對於生產商而言，了解顧客購物的動機和理由是一個有趣且重要的議題，高投資和期待的產品更是如此。過往的研究已證明了線上產品評論可被認為是電子口碑，這些評論隱含了一些和產品或市場策略有關的資訊。本研究主要探討的產品是熱門電影，也就是片商投入了大量資金製作的電影，或是小成本但熱賣的成功電影。由於這些電影知名度高，一些基本的資訊如電影類型、影星、探討主題都普遍被大眾所了解，而且也被廣泛的討論。由於線上產品評論數量眾多，而且大部分所包含的資訊都差不多。顧客為了節省時間，可能只會閱讀一些包含不一樣或相反意見的評論。故本研究透過使用奇異函數去調高少數評論的重要性，進而去驗證這些少數評論是否比大部分評論更具有銷售衝擊。除了少數評論對銷售的影響，本研究也同時探討銷售和情緒之間的關係。透過銷售資料去推斷情緒極性，銷售與情緒之間的直接關係能夠被查證。實驗結果顯示少數評論影響力的確存在，只包含文字變數的銷售預測模型之解釋力因加上奇異函數而明顯增加。而銷售與情緒之間的關係則是顯得不直接，銷售推斷情緒的結果和字典法的結果無顯著差異。由於本研究結果仍有些許模糊的地方，而且經濟模型結合產品特徵和意見字具有取代傳統市場調查的潛力，所以少數影響和銷售推斷情緒需要更深入的研究。

The reasons or motivations behind the purchase of a product are an interesting issue to manufacturers, especially those products that involve great investment or high expectation to success. Previous researches have demonstrated that online reviews can be recognized as electronic word of mouth and provide interesting information that relate to sales and marketing strategies. Product like blockbuster movies, which contain large investment from film makers or success movies with small budget, basic information like genre, stars and topics are well known and most reviews contain similar information and opinions. Since the volume of online review is huge, people might only read those reviews which carry different or opposite opinions to save time. By applying singularity weight to increase the importance of minority reviews, this research tries to examine the possibility of whether the minority reviews impact sales more than majority reviews. Except minority effect on sales, this research also explores the relation between sales and sentiment. Through inferring sentiment polarity from sales data, the direct relation between sales and sentiment is investigated. Results showed that minority effect does exist as the explanation power of textual variables to sales increase when singularity weight is adopted. While the relation appears to be indirect between sales and sentiment, with the results of sales inferred sentiment yield similar accuracy as dictionary method. Much works need to be done to expose the mechanism of minority effect on sales and sales inferred sentiment, as the econometric model with product features and opinion words possess the potential to substitute traditional marketing research.

Archak, N., Ghose, A., & Ipeirotis, P. G. (2007). Show me the Money! Deriving the Pricing Power of Product Features by Mining Consumer Reviews. Paper presented at the Proceedings of the Thirteenth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD 2007), San Jose, California, USA. http://pages.stern.nyu.edu/~aghose/kdd2007.pdf
Archak, N., Ghose, A., & Ipeirotis, P. G. (2011). Deriving the Pricing Power of Product Features by Mining Consumer Reviews. Management Science, 57(8), 1485-1509. doi: 10.1287/mnsc.1110.1370
Awad, N. F., & Zhang, J. (2007). Stay out of My Forum! Evaluating Firm Involvement in Online Ratings Communities. Paper presented at the Proceedings of the 40th Annual Hawaii International Conference on System Sciences.
Berger, J., Sorensen, A. T., & Rasmussen, S. J. (2010). Positive Effects of Negative Publicity: When Negative Reviews Increase Sales. Marketing Science, 29(5), 815-827. doi: 10.1287/mksc.1090.0557
Bobadilla, J., Ortega, F., & Hernando, A. (2012). A collaborative filtering similarity measure based on singularities. Information Processing & Management, 48(2), 204-217. doi: http://dx.doi.org/10.1016/j.ipm.2011.03.007
Chang, C.-C., & Lin, C.-J. (2011). LIBSVM: A library for support vector machines. ACM Trans. Intell. Syst. Technol., 2(3), 1-27. doi: 10.1145/1961189.1961199
Chevalier, J. A., & Mayzlin, D. (2006). The effect of word of mouth on sales: Online book reviews. Journal of Marketing Research, 43(3), 345-354. doi: 10.1509/jmkr.43.3.345
Chintagunta, P. K., Gopinath, S., & Venkataraman, S. (2010). The Effects of Online User Reviews on Movie Box Office Performance: Accounting for Sequential Rollout and Aggregation Across Local Markets. [Article]. Marketing Science, 29(5), 944-957. doi: 10.1287/mksc.1100.0572
Decker, R., & Trusov, M. (2010). Estimating aggregate consumer preferences from online product reviews. [Review]. International Journal of Research in Marketing, 27(4), 293-307. doi: 10.1016/j.ijresmar.2010.09.001
Dellarocas, C., Zhang, X. Q., & Awad, N. F. (2007). Exploring the value of online product reviews in forecasting sales: The case of motion pictures. [Article]. Journal of Interactive Marketing, 21(4), 23-45. doi: 10.1002/dir.20087
Dhar, V., & Chang, E. A. (2009). Does Chatter Matter? The Impact of User-Generated Content on Music Sales. Journal of Interactive Marketing, 23(4), 300-307. doi: 10.1016/j.intmar.2009.07.004
Ding, X., Liu, B., & Yu, P. S. (2008). A holistic lexicon-based approach to opinion mining. Paper presented at the Proceedings of the international conference on Web search and web data mining, Palo Alto, California, USA.
Eliashberg, J., Hui, S. K., & Zhang, Z. J. M. (2007). From story line to box office: A new approach for green-lighting movie scripts. [Article]. Management Science, 53(6), 881-893. doi: 10.1287/mnsc.1060.0668
Esuli, A., & Sebastiani, F. (2006). SentiWordNet: A Publicly Available Lexical Resource for Opinion Mining. Paper presented at the Proc. Fifth Conf. Language Resources and Evaluation.
Fahrni A., K. M. (2008). Old Wine or Warm Beer: Target-Specific Sentiment Analysis of Adjectives. Paper presented at the Proceedings of the symposium on affective language in human and machine.
Fellbaum, C. (1998). WordNet: an Electronic Lexical Database. MIT Press, Cambridge, MA.
Ghose, A., Ipeirotis, P. G., & Li, B. B. (2012). Designing Ranking Systems for Hotels on Travel Search Engines by Mining User-Generated and Crowdsourced Content. [Article]. Marketing Science, 31(3), 493-520. doi: 10.1287/mksc.1110.0700
Ghose, A., Ipeirotis, P. G., & Sundararajan, A. (2007). Opinion Mining using Econometrics: A case Study on Reputation Systems. Paper presented at the P 45 ANN M ASS COMP.
Goldberg, A. B., & Zhu, X. (2006). Seeing stars when there aren't many stars: graph-based semi-supervised learning for sentiment categorization. Paper presented at the Proceedings of the First Workshop on Graph Based Methods for Natural Language Processing.
Green, P. E., & Srinivasan, V. (1978). Conjoint analysis in consumer research - issues and outlook. [Article]. Journal of Consumer Research, 5(2), 103-123. doi: 10.1086/208721
He, B., Macdonald, C., He, J., & Ounis, I. (2008). An effective statistical approach to blog post opinion retrieval. Paper presented at the Proceedings of the 17th ACM conference on Information and knowledge management, Napa Valley, California, USA.
Hu, M., & Liu, B. (2004). Mining and summarizing customer reviews. Paper presented at the Proceedings of the tenth ACM SIGKDD international conference on Knowledge discovery and data mining, Seattle, WA, USA.
Hu, N., Liu, L., & Zhang, J. J. (2008). Do online reviews affect product sales? The role of reviewer characteristics and temporal effects. [Article]. Information Technology & Management, 9(3), 201-214. doi: 10.1007/s10799-008-0041-2
Jaap Kamps, M., Maarten, M., Robert, J. M., & Maarten De, R. (2004). Using WordNet to Measure Semantic Orientations of Adjectives. Paper presented at the Proceedings of the 4th International Conference on Language Resources and Evaluation, Paris, France.
Joonhyuk Yang, W. K., Naveen Amblee, Jaeseung Jeong. (2012). The heterogeneous effect of WOM on product sales: why the effect of WOM valence is mixed? European Journal of Marketing, 46(11), 1523-1538. doi: 10.1108/03090561211259961
Klein, D., & Manning, C. D. (2003). Accurate unlexicalized parsing. Paper presented at the Proceedings of the 41st Annual Meeting on Association for Computational Linguistics - Volume 1, Sapporo, Japan.
Kumar, A., & Sebastian, T. M. (2012). Sentiment Analysis: A Perspective on its Past, Present and Future. I. J. Intelligent Systems and Applications, 4(10), pp 1-14. doi: 10.5815/ijisa.2012.10.01
Lee, T. Y. (2007). Needs-based analysis of online customer reviews. Paper presented at the Proceedings of the ninth international conference on Electronic commerce, Minneapolis, MN, USA.
Lee, T. Y., & Bradlow, E. T. (2011). Automated Marketing Research Using Online Customer Reviews. [Article]. Journal of Marketing Research, 48(5), 881-894.
Leung CWK, C. S., Chung FL. (2006). Integrating collaborative filtering and sentiment analysis: a rating inference approach. Paper presented at the ECAI 2006 workshop on recommender systems.
Li, X. X., & Hitt, L. M. (2008). Self-Selection and Information Role of Online Product Reviews. [Article]. Information Systems Research, 19(4), 456-474. doi: 10.1287/isre.1070.0154
Liu, Y. (2006). Word of Mouth for Movies: Its Dynamics and Impact on Box Office Revenue. Journal of Marketing, 70(3), 74-89. doi: 10.2307/30162102
Lu, Q., Xiao, L., & Ye, Q. (2012, 20-22 Sept. 2012). Investigating the impact of online word-of-mouth on hotel sales with panel data. Paper presented at the Management Science and Engineering (ICMSE), 2012 International Conference on.
Maeyer, P. D. (2012). Impact of online consumer reviews on sales and price strategies: a review and directions for future research. Journal of Product & Brand Management, 21(2), 132-139. doi: 10.1108/10610421211215599
Na, J.-C., Kyaing, W., Khoo, C. G., Foo, S., Chang, Y.-K., & Theng, Y.-L. (2012). Sentiment Classification of Drug Reviews Using a Rule-Based Linguistic Approach. In H.-H. Chen & G. Chowdhury (Eds.), The Outreach of Digital Libraries: A Globalized Resource Network (Vol. 7634, pp. 189-198): Springer Berlin Heidelberg.
Netzer, O., Feldman, R., Goldenberg, J., & Fresko, M. (2012). Mine Your Own Business: Market-Structure Surveillance Through Text Mining. Marketing Science, 31(3), 521-543. doi: 10.1287/mksc.1120.0713
Pang, B., Lee, L., & Vaithyanathan, S. (2002). Thumbs up? Sentiment classification using machine learning techniques. Somerset: Association Computational Linguistics.
Roberts, J. H., & Urban, G. L. (1988). Modeling Multiattribute Utility, Risk, and Belief Dynamics for New Consumer Durable Brand Choic. Management Science, 34(2), 167-185. doi: 10.1287/mnsc.34.2.167
Rui, H., Liu, Y., & Whinston, A. (2013). Whose and what chatter matters? The effect of tweets on movie sales. Decision Support Systems. doi: 10.1016/j.dss.2012.12.022
Sher, P. J., & Lee, S. H. (2009). Consumer skepticism and online reviews: an elaboration likelihood model perspective. [Article]. Social Behavior and Personality, 37(1), 137-143.
Tirunillai, S., & Tellis, G. J. (2012). Does Chatter Really Matter? Dynamics of User-Generated Content and Stock Performance. Marketing Science, 31(2), 198-215. doi: 10.1287/mksc.1110.0682
Tsytsarau, M., & Palpanas, T. (2012). Survey on mining subjective data on the web. [Article]. Data Mining and Knowledge Discovery, 24(3), 478-514. doi: 10.1007/s10618-011-0238-6
Turney, P. D. (2002). Thumbs up or thumbs down?: semantic orientation applied to unsupervised classification of reviews. Paper presented at the Proceedings of the 40th Annual Meeting on Association for Computational Linguistics, Philadelphia, Pennsylvania.
Urban, G. L. (2005). Customer advocacy: A new era in marketing? [Editorial Material]. Journal of Public Policy & Marketing, 24(1), 155-159. doi: 10.1509/jppm.24.1.155.63887
Wilson, T., Wiebe, J., & Hoffmann, P. (2005). Recognizing contextual polarity in phrase-level sentiment analysis. Paper presented at the Proceedings of the conference on Human Language Technology and Empirical Methods in Natural Language Processing, Vancouver, British Columbia, Canada.
Yu, X. H., Liu, Y., Huang, J. X., & An, A. J. (2012). Mining Online Reviews for Predicting Sales Performance: A Case Study in the Movie Domain. [Article]. Ieee Transactions on Knowledge and Data Engineering, 24(4), 720-734. doi: 10.1109/tkde.2010.269
Zhu, F., & Zhang, X. Q. (2010). Impact of Online Consumer Reviews on Sales: The Moderating Role of Product and Consumer Characteristics. [Article]. Journal of Marketing, 74(2), 133-148.