進階搜尋


   電子論文尚未授權公開,紙本請查館藏目錄
(※如查詢不到或館藏狀況顯示「閉架不公開」,表示該本論文不在書庫,無法取用。)
系統識別號 U0026-0208201618490000
論文名稱(中文) 社群粉絲之感性需求分析研究
論文名稱(英文) A Study of Kansei Demand of Fans in Social Media
校院名稱 成功大學
系所名稱(中) 資訊管理研究所
系所名稱(英) Institute of Information Management
學年度 104
學期 2
出版年 105
研究生(中文) 何健偉
研究生(英文) CHIEN-WEI HE
學號 R76034111
學位類別 碩士
語文別 英文
論文頁數 48頁
口試委員 指導教授-李昇暾
口試委員-林清河
口試委員-耿伯文
口試委員-陳志全
中文關鍵字 感性工學  主題模型  文字探勘  需求分析 
英文關鍵字 Kansei engineering  topic model  text mining  demand analysis 
學科別分類
中文摘要 隨著網路科技的逐漸發達,人們花費越來越多的時間在社群媒體上,如Facebook, Twitter, Tumblr等等。也因為社群媒體的興盛,使得人們越來越容易分心,對公司與想要成名的人而言,如何抓住人們的注意力成為了一個很關鍵的議題。在過去,如果你或是你的公司想要成名,只要選擇在傳統的電視媒體、新聞報紙打廣告就可以了。而現今,你必須要了解人們的需求,並透過新興的社群媒體來接觸他們才有成名的機會。如何了解人們的需求又是一個難題,最普遍的方式大概是執行市場調查、問卷、焦點團體訪談等,但這些方式不但耗費時間也花費大量的人力。
在本研究當中,我們結合了文字探勘與感性工學來分析人們對於療癒型作家的需求。首先,我們從Facebook的粉絲專頁中蒐集欲探討對象之相關數據,包括數值型態的數據(如按讚、分享、留言等數量)與文字資料(所寫之文章)。接著我們藉由Latent Dirichlet Allocation (LDA)來自動萃取出該作家的寫作主題,設定主題數從4~8,經由專家看過之後認為主題數選擇4所得出之結果最能代表該作家之寫作風格。然後挑選出八組的感性詞組搭配所前一步驟所得之4個主題來進行語意差異問卷法找出讀者對不同主題文章之感性需求。本研究建立之感性-主題關聯可以有效的幫助到作家未來針對不同的讀者需求來調整寫作之主題。最後,我們利用監督式的LDA建立出一個預測模型,可以在作家寫完文章之後就知道本篇文章的受歡迎程度為何。
英文摘要 As the booming of the Internet era, people spend more and more time on social media, such as Facebook, Twitter, Tumblr, etc. How to catch people’s eye is becoming a critical issue for companies and celebrities, since it’s an era of distractions. In the past, if you or your company want to become popular, simply spend money on traditional media, like newspaper, TV commercial. Now, you need to know audiences’ need, then utilize the new social media platform to reach those specific audiences.
There is another question raised, that is how to know the demand of customers (namely audiences)? Most common used methods are conducting a market survey, including questionnaires and focus group. However, it’s not only wasting time but also effort-consuming.
In this research, we combine text mining technique and Kansei engineering to analysis audiences’ demand. First, we collect data from Facebook Fan Pages, including numerical data (number of likes, shares, comments) and text data (posts’ content). Then extract the topics by using Latent Dirichlet allocation (LDA). Next, Experts will give eight pairs of Kansei words that most relevant for the articles. After that, we conduct semantic differential questionnaire to find the relationship between topics and Kansei words. The relationship can be helpful to writers to know the demand of audience. Finally, we use supervised LDA to predict the popularity of posts.
論文目次 摘要 I
Abstract II
誌謝 III
Table of Content IV
List of Tables VI
List of Figures VII
Chapter 1 Introduction 1
1.1 Background and Research Motivation 1
1.2 Research Objective 3
1.3 Process of the Research 4
Chapter 2 Literature Review 5
2.1 Text Mining 5
2.2 Kansei Engineering 7
2.3 Topic Model 9
2.3.1 Probabilistic Latent Semantic Analysis 9
2.3.2 Latent Dirichlet Allocation 12
2.3.3 Supervised LDA 17
Chapter 3 Research Method 18
3.1 Data Collection 18
3.2 Data Preprocessing 20
3.3 Kansei Extraction 22
3.4 Topic Extraction 23
3.5 Semantic Differential 26
Chapter 4 Experiment and Analysis 27
4.1 Experiment 27
4.1.1 Numerical Data 28
4.1.2 Textual Data 29
4.1.3 Topics Generating 30
4.1.4 Semantic Differential Questionnaire 34
4.2 Analysis 36
4.2.1 ANOVA 38
4.2.2 Topic-Kansei Relationship 41
4.2.3 Prediction 42
Chapter 5 Conclusion and Future Work 45
5.1 Conclusion 45
5.2 Future Work 46
Reference 47
參考文獻 Blei, D., & Lafferty, J. (2006). Correlated topic models. Advances in neural information processing systems, 18, 147.
Blei, D. M., & Lafferty, J. D. (2006). Dynamic topic models. Paper presented at the Proceedings of the 23rd international conference on Machine learning.
Blei, D. M., Ng, A. Y., & Jordan, M. I. (2003). Latent dirichlet allocation. the Journal of machine Learning research, 3, 993-1022.
Girolami, M., & Kabán, A. (2003). On an equivalence between PLSI and LDA. Paper presented at the Proceedings of the 26th annual international ACM SIGIR conference on Research and development in informaion retrieval.
Griffiths, T. L., & Steyvers, M. (2004). Finding scientific topics. Proceedings of the National Academy of Sciences, 101(suppl 1), 5228-5235.
Hofmann, T. (1999). Probabilistic latent semantic indexing. Paper presented at the Proceedings of the 22nd annual international ACM SIGIR conference on Research and development in information retrieval.
Hofmann, T., Puzicha, J., & Jordan, M. I. (1999). Learning from dyadic data. Advances in neural information processing systems, 466-472.
Jin, J., Ji, P., Liu, Y., & Johnson Lim, S. C. (2015). Translating online customer opinions into engineering characteristics in QFD: A probabilistic language analysis approach. Engineering Applications of Artificial Intelligence, 41, 115-127. doi:10.1016/j.engappai.2015.02.006
Jordan, M. I., Ghahramani, Z., Jaakkola, T. S., & Saul, L. K. (1999). An introduction to variational methods for graphical models. Machine learning, 37(2), 183-233.
Llinares, C., & Page, A. (2007). Application of product differential semantics to quantify purchaser perceptions in housing assessment. Building and environment, 42(7), 2488-2497.
Llinares, C., & Page, A. F. (2011). Kano’s model in Kansei Engineering to evaluate subjective real estate consumer preferences. International Journal of Industrial Ergonomics, 41(3), 233-246.
Matsubara, Y., & Nagamachi, M. (1997a). Hybrid Kansei engineering system and design support. International Journal of Industrial Ergonomics, 19(2), 81-92.
Matsubara, Y., & Nagamachi, M. (1997b). Kansei analysis support system and virtual kes. Kansei Engineering I, Kaibundo, 53-62.
Mcauliffe, J. D., & Blei, D. M. (2008). Supervised topic models. Paper presented at the Advances in neural information processing systems.
McKnight, W. (2005). Text Data Mining in Business Intelligence. Information Management Magazine. Retrieved from http://www.information-management.com/issues/20050101/1016487-1.html
MIC. (2014). 96.2%台灣網友近期曾使用社交網站. Market Intelligence & Consulting Institute. Retrieved from http://mic.iii.org.tw/intelligence/pressroom/pop_pressfull.asp?sno=364
Minka, T., & Lafferty, J. (2002). Expectation-propagation for the generative aspect model. Paper presented at the Proceedings of the Eighteenth conference on Uncertainty in artificial intelligence.
Mrva, D., & Woodland, P. C. (2006). Unsupervised language model adaptation for Mandarin broadcast conversation transcription. Paper presented at the INTERSPEECH.
Nagamachi, M. (1996). Introduction of Kansei engineering. Japan Standard Association, Tokyo.
Nagamachi, M. (2002). Kansei engineering as a powerful consumer-oriented technology for product development. Applied ergonomics, 33(3), 289-294.
Nagasawa, S. (1997). Kansei evaluation using fuzzy structural modeling. Paper presented at the Proceedings of the 1st Japan-Korea symposium on kansei engineering—consumer oriented product development technology on Kansei engineering I.
Popescu, O., & Strapparava, C. (2014). Time corpora: Epochs, opinions and changes. Knowledge-Based Systems, 69, 3-13.
Sato, N., Anse, M., & Tabe, T. (2007). A Method for Constructing a Movie-Selection Support System Based onKansei Engineering Human Interface and the Management of Information. Methods, Techniques and Tools in Information Design (pp. 526-534): Springer.
Steyvers, M., & Griffiths, T. (2007). Probabilistic topic models. Handbook of latent semantic analysis, 427(7), 424-440.
Tam, Y.-C., & Schultz, T. (2005). Dynamic language model adaptation using variational Bayes inference. Paper presented at the INTERSPEECH.
論文全文使用權限
  • 同意授權校內瀏覽/列印電子全文服務,於2021-12-31起公開。


  • 如您有疑問,請聯絡圖書館
    聯絡電話:(06)2757575#65773
    聯絡E-mail:etds@email.ncku.edu.tw