隨著電子商務平台的日漸普及，客戶對產品的評論在市場行銷上扮演著重要的角色。雖然現在市面上產品評論的數量日益增加，但通常會被大眾採用的評論皆來自少數聲譽相對較良好的使用者。若能在大量評論中，找到最有幫助的評論，將會對提高產品銷售量有重要的意義。
在學術界，有很多研究者都已針對預測產品評論幫助性的進行了廣泛研究。但這些研究都只找出評論的品質與產品的評分，兩者之間並沒有關連性。然而，「情緒」對於產品的銷售擁有非常大的影響力，同時也在決定評論的幫助性上扮演了關鍵的角色。目前學界缺乏使用情緒預測產品評論幫助性，本研究針對評論中的字詞進行文字探勘，找尋隱藏在其中的情緒樣式，並透過該情緒樣式更精準地找出評論的幫助性。
本研究目標分成兩個方向：首先，針對同類型的產品進行幫助性預測。其次，將幫助性預測應用至不同類型的產品。在情緒字詞組合樣式的文字探勘中，情緒程度是非常重要的依據，本文也基於此在評論中定義出了數種特徵。實驗結果顯示，相較於基線法(Baseline method)，在同類型商品中，本方法的準確率高出6.77％；在跨領域的預測中，準確率更高出10.13％。

With the popularity of e-commerce platforms, customer product reviews tend to have a significant impact on markets. Nowadays, more and more reviews are available on products and usually, good contributions are produced by a relatively small set of reputable users and consumed by a large user population. Therefore, to identify the most helpful reviews is very essential to improve the product sales. Several researches have been done to predict the helpfulness of product reviews. However, it is found out that the quality of a review is not correlated to the rating of the product. Sentiments, however, have a direct significant impact on sales. Therefore, emotions can play a vital role to determine the helpfulness of reviews. Very few researches have been done on using emotion for prediction of helpfulness. Therefore, we intend to mine emotional patterns contained in the text of the reviews and use these patterns to predict its helpfulness. Our objective is divided into two parts: firstly, to predict helpfulness in the same product category (within domain) and secondly, across different product categories (cross domain). We identified several features based on the degree of emotions that can be used to mine the patterns. Our experiment results show that the proposed approach can outperform the existing baseline method upto 6.77 % accuracy for within domain prediction and upto 10.13 % for cross-domain predictions.

[1] W. Duan, B. Gu, and A. B. Whinston, "The dynamics of online word-ofmouth and product sales|an empirical investigation of the movie industry,"Journal of retailing, vol. 84, no. 2, pp. 233-242, 2008.
[2] B.-C. Chen, J. Guo, B. Tseng, and J. Yang, "User reputation in a comment rating environment," in Proceedings of the 17th ACM SIGKDD inter-national conference on Knowledge discovery and data mining, pp. 159-167,ACM, 2011.
[3] N. Hu, N. S. Koh, and S. K. Reddy, "Ratings lead you to the product, reviews help you clinch it? the mediating role of online review sentiments on product sales," Decision Support Systems, vol. 57, pp. 42-53, 2014.
[4] Y. Zhang and D. Zhang, "Automatically predicting the helpfulness of online reviews," in Information Reuse and Integration (IRI), 2014 IEEE 15th International Conference on, pp. 662-668, IEEE, 2014.
[5] A. Ghose and P. G. Ipeirotis, "Estimating the helpfulness and economic impact of product reviews: Mining text and reviewer characteristics," Knowl-
edge and Data Engineering, IEEE Transactions on, vol. 23, no. 10, pp. 1498-1512, 2011.
[6] S.-M. Kim, P. Pantel, T. Chklovski, and M. Pennacchiotti, "Automatically assessing review helpfulness," in Proceedings of the 2006 Conference on empirical methods in natural language processing, pp. 423-430, Association for Computational Linguistics, 2006.
[7] M. P. O'Mahony and B. Smyth, "Using readability tests to predict helpful product reviews," in Adaptivity, Personalization and Fusion of HeterogeneousInformation, pp. 164{167, LE CENTRE DE HAUTES ETUDES INTERNATIONALES
D'INFORMATIQUE DOCUMENTAIRE, 2010.
[8] Y. Liu, X. Huang, A. An, and X. Yu, "Modeling and predicting the helpfulness of online reviews," in Data Mining, 2008. ICDM'08. Eighth IEEE International Conference on, pp. 443-452, IEEE, 2008.
[9] S. Lee and J. Y. Choeh, "Predicting the helpfulness of online reviews using multilayer perceptron neural networks," Expert Systems with Applications,
vol. 41, no. 6, pp. 3041-3046, 2014.
[10] L. Martin and P. Pu, "Prediction of helpful reviews using emotions extraction,"in Twenty-Eighth AAAI Conference on Articial Intelligence, 2014.
[11] K. R. Scherer, "What are emotions? and how can they be measured?," Social science information, vol. 44, no. 4, pp. 695-729, 2005.
[12] D. Garcia and F. Schweitzer, "Emotions in product reviews-empirics and
models," in Privacy, Security, Risk and Trust (PASSAT) and 2011 IEEE Third Inernational Conference on Social Computing (SocialCom), 2011 IEEE Third International Conference on, pp. 483-488, IEEE, 2011.
[13] C. Argueta, Y.-S. Chen, and E. Saravia,"Unsupervised graph-based patterns extraction for emotion classication," in 2015 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM 2015), 2015.
[14] R. Plutchik, "The natural of emotions," American Scientist, vol. 89, pp. 344-350, July 2001.
[15] M. Thelwall, K. Buckley, G. Paltoglou, D. Cai, and A. Kappas, "Sentiment strength detection in short informal text," Journal of the American Society for Information Science and Technology, vol. 61, no. 12, pp. 2544-2558, 2010.
[16] M. Thelwall, K. Buckley, and G. Paltoglou, "Sentiment strength detection for the social web," Journal of the American Society for Information Science
and Technology, vol. 63, no. 1, pp. 163-173, 2012.