在現今企業競爭激烈的環境中，企業提昇競爭優勢的根源在於瞭解目標客群對於產品的喜好與需求。過去企業主要透過銷售人員與消費者之間的訪談或問卷調查等方式來暸解消費者喜好與需求，但隨著網際網路發達以及討論社群的普及，越來越多消費者會在網路上發表產品評論，這也意味著企業有著另一種不同的管道可以更客觀地暸解消費者對於產品的喜好與需求。因此，如何協助企業有效地從大量的目標客群網路口碑中分析出有價值的決策資訊實為現今企業提昇競爭優勢的重要研究課題之一。
本研究目的在於針對目標客群網路口碑發展一理想產品規格勾勒機制，以協助企業快速地將目標客群對於產品的喜好與需求轉為產品規劃之依據，進而縮短產品上市時間(Time to Market)以及提升目標客群對於產品之滿意度。針對上述目的，本研究主要研究項目包括: (i)目標客群網路口碑之理想產品規格勾勒流程設計，(ii)目標客群網路口碑之理想產品規格勾勒方法發展與(iii)目標客群網路口碑之理想產品規格勾勒機制實作。其中，目標客群網路口碑之理想產品規格勾勒方法發展主要包括目標客群之網路口碑篩選、目標客群之網路口碑分析與目標客群網路口碑之理想產品規格評量。

In today's highly competitive business environment, the primary way an enterprise enhances its competitive advantage is to understand target customers’ preferences and needs for the products. In the past, visiting customers in person or conducting questionnaires were the main measures an enterprise took to grasp customers’ preferences and needs. With the development of Internet and the rising popularity of community websites, more and more consumers will post the Product Review online, which offers enterprises another way to grip consumers’ preferences and needs for products more objectively. As a result, how to assist enterprises to effectively analyze a large number of target customers’ eWOM on the Internet and further extracting decision-making information is one of an enterprise’s major studies on increasing its competitive capability.

The purpose of the study lies in designing an IT-based method that can outline desirable specifications on the basis of target customers’ eWOM. Such method is able to help an enterprise quickly adapt consumers’ preferences and demands for products to product planning. In so doing, not only can an enterprise shorten its time to market, but it can also raise the target customers’ satisfaction for the products. In accordance with above purposes, the main research projects include: (i) the design of a desirable product specification identification process for target customers’ eWOM, (ii) the development of desirable product specification identification techniques for target customers’ eWOM, and (iii) the implement of desirable product specification identification techniques for target customers’ eWOM.

1. Arndt Johan A., Role of Product-Related Conversations in the Diffusion of a New Product. Journal of Marketing Research, Vol. 4, 1967, pp. 291-295.
2. Changqin Quan and Fuji Ren, Unsupervised product feature extraction for feature-oriented opinion determination, Information Sciences, Vol. 272(10), 2014, pp. 16-28
3. C. L. Goh, M. Asahara and Y. Matsumoto.,Chinese Word Segmentation by Classification of Characters, International Journal of Computational Linguistics and Chinese Language Processing, Vol. 10(3) 2005, pp. 381-396,
4. Ghani R., Probst K., Liu Y., Krema M., and Fano A., Text mining for product attribute extraction. SIGKDD Explorations, 2006, Vol. 8(1), pp. 41–48.
5. Godes D., Mayzlin D., Chen Y., Das S., Dellarocas C., Pfeiffer B., Libai B., Sen S.,Shi M., Verlegh P. ,The Firm’s Management of Social Interactions, Marketing Letters, Vol. 16 (3),2005,pp. 415-428.
6. Hennig-Thurau T., Gwinner K. P., Walsh G., & Gremler D., Electronic word-of-mouth via consumer-opinion,platforms: What motivates consumers to articulate themselves on the internet?, Journal of Interactive,Marketing, Vol. 18(1), 2004, pp. 38-52
7. Hongyan Liu, Jun He, Tingting Wang and Wenting Song, Xiaoyang Du, Combining user preferences and user opinions for accurate recommendation, Electronic Commerce Research and Applications, Vol. 12(1), 2013, pp. 14-23
8. H. P. Zhang, H. K. Yu, D. Y. Xiong and Q. Liu., HHMM-based Chinese Lexical Analyzer ICTCLAS, In Proceedings of Second SIGHAN Workshop on Chinese Language Processing, 2003, pp. 187–187
9. Hu M., and Liu B., Mining and summarizing customer reviews. In Proceedings of the Tenth ACM SIGKDD International Conference on Knowledge Discovery and DataMining, Seattle, WA, August 22–25, 2004, ACM Press, New York, NY, 2004, pp. 8–17
10. Jingbo Zhu, Huizhen Wang, Muhua Zhu, Benjamin K. Tsou, Matthew Ma ,Aspect-Based Opinion Polling from Customer Reviews, IEEE Transactions on Affective Computing, Vol. 2(1), 2011, pp. 37-48.
11. Jiaming Zhan, Han Tong Loh and Ying Liu, Gather customer concerns from online product reviews, Expert Systemswith Applications, Vol. 32(2), 2008, pp. 2107-2115
12. J.N Lewis and R Teratanavat and J Beckley and M.A Jeltema., “Using a Consumer-driven Rapid Product Navigation Process to Develop an Optimal Product” Food Quality and Preference, Vol. 21(8), 2010, pp. 1052-1058.
13. Kruskal, J. B., and Wish, M., Multidimensional Scaling, Sage University Paper series on Quantitative Application in the Social Sciences,1978, pp. 07-11.
14. Kushal Bafna and Durga Toshniwal, Feature based Summarization of Customers’ Reviews of Online Products, Procedia Computer Science, Vol. 22, 2013, pp 142–151
15. Liu B., Hu M., and Cheng J., Opinion observer: Analyzing and comparing opinionson the Web. In Proceedings of the 14th International Conference on World WideWeb, Chiba, Japan, 2005, ACM Press, New York, NY, 2005, pp. 342–351.
16. M. Asahara, C.L. Goh, X. Wang and Y. Matsumoto., Combining Segmenter and Chunker for Chinese Word Segmentation, In Proceedings of Second SIGHAN Workshop on Chinese Language Processing, 2003, pp. 144–147
17. Moutinho L., Brownlie, D.,The Stratlogic Approach to Analysis of Competitive Position, Market Intelligence & Planning, Vol 12(4), 1994, pp. 15-21
18. N. Xue., Chinese Word Segmentation as Character Tagging, International Journal of Computational Linguistics and Chinese,2005, pp. 29–48
19. N. Xue and L. Shen, Chinese Word Segmentation as LMR Tagging, In Proceedings of Second SIGHAN Workshop on Chinese Language Processing,2003, pp. 176–179
20. Paula Fitzgerald Bone, Word-of-mouth effects on short-term and long-term product judgments, Journal of Business Research, Vol. 32(3), 1995, pp. 213–223
21. Popescu A., and Etzioni O. P., Extracting product features and opinions from reviews. Natural Language Processing and Text Mining, 2007, pp. 9–28.
22. Ries A.,Trout J., Sabin W., & Hamerling M.,Positioning: The battle for your mind:McGraw-Hill New Youk, 1986
23. Robert G. Cooper ,Elko J. Kleinschmidt, An Investigation into the New Product Process:Steps, Deficiencies, and Impact, Journal of Product Innovation Management, Vol. 3, 1986, pp71-85
24. Sandra Garcia Esparza, Michael P. O’Mahony and Barry Smyth, Mining the real-time web A novel approach to product recommendation, Knowledge-Based Systems, Vol. 29,2012, pp. 3-11
25. Tianfang Yao, Siwei Peng, “A Study of the Classification Approach for Chinese Subjective and Objective Texts”, Third Conference on National Information Retrieval and Content Security Academic,2007, pp. 117-123
26. Wei Chen, Yanquan Zhou and Xin Wang, Chinese Subjective Sentence Extraction Based on Dictionary and Combination Classifiers, Physics Procedia, Vol. 22, 2011, pp. 593-601
27. Wenhao Zhang, Hua Xu and Wei Wan, Weakness Finder: Find product weakness from Chinese reviews by using aspects, Expert Systems with Applications, Vol. 39(11), 2012, pp. 10283–10291
28. X. Lu.,Towards a Hybrid Model for Chinese Word Segmentation, In Proceedings of Fourth SIGHAN Workshop on Chinese Language Processing,2005, pp. 189–192
29. X. Wan, Using Bilingual Knowledge and Ensemble Techniques for Unsupervised Chinese Sentiment Analysis, Proc. Conf. Empirical Methods in Natural Language Processing, 2008, pp. 553-561
30. 東東線上同義詞典, http://www.kwuntung.net/synonym/
31. 高聖傑, 詞性組合輔助之中文網路口碑評價分析技術研發, 國立成功大學, 2014, pp. 1-48
32. 洪儷瑜, 陳佩盈, 中文句型類型整理, http://goo.gl/YJAPBD, 2005
33. 教育部辭典, http://dict.revised.moe.edu.tw/
34. 游和正, 領域相關詞彙及性分析及文件情緒分類之研究台灣大學, 2012, pp. 57
35. CKIP中文斷詞系統, http://ckipsvr.iis.sinica.edu.tw/