本研究的動機希望能給予清潔用品採購的消費者提供建議，研究的資料來源主要是社群媒體的文章，經過行為模型的文獻回顧後，我們發現知覺品質與體驗價值對滿意度有正面影響，滿意度的提升對忠誠度也有提升效果，而推薦度是忠誠度體現的一種方式，所以我們將行為模型拆為15個構面，並以此觀察對推薦度的影響，我們使用文字探勘工作流程平台來處理文字資料；採用文字分析工具Guided LDA來找出每篇文章主題標籤，再利用Python工具將同一個品牌聚合再一起，並計算各品牌在不同構面的分數，預期在分析後能得到關於主題構面對推薦度的影響，以及同類型產品不同品牌在同一構面上的比較；最後使用R語言來做視覺化呈現。
研究發現優惠價格對推薦度有正面影響，折扣活動對推薦度有正面影響，但並非所有構面對推薦度都有正面影響。在既有理論與實務之間的關係，本研究結果價格與活動對推薦度有顯著且正面的影響，在實務面的例子有廠商所舉辦的集點活動，點數累積的過程可以讓消費者保持忠誠度，而消費者也會因忠誠度而得到回饋；此外香味和廣告也是顯著但為負相關，顯示消費者對於太香或廣告過頭的產品會產生反感。本研究有別於以往之處在於兩點，第一點我們利用文字探勘的方式探討影響推薦度關鍵因素，與傳統常以問卷形式調查不同，第二點我們以模型引導主題分布結果做因素分析，過去的文獻是以主題分布結果做因素分析。

There are many types of cleaning brands in the market, and the purpose of this research is to identify the feature of products that mostly concern the consumers using Electronic Word-of-Mouth (eWOM).
From the literature, we found that perceived quality and experience value have a positive impact on user satisfaction, and the improvement of satisfaction can also increase loyalty (recommendation). Therefore, we link these two behavior models as this study’s main model and expand them to 15 factors. For the Social Media Analytics process, we use the Text Mining Workflow System for processing textual data, semi-supervised machine learning tool Guided LDA for identify the 15 factors, and R for visualization.
The results of the study show that the factors with positive impacts are the price, and the discount activity, whereas scent and advertisement show negative impacts. We use text mining to explore the key factors that impact on the satisfaction, which is different from the traditional survey of questionnaires. In addition, we use the model to guide topics distribution to do factor analysis which is different from the past work.

目 錄
論文審定書 i
誌 謝 ii
摘 要 iii
Abstract iv
目 錄 v
圖 次 vii
表 次 viii
第一章 緒論 1
1-1 研究背景 1
1-2 研究動機 2
1-3 研究目的 2
1-4 論文結構 3
第二章 文獻探討 4
2-1 行為模型 4
2-2 主題模型介紹 6
2-3 Guided LDA介紹 8
2-4 文字探勘應用於滿意度調查 10
第三章 實驗設計 12
3-1 研究模型架構 12
3-2 文字探勘 14
3-2-1 資料來源 14
3-2-2 資料處理方式 16
3-2-3 導入Guided-LDA的前處理DTM 18
3-2-4 Guided-LDA Model Fit過程 19
3-3 觀察各品牌構面與迴歸 22
3-3-1 品牌構面 22
3-3-2 資料正規化 22
3-3-3 分析迴歸 24
第四章 研究分析 25
4-1 主題模型分析結果 25
4-1-1 Guided LDA分析 25
4-1-2 依據品牌聚合結果 28
4-2 數值分析 31
4-2-1 數值迴歸 31
4-2-2 因素分析 33
4-2-3 信度分析 35
第五章 結論 36
5-1 研究發現 36
5-2 管理意涵 37
5-3 未來展望 38
5-4 補充資料 39
參考文獻 40
Appendix Ⅰ、實驗聚合結果 42
Appendix Ⅱ、實驗迴歸參數 43
Appendix Ⅲ、15個構面訓練後與應變數(Y)的回歸結果 44
Appendix Ⅳ、聚合結果的熱力分析圖 45
Appendix Ⅴ、各構面(Factors)的相關性熱點圖 46
Appendix Ⅵ 、固定種子字數目的訓練結果，seed_confidence=0.15 47
Appendix Ⅶ、固定種子字數目的訓練結果，seed_confidence=0.10 49

參考文獻
Bauer, H. H., Grether, M., & Leach, M. (2002). Building customer relations over the Internet. Industrial Marketing Management, 31(2), 155-163.
Cardozo, R. N. (1965). An experimental study of customer effort, expectation, and satisfaction. Journal of marketing research, 2(3), 244-249.
Chatterjee, S., Goyal, D., Prakash, A., & Sharma, J. (2021). Exploring healthcare/health-product ecommerce satisfaction: A text mining and machine learning application. Journal of Business Research, 131, 815-825.
Chen, S.-C., & Lin, C.-P. (2015). The impact of customer experience and perceived value on sustainable social relationship in blogs: An empirical study. Technological forecasting and social change, 96, 40-50.
Griffin, J. (1995). Customer loyalty. Esensi.
Jagarlamudi, J., Daumé III, H., & Udupa, R. (2012). Incorporating lexical priors into topic models. Proceedings of the 13th Conference of the European Chapter of the Association for Computational Linguistics,
Lim, M. K., Li, Y., & Song, X. (2021). Exploring customer satisfaction in cold chain logistics using a text mining approach. Industrial Management & Data Systems.
Lucini, F. R., Tonetto, L. M., Fogliatto, F. S., & Anzanello, M. J. (2020). Text mining approach to explore dimensions of airline customer satisfaction using online customer reviews. Journal of Air Transport Management, 83, 101760.
Ramage, D., Hall, D., Nallapati, R., & Manning, C. D. (2009). Labeled LDA: A supervised topic model for credit attribution in multi-labeled corpora. Proceedings of the 2009 conference on empirical methods in natural language processing,
Reichheld, F. F., & Covey, S. R. (2006). The ultimate question: Driving good profits and true growth (Vol. 211). Harvard Business School Press Boston.
Sashi, C., Brynildsen, G., & Bilgihan, A. (2019). Social media, customer engagement and advocacy: An empirical investigation using Twitter data for quick service restaurants. International Journal of Contemporary Hospitality Management.
Schmitt, B. (1999). Experiential marketing. Journal of marketing management, 15(1-3), 53-67.
Schmitt, B. H. (2010). Customer experience management: A revolutionary approach to connecting with your customers. John Wiley & Sons.
Yuan, Y.-H. E., & Wu, C. K. (2008). Relationships among experiential marketing, experiential value, and customer satisfaction. Journal of Hospitality & Tourism Research, 32(3), 387-410.
Zeithaml, V. A. (1988). Consumer perceptions of price, quality, and value: a means-end model and synthesis of evidence. Journal of Marketing, 52(3), 2-22.
吳佳倩. (2018). 以Airbnb顧客評論分析服務品質與顧客滿意度 東吳大學]. 台北市.
曾光華. (2021). 消費者行為：洞察生活、掌握行銷 (4/e ed.). 前程文化.
劉明德, & 梅國忠. (2011). 網站體驗行銷, 體驗價值, 顧客滿意度與顧客忠誠度關係之探討. 行銷科學學報, 7(2), 129-153.