隨著社群網站興起，越來越多業主與名人選擇以Facebook作為廣告曝光或更進一步與粉絲接觸並培養感情的重要媒介，粉絲團的經營儼然成為不可忽視的市場行銷。然而粉絲的好惡往往是抽象而且難以捉摸的，如何藉由過去的文章中找到能吸引粉絲目光並且大為分享或推廣的關鍵字，便成為每個粉絲團經營者亟欲了解的經營祕訣。
本研究以網路作家我是小生所經營的粉絲團為例，以感性工學之研究架構輔以文字探勘技術LDA(Latet Dirichlet Allocation)篩選關鍵感性詞並彙整為寫手風格的主題，並感性工學配合以語意差異法設計問卷。根據受測者背景資料做不同族群的統計分析，找出不同族群的喜好，從而建立文創家的品牌價值，以及針對不同目標族群與不同議題時的撰文取向。
我們期望藉由這樣的研究方式，建立一套可依循的分析模式，將文字當作可分析的產品，將粉絲的感受作為需求，以分析模式做為橋樑，讓兩者之間能充分的結合、發想，作為粉絲團經營的參考依據。

With the global rise of social network, business owners and famous stars use Facebook as a channel to explore potential customers and engage with fans. Thus, fan page managing becomes an essential marketing strategy. However, fans’ interest and feeling are usually undetectable. Owners of fan pages are eager to know the key words that can touch the true demand and emotion of their fans. In order to realize the emotion when fans reading articles, we study the popular posts on the well-known authors of Littlelifer. In the framework of Kansei Engineering, we convert the abstract writing style into numbers of evaluable topics by LDA, quantizing the feeling of fans into Semantic Differential Scale. Combining quantized feeling of fans and evaluable topics of the author enables us to distinguish the effect of different topics, mining the exact feeling of readers, strengthen the engagement with fans, exploring the potential customers. In conclusion, this research establishes an analytical model that can be followed by researchers of online marketing.

1. 英文參考文獻

Aizawa, A. (2003). An information-theoretic perspective of tf–idf measures.Information Processing & Management, 39(1), 45-65.
Blei, D. M., Ng, A. Y., & Jordan, M. I. (2003). Latent dirichlet allocation. Journal of machine Learning research, 3(Jan), 993-1022.
Blei, D. M., & Lafferty, J. D. (2007). A correlated topic model of science. The Annals of Applied Statistics, 17-35.
Chen, J., Chen, X., Kauffman, R. J., & Song, X. (2009). Should we collude? Analyzing the benefits of bidder cooperation in online group-buying auctions.Electronic Commerce Research and Applications, 8(4), 191-202.
Deerwester, S., Dumais, S. T., Furnas, G. W., Landauer, T. K., & Harshman, R. (1990). Indexing by latent semantic analysis. Journal of the American society for information science, 41(6), 391.
Ding, C. H. (2005). A probabilistic model for latent semantic indexing. Journal of the American Society for Information Science and Technology, 56(6), 597-608.
Du, Y., & Tang, Y. (2014). Study on the Development of O2O E-commerce Platform of China from the Perspective of Offline Service Quality. International Journal of Business and Social Science, 5(4), 308-312.
Frawley, W. J., & Matheus, C. J. (1991). Knowledge discovery in databases (pp. 1-27). G. Piatetsky-Shapiro (Ed.). Menlo Park, CA: AAAI Press.
Girolami, M., & Kabán, A. (2003, July). On an equivalence between PLSI and LDA. In Proceedings of the 26th annual international ACM SIGIR conference on Research and development in informaion retrieval (pp. 433-434). ACM.
Hou, F., & Zhang, S. (2014, October). A Study on Group Buying of O2O Mode using Generalized Stochastic Petri Nets. In Management of e-Commerce and e-Government (ICMeCG), 2014 International Conference on (pp. 354-360). IEEE.
Hong, L., & Davison, B. D. (2010, July). Empirical study of topic modeling in twitter. In Proceedings of the First Workshop on Social Media Analytics (pp. 80-88). ACM.
Heise, D. R. (1970). The semantic differential and attitude research. Attitude measurement, 235-253.
Landauer, T. K., Foltz, P. W., & Laham, D. (1998). An introduction to latent semantic analysis. Discourse processes, 25(2-3), 259-284.
Li, J., & Mo, W. J. (2015). The O2O Mode in Electronic Commerce. development, 1, 3.
Li, C., Sycara, K., & Scheller-Wolf, A. (2010). Combinatorial coalition formation for multi-item group-buying with heterogeneous customers. Decision Support Systems, 49(1), 1-13.
Nelson-Field, K., Riebe, E., & Sharp, B. (2012). What’s not to ‘Like?’. Journal of Advertising Research, 52(2), 262-269.
Papadimitriou, C. H., Tamaki, H., Raghavan, P., & Vempala, S. (1998, May). Latent semantic indexing: A probabilistic analysis. In Proceedings of the seventeenth ACM SIGACT-SIGMOD-SIGART symposium on Principles of database systems (pp. 159-168). ACM.
Rogers, E. (2003). Diffusion of Innovations, 5th edn Free Press. New York.
Smitha N. (2013) Facebook material defined: Engagement rate [online]. Available from http://simplymeasured.com/blog/facebook-metrics-defined-engagement-rate/#sm.10s wcodp2dcx410om 1voge5tbed
Steyvers, M., & Griffiths, T. (2007). Probabilistic topic models. Handbook of latent semantic analysis, 427(7), 424-440.
Salton, G., & Buckley, C. (1988). Term-weighting approaches in automatic text retrieval. Information processing & management, 24(5), 513-523.
Yan, H. B., Huynh, V. N., Murai, T., & Nakamori, Y.(2008), Kansei evaluation based on prioritized multi-attribute fuzzy target-oriented decision analysis, Information Science, 178(21), 4080-4093

2. 中文參考文獻

邱莉燕(2014)，「大玩廣告創意：把社群媒體便行銷平台」，遠見雜誌12月刊，pp140-142
許景泰(2015)，「你，就是媒體：打造個人自媒體與企業經營成功術」，三采文化
張瑞山(2014)，感性知識萃取法於空間設計應用之研究，成功大學工業與資訊管理學 系碩士在職專班學位論文
洪黛芬與聶志高(2013)，商店外觀感性意向之語意評價研究-造型特徵與意向關聯性 之探討，建築學報84期，pp55-75
鐘任明、李維平與吳澤民(2005)，運用文字探勘於日內股價漲跌趨勢預測之研究
謝曼君(2014)，網路作家寫作風格與人氣指數分析之研究-以痞克邦部落格為例，臺灣 大學資訊管理學研究所學位論文
新浪網(2015)，網路寫手生存狀況：九成人沒錢拿，日更新近萬字 http://news.sina.com.tw/article/20151018/15358129.html
張育銘 與 鄧怡華 (2007)，由設計意圖中淺談感性工學 http://email.ncku.edu.tw/~em50190/ncku/196/d/d04.htm