markert, K. (2008, August). From words to senses: a case study of subjectivity recognition. In Proceedings of the 22nd International Conference on Computational Linguistics (Coling 2008) (pp. 825-832).
Tan, S., & Zhang, J. (2008). An empirical study of sentiment analysis for chinese documents. Expert Systems with applications, 34(4), 2622-2629.
Turney, P. D. (2002). Thumbs up or thumbs down? Semantic orientation applied to unsupervised classification of reviews. arXiv preprint cs/0212032..
Vapnik, V. (2013). The nature of statistical learning theory. Springer science & business media.
Xia, R., Zong, C., & Li, S. (2011). Ensemble of feature sets and classification algorithms for sentiment classification. Information sciences, 181(6), 1138-1152.
Xu, K., Liao, S. S., Li, J., & Song, Y. (2011). Mining comparative opinions from customer reviews for competitive intelligence. Decision support systems, 50(4), 743-754.
Zhang, Ziqiong, et al. "Sentiment classification of Internet restaurant reviews written in Cantonese." Expert Systems with Applications 38.6 (2011): 7674-7682.