網際網路的發展改變人們的購物方式與行為，消費者在網路提供的評論與評價，不僅影響人們的購買意願，對企業而言也是重要的決策資訊，然而過去未存在一個系統性的方法，將消費者的評論精準地轉換為決策所需之偏好模型。本研究提出一個基於文字探勘與貝氏方法之消費者偏好多屬性評估模型。本研究利用文字探勘之主題分析方法暸解消費者在評估產品時所側重的面向或準則，透過貝氏網路建構評估的層級架構並決定消費者在評估產品時不同準則或面向之相對權重，最後透過貝氏迴歸方法，從消費者對產品之整體評價回推消費者對該產品個別屬性之評價，以建立完整的偏好模型。本研究最後並利用電商平台的消費者評論，進行上述方法的測試與驗證。本研究的結果，不僅能幫助決策者建立對消費者的洞察力，且可對消費者在意的每一面向做精準的推論，因此可供決策者做為產品推薦、產品改善與下一代產品研發之基礎。

The Internet has changed people’s shopping behaviors. The online comments and rating of products provided by consumers not only influence people’s willingness to buy, but also play an important role for the decision maker of the enterprises. However, a systematic method that could convert consumers reviews into preference model for decision making has not yet been developed. This study thus proposes a multi-crietria preference model of consumers based on text mining and Bayesian network. Our study uses topic analysis of text mining to elicit the attributes (i.e., criteria) that consumers might consider when evaluating a product. After that, we build a multi-criteria decision analysis (MCDA) hierarchical structure and determine the relative weights of different criteria via Bayesian network. Finally, a Bayesian linear regression model is implemented to estimate the consumers’ rating scores on different criteria for building the complete preference model. The proposed method has been tested and verified by using consumer reviews on e-commence website. Results of this research not only can give decision makers a clear view of consumers’ preferences, but also makes it easier to for managers to make accurate inference on different product or service aspects that the consumer focus on.

Arndt, J., (1967). Role of Product-Related Conversations in the Diffusion of a New Product. Journal of Marketing Research, 4(3), 291-295.
Anandarajan, M., Hill, C., Nolan, T., (2019). Practical Text Analytics: Maximizing the value of Text Data. Springer.
Bethard, S., Hong, Y., Ashley, T., Vasileios, H., Dan, J. (2004). Automatic Extraction of Opinion Propositions and Their Holders. In Proceedings of the AAAISpring Symposium on Exploring Attitude and Affect in Text.
Bi, J., & Liu, Y., Fan, Z., & Zhang, J. (2019). Wisdom of crowds: Conducting importance-performance analysis (IPA) through online reviews, Tourism Management, 70(2), 460-478.
Blei, D. M., Ng, A. Y., Jordan, M. I. (2003). Latent dirichlet allocation. Journal of Machine Learning Research, Vol. 3, 993-1022.
Blei, D. M., Carin, L., Dunson, D. (2010). Probabilistic topic models. IEEE Signal Processing Magazine, 27(6), 55–65.
Blei, D. M. (2012). Probabilistic topic models. Communications of the ACM, 55(4), 77–84
Büschken,J., Allenby, G.M. (2016). Sentence-based text analysis for customer reviews. Marketing Science, 35(6), 953–75.
Butler, J.C., Dyer, J.S,, Jia, J., Tomak, K. (2008). Enabling e-transactions with multi-attribute preference models. European Journal of Operational Research, 186(2), 748–65.
Chatterjee, P., (2001). Online reviews: Do consumers use them?, Advances in Consumer Research. Vol. 28, 129-133.
Corrente, S., Greco, S., Słowiński, R. (2012). Multiple Criteria Hierarchy Process in Robust Ordinal Regression. Decision Support Systems, 53(3), 660-674.
Corrente, S., Greco, S., Kadziński, M., Słowiński, R. (2013). Robust ordinal regression in preference learning and ranking. Machine Language, 93(2), 381–422.
Denguir-Rekik, A., Montmain, J., Mauris, G. (2009). A possibilistic-valued multi-criteria decision-making support for marketing activities in e-commerce: Feedback based diagnosis system. European Journal of Operation Research, 195(3), 876–88.
Doumpos, M., & Zopounidis, C. (2002). Multicriteria Decision Aid Classification Methods. New York, USA: Kluwer Academic.
Duan, W., Gu, B., Whinston, A. B., (2008). Do online reviews matter? – An empirical investigation of panel data. Decision Support Systems, 45(4), 1007-1016.
Farias, V. F., Li, A. A. (2019). Learning preferences with side information. Management Science, 65(7), 3131-3149.
Godes, D., Mayzlin, D., (2004). Using Online Conversations to Study Word-of Mouth Communication. Marketing Science, 23(4), 469-631.
Goodman, J. A., (2009). Strategic Customer Service, AMACOM.
Greco, S., Kadziński, M., Mousseau, V., Slowiński, R. (2012) Robust ordinal regression for multiple criteria group decision: UTA-GROUP and UTADIS-GROUP. Decision Support Systems, 52(3), 549-561
Greco, S., Mousseau, V., Slowiński, R. (2010). Multiple criteria sorting with a set of additive value functions. European Journal of Operational Research, 207(3), 1455–70.
Griffiths, T. L., Steyvers, M. (2004). Finding Scientific Topics. Proceedings of National Academy of Sciences, 101(1), 5228-35.
Guo, M., Liao, X., Liu, J. (2019). A progressive sorting approach for multiple criteria decision aiding in the presence of non-monotonic preferences. Expert Systems with Application, 123, 1–17.
Guo, M., Liao, X., Liu, J., Zhang, Q. (2020). Consumer preference analysis: A data-driven multiple criteria approach integrating online information. Omega, 96(6), 102074.
Hernández-Ortega, B., (2020). When the performance comes into play: The influence of positive online consumer reviews on individuals' post-consumption responses. Journal of Business Research, Vol. 113, 422-435.
Hu, M. & Liu, B. (2006). Opinion extraction and summarization on the web. Paper presented at the 21st National conference on artificial intelligence, Boston, Massachusetts.
Hu, N., Liu, L., & Zhang, J. J. (2008), Do online reviews affect product sales? The role of reviewer characteristics and temporal effects, Information Technological Management, Vol. 9, pp. 201-214. Bi, J., Liu, Y., Fan, Z., Zhang, J. (2019), Wisdom of crowds: Conducting importance-performance analysis (IPA) through online reviews, Tourism Management, Vol. 70, 460-478.
Jacquet-Lagreze, E., & Siskos, J. (1982). Assessing a set of additive utility functions for multicriteria decision-making, the UTA method. European Journal of Operational Research, 10(2), 151–64.
Janjevic, M., Winkenbach, M. (2020). Characterizing urban last-mile distribution strategies in mature and emerging e-commerce markets. Transportation Research Part A: Policy and Practice, Vo1 133, 164-169
Jo, Y. & Oh, A. H. (2011). Aspect and sentiment unification model for online review analysis. Paper presented at the 4th ACM International conference on web search and data mining, Hongkong, China.
Kadziński, M., Tervonen, T. (2013). Robust multi-criteria ranking with additive value models and holistic pair-wise preference statements. European Journal of Operational Research, 228(1), 169-180.
Keeney, R.L., Raiffa, H. (1993). Decisions with multiple objectives : preferences and value tradeoffs. Cambridge University Press.
Kim, S., & Kang, J., 2018, Analyzing the discriminative attributes of products using text mining focused on cosmetic reviews, Information Processing and Management, Vol. 54, pp. 938-957.
Korb, K. B., & Nicolson, A. E. (2011). Bayesian Artificial Intelligence. USA: Taylor & Francis.
Lakiotaki, K., Matsatsinis, N. F., Tsoukias, A. (2011). Multicriteria user modeling in recommender systems. IEEE Intelligent System, 26(2), 64–76.
Liu, Y., (2006). Word-of-Mouth for Movies: Its Dynamics and Impact on Box Office Revenue. Journal of Marketing, 70(3), 74-89
Martin, A., Zarate, P., Camillieri, G.. (2017). A Multi-Criteria Recommender System Based on Users’ Profile Management. Multiple criteria decision making, Springer, p. 83–98.
Mauri, A. G., Minazzi, R. (2013). Web reviews influence on expectations and purchasing intentions of hotel potential customers. International Journal of Hospitality Management, Vol. 34, 99-107.
Roberts, M. E., Stewart, B. M., Tingley, D., Lucas, C. (2014). Structural Topic Models for Open-Ended Survey Responses. American Journal of Political Science, 58(4), 1064-82.
Siskos, Y., Grigoroudis, E., Matsatsinis, N. F. (2005). UTA Methods. Multiple Criteria Decision Analysis: State of the Art Surveys. Springer, p. 297-334.
Solomon, M. R., (2017). Consumer Behavior: Buying, Having, and Being. USA: Pearson Education.
Sun, Q., Niu, J., Yao, Z., & Yan, H. 2019, Exploring eWOM in online customer reviews: Sentiment analysis at a fine-grained level, Engineering Applications of Artificial Intelligence, Vol. 81, pp. 68-78.
Wallenius, J., Dyer, J.S., Fishburn, P.C., Steuer, R.E., Zionts, S., Deb, K. (2008). Multiple criteria decision making, multi-attribute utility theory: recent accomplishments and what lies ahead. Management Science, 54(7), 1336–49.
Wiebe, J., Ellen R. (2005). Creating Subjective and Objective Sentence Classifiers from Unannotated Texts. Computational Linguistics and Intelligent Text Processing, 486–97.
Xiao, S., Wei, C. P., Dong, M. (2016). Crowd intelligence: analyzing online product reviews for preference measurement. Information & Management, 53(2), 169–82.
Ye, K., Li, L., Guo, M., Qian, Y., Yuan, H. (2015). Summarizing product aspects from massive online review with word representation. Paper presented at the 8th International Conference on Knowledge Science Engineering and Management, Chongqing, China.
Yi, X., Allan, J. (2009). A Comparative Study of Utilizing Topic Models for Information Retrieval. Paper presented at the 31th European Conference on Information Retrieval Research, Toulouse, France.