為因應消費者多屏跨螢與重視互動性的網路使用習慣，數位行銷工具與手法推陳出新，將數位行銷帶入導致數位廣告全球競爭趨勢變遷異常快速，消費者對於廣告訴求內容的需求也越來越難以掌握，對於廣告企業主如何因應這樣的趨勢，已經成為商品或是企業廣告的成敗關鍵。廣告前測是一種客製化的廣告研究類型，通常以廣告主需求設計並進行市場調查，以瞭解受眾對於廣告或行銷方案的認知與感受，作為廣告策略之參考依據。本研究旨在探討如何運用社群網路輿情分析資料作為廣告執行前的預測。
自從資料大數據被提出後形成顯學加上AI人工智慧的崛起，企業主對於廣告策略是否能透過資料科學分析消費者需求，從大量的資料中分析出新的廣告策略，以找到新的銷售契機就成為各家公司從總經理室到研發製造單位、行銷部門甚至公關室與客服部門都非常重要的事情。一般而言我們知道包含數位廣告三大組成元素，即：廣告主(出資製作廣告內容以達成其行銷產品或是某種商業訴求目的者)、廣告平台(電視媒體、部落客、網路平台….等)，以及廣告受眾。這其中絕大部分的成本是來自於廣告主，所以對於廣告主而言如何運用廣告前測期望透過對廣告受眾的喜好或是觀點、認同度等做出分析，掌握能真正帶來消費人次(潛在買家)的網路文章，再藉由數位口碑與文字探勘技術對口碑文章進行解析，萃取真正影響消費意願的動機、訴求、觀點等。最後再透過這些資料對品牌熱詞、品牌線索發展、消費社群畫像，分析品牌力與品牌趨勢後建構足以輔助廣告行銷策的品牌力決策等，此一資訊架構將可協助廣告主降低廣告資源的浪費之外還可以針對不同平台的訴求不同價值觀點以增加廣告受眾者的認同進而增加營收與獲利。本研究將以實例說運用輿情分析在廣告前測上對於數位廣告的重要性。

SUMMARY
With the trend of the multi-screen and cross-platform customer behavior and informed customers, the marketing landscape has evolved dramatically in response to customer trend in digital advertising industry. The critical element leading to marketing success is to leverage right channel and content to connect with current and potential customers. Therefore, it is vital for businesses to develop more diverse and customer-centric marketing strategy to satisfy customer demands and expectations from different channels and platforms in the digital society.

The advertising pre-testing is a type of customized advertising research, which is conducted based on the requirements from business owner to obtain insights into customer perception and cognition toward the advertising. The output of pre-testing helps optimizing advertising before launching a campaign. The purpose of our research is to develop an opinion-analytics model of social media to assist advertising pre-testing in a more effective manner by application of text mining techniques.

Keyword: Digital Advertising; public Opinion Analysis; Big Data; Brand; eWOM

1. 中文參考文獻
[1] 劉鵬、王超(2016)。計算廣告：互聯網時代商業變現的市場與技術。佳魁資訊。
[2] DMA台灣數位媒體暨行銷應用協會(2017)。2017年數位廣告調查報告。
[3] 陳怡廷與欒錦榮(2012)。自然語言處理在口碑研究的應用。中華傳播學刊(22)，259-289。
[4] 劉文良(2015)。電子商務：雲端時代。碁峰出版社。
[5] 王遵智（2004）。網路口碑中個人專業與關係強度對購買決策的影響── 以電子郵件為例。國立台灣科技大學企管所碩士論文。
[6] 黃麗霞、張重昭（2003）。訊息來源、正面訊息與市場行家特質對網路訊 息傳喔之影響。電子商務研究，第 1 卷，第 1 期，頁 25－40。
[7] 范有寧；黃心惟；陳靜枝(2012)。以數位口碑為基礎之流行性商品銷售預測模式。資訊管理學報，19卷1期(2012 / 01 / 01)，P27 - 50。
[8] 大數據廣告(2015)。台灣行動廣告市場報告。Vpon 威朋。
[9] 楊學成、錢明輝（2006）。網上口碑對消費者決策的影響及啟示。當代經濟管理，第 28 卷，第 3 期，頁 27－31。
[10] 凱絡媒體報(2015)。台灣Z世代5A觀察。凱絡媒體週報。
[11] 練乃華、留淑芳（2003）。口耳相傳訊息之傳播及對消費者購買行為之影響。中山管理評論，第 11 卷，第 2 期，頁 283－307。
[12] 江義平與林志穎(2012)。網路品牌個性知覺定位分析探究。電子商務學報；14卷3期(2012 / 09 / 01)，P383 – 410。
[13] Arens, W. F., & 丁俊杰(2000)。當代廣告學。華夏出版社。
[14]詹智安(2016)。數位口碑與感性知識萃取法於精準行銷應用之研究以烘培業電子商務網站為例。國立成功大學工資所碩士論文。

2. 外文參考文獻
[1] Ahluwalia, R., & Gürhan-Canli, Z. (2000). The effects of extensions on the family brand name: An accessibility-diagnosticity perspective. Journal of Consumer Research, 27(2), 371-381.
[2] Alba, J. W., & Hutchinson, J. W. (1987). Dimensions of consumer expertise. Journal of Consumer Research, 13, 411-454.
[3]Anderson, James C., & Gerbing, David. (1988). Structural Equation Modeling in Practice: A Review and Recommended Two Step Approach. Psychological Bulletin, 103, 411-423.

[3] Bansal, H. S., & Voyer, P. A. (2000). Word-of-mouth processes within a service purchase decision context. Journal of Service Research, 3(2), 166-177.
[4] Bayus, B. L. (1985). Word of mouth: The indirect effects of marketing efforts. Journal of Advertising Research, 25(3), 31-39
[5] Bone, P. F. (1995). Word-of-mouth Effects on Short-term and Long-term Product Judgment. Journal of Business Research, 32, 213-223.
[6]Bristor, J. M. (1990). Enhanced explanations of word of mouth communications: The power of relationships. Research in Consumer Behavior, 4, 51-83.
[7]Cothey, V. (2002). A longitudinal study of World Wide Web user’s information-searching behavior. Journal of American Society for Information Science and Technology, 53(2), 67-78.
[8]Day, G. S. (1971). Attitude change, media, and word of mouth. Journal of Advertising Research, 11, 31-40.
[9] Digital Influence Index (2008). New Research Shows the Impact of the Internet on Consumer Behaviour in Europe. http://www.harrisinteractive.Com/news/ allnewsbydate.asp?NewsID=1314
[10] Dodds, W. B., Monroe, K. B., & Grewal, D. (1991). Effects of price, brand, and store information on buyers’ product evaluation. Journal of Marketing Research, 28, 307-319.
[11] Engel, J. R., Blackwell, R. D., & Miniard, P. W. (2001). Consumer behavior. Orlando Florida: Harcourt Inc.
[12] Flynn, L. R., & Goldsmith, R. E. (1993). Application of the personal involvement inventory in marketing. Psychology and Marketing, 10, 357-366.
[13] Gelb, B. D., & Sundaram, S. (2002). Adapting to word of mouse. Business Horizons, 45(4), 21-25.
[14] Goldsmith, R. and D. Horowitz (2006), Measuring Motivations for Online Opinion Seeking. Journal of Interactive Advertising, 6(2), 1-16.
[15] Hanson, W. (2000).Principles of Internet Marketing.Cincinnati:South-Western College.
[16] Hoffman, D. L., & Novak, T. P. (1996). Marketing in hypermedia computermediated environments: Conceptual foundations. Journal of Marketing, 60(3), 50-68.
[16] Kalakota, R. & Whinston, A. B. (1997). “Electronic commerce: a manager’s guide”, New York: Addison-Wesley Publishing
[17] Kwak, H., Fox, R. J., & Zinkhan, G. M. (2002). What products can be successfully promoted and sold via the Internet?. Journal of Advertising Research, 42(1), 23-38.
[10] Lee, S., Baker, J., Song, J., & Wetherbe, J. C. (2010, January). An empirical comparison of four text mining methods. In System Sciences(HICSS), 2010 43rd Hawaii International Conference on(1-10). IEEE.
[11] N. Hu; L. Liu; J. Zhang (Jan. 2007). Analyst Forecast Revision and Market Sales Discovery of Online Word of Mouth. System Sciences, 2007. HICSS 2007. 40th Annual Hawaii International Conference on(210C) . IEEE.
[12] Nunnally, J. C. (1978). Psychometric theory. New York: McGraw-Hill.
[13] Roger D Blackwell; Paul W Miniard; James F Engel (2006). Consumer behavior, 10. ed. Mason, Ohio : Thomson Business and Economics, cop.
[14] Salton, G., ＆ Buckley, C. (1988). Term-weighting approaches in automatic text retrieval. Information processing ＆ management, 24(5), 513-523.
[15] Scott Brinker & Laura McLellan (July 2014). The Rise of the Chief Marketing Technologist. Harvard Business Review. https://hbr.org/2014/07/the-rise-of-the-chief-marketing-technologist
[16] Singhal, Amit, Gerard Salton, and Chris Buckley (1995). Length normalization in degraded text collections. Cornell University.
[17] Sullivan, D. (2001). Document warehousing and text mining: techniques for improving business operations, marketing, and sales. John Wiley & Sons, Inc.
[18] T. Ogawa,Y. Nagai, M. Ikeda (2009). An ontological approach to designers’ idea explanation style: Towards supporting the sharing of kansei-ideas in textile design. Advanced Engineering Informatics Volume 23, Issue 2, April 2009, Pages 157–164
[19] Tanimoto, J., & Fujii, H. (2003). A study on diffusion characteristics of information on a human network analyzed by a multi-agent simulator. The Social Science Journal, 40(3), 479-85.
[21]Ott, J. S. (1996). Classic reading in organizational behavior. Belmont: Wadsworth Publishing Company
[22] Park, C. W., Jaworski, B. J., & MacInnis, D. J. (1986). Strategic brand conceptimage management. Journal of Marketing, 50(4), 135-145.
[23] Richardson, P. S., Dick, A. S., & Jain, A. K. (1994). Extrinsic and intrinsic cue effect on perceptions of store brand quality. Journal of Marketing Research, 58(4), 28-36
[24] Warrington, P., & Shim, S. (2000). An empirical investigation of the relationship between product involvement and brand commit-ment. Psychology & Marketing, 17(9), 761-782
[25] Westbrook, R. A. (1987). Product/consumption-based affective responses and postpurchase processes. Journal of Marketing Research, 24(3), 258-270.
[26] Yan, H. B., Huynh, V. N., Murai, T., ＆ Nakamori, Y. (2008). Kansei evaluation based on prioritized multi-attribute fuzzy target-oriented decision analysis. Information Sciences, 178(21), 4080-4093.
[27] Kirmani, A., & Zeithaml, V. (1993). Advertising, perceived quality, and brand image (pp. 143-62). Hillsdale, NJ: Lawrence Erlbaum Associates.
[28] Zaichkowsky, J. L. (1985). Measuring the involvement construct. Journal of Consumer Research, 12, 341-352.
[29] Kobayashi, V. B., Mol, S. T., Berkers, H. A., Kismihók, G., & Den Hartog, D. N. (2017). Text mining in organizational research. Organizational research methods, 1094428117722619.