隨著消費者的購買行為的改變，許多公司需要利用他們在線上的評論的分析，因為在線上消費者會將論壇評論視為購買商品前的商品訊息的渠道，其中也漸漸改變市場分析的方法，在這其中也有許多新的分析技術與工具出現，為決策者與市場分析人員提供決策工具。從論壇中萃取珍貴的資訊，其中最重要就是文字分析技術，而世界上有不同的人類語言在網路世界流動，在國外文字探勘技術已經發展純熟，尤其是英文語言，但是繁體中文還有很大進步空間，一方面是英文主要還是國際的語言，所以大多數研究還是專注在英文語言，另一方面是，繁體中文在技術分析上沒有像英文有固定的方式，使得繁體中文需要透過權重與詞頻來建立詞典才有效果的斷詞。而在數據分析的浪潮下，數據分析的方法提供給營業單位在不同文本挖掘技術上幫助分析。本研究將透過自然語言處理方法結合品牌權益構面在繁體中文上提供更有效的分析流程。
本研究將藉由自然語言技術作為支援來幫助從論壇中挖掘有意義的資訊，並且以品牌權益的構面概念去建立分析的繁體中文詞典，而本研究將透過自然語言處理技術的聲量分析、情緒分析、語意分析，並透過網絡視覺化分析分別對品牌權益的品牌知名度、認知品質與品牌聯想去進行衡量。此外，本研究也將對家電產業品牌去進行分析。
從研究結果得知透過文字分析可以有概念性地擷取競爭品牌的資訊，也可以利用對論壇文字的觀察來設計不同的詞典來加強分析的效果，其中透過洞察與品牌權益的觀念進行結合，可以提供給管理者與分析人員進行行銷與營運上的管理意涵。

With changing consumer behavior, companies increasingly analyze online reviews as consumers consider forum comments a crucial source of product information prior to purchasing. This shift has resulted in new market analysts techniques and tools that aid decision-making for managers and market analysts. Extracting valuable insights from forums heavily relies on text analysis, although there is still room for improvement in traditional Chinese compared to the well-developed English language. This study combines natural language processing and brand equity to offer a more effective analysis process in traditional Chinese.
Using sentiment analysis, semantic analysis, and volume analysis and visualized via interactive charts and dynamic network graphs, brand awareness, perceived quality, and brand association are measured. The focus is on analyzing brands in the home appliance industry.The findings demonstrate the effectiveness of text analysis in capturing information about competing brands. By designing customized dictionaries based on forum observations, analysis can be enhanced. The integration of insights and brand equity provides valuable implications for marketing and operational management.
Finally, future researchers can apply this process and analysis method to their own companies, utilizing volume analysis for brand awareness and sentiment analysis to gauge perceived quality. Semantic analysis reveals consumer associations with relevant products or concepts.

論文審定書i
中文摘要ii
Abstractiii
目錄iv
圖次v
表次vi
第一章 緒論1
第一節 研究背景1
第二節 研究動機與目的2
第二章 文獻探討3
第一節 文字探勘3
第二節 自然語言處理於競爭分析的相關研究4
第三節 品牌權益4
第三章 研究方法與步驟8
第一節 資料來源與分析流程建立8
第二節 資料處理10
第三節 分析方法14
第四章 研究結果15
第一節 聲量分析15
第二節 交叉分析22
第三節 情緒分析25
第四節 網絡語意分析27
第五章 研究結果與限制38
第一節 研究結論38
第二節 管理意涵與研究貢獻39
第三節 研究限制與展望40
參考文獻40

一、英文文獻
Andry Alamsyah, Vidya Salsabila Pambudi, and Dian Puteri Ramadhani (2022). Sentiment Correlation in News Network and Associated Market Movements Based on Co-occurrence Network.
Aaker, D. A. (1991). Managing Brand Equity, New York: The Free Press.
Bauer, H. H., Grether, M., & Leach, M. (2002). Building customer relations over the Internet. Industrial Marketing Management, 31(2), 155-163.
De Chernatony, L., & McDonald, M. (2003). Creating Powerful Brands. Oxford: Routledge.s
Fu et al.(2020). Measuring the impact of online reviews on consumer purchase decisions-A scale development study, Journal of Retailing and Consumer Services,68,103066.doi: https://doi.org/10.1016/j.jretconser.2022.103066
Goh, K. Y., Heng, C. S., & Lin, Z. (2013). Social media brand community and consumer behavior: Quantifying the relative impact of user-and marketer-generated content. Information Systems Research, 24(1), 88-107.doi: https://doi.org/10.1287/isre.1120.0469
Gelb, B. D., & Sundaram, S. (2022). Adapting to Word of Mouse. Business Horizon, 21-25.
Garvin, D. A. (1983). Quality on the Line. Harvard Business Review, 61(3), 65-75.
Hongjiang Yue (2009). S&T Text Mining and Visualization Applied on Enterprise's R&D: A Case Study.
Harris, Z. (1954). Distributional Structure. Word, 10(2-3), 146-162.
Hussein, DME-DM.(2018). A survey on sentiment analysis challenges. Journal of King Saud University – Engineering Sciences, 30(4), 330-338. doi: https://doi.org/10.1016/j.jksues.2016.04.002
Keller, K, L. (2003), Strategic brand management, Building, Measuring and Managing Brand Equity, 2^nd ed.; Prentice Hall, New Jersey.
Ladhari,R.,Brun,I. & Morales, M.(2008).Determinants of dining satisfaction and post-dining behavioral intentions. International Journal of Hospitality
Mehmet Ali Köseoglu, Fuad Mehraliyev, Mehmet Altin, and Fevzi Okumus (2020). Competitor Intelligence and Analysis (CIA) Model and Online Reviews: Integrating Big Data Text Mining with Network Analysis for Strategic Analysis.
Olshavsky, Richard W.(1985), Perceived Quality in Consumer Decision Making: An Integrated Theoretical Perspective, in Perceived Quality, J.Jacoby and J. Olson, eds. Lexington, MA: Lexington Books, 3-29.
Park, C.W., Jaworski, B.J. and Maclnnis, D.J. (1986) Strategic Brand Concept-Image Management. Journal of Marketing, 50, 135-145.doi: http://dx.doi.org/10.2307/1251291
Pang, B., Lee, L., & Vaithyanathan, S. (2002). Thumbs up? Sentiment classification using machine learning techniques. In Proceedings of the ACL-02 conference on Empirical methods in natural language processing (pp. 79-86). Association for Computational Linguistics.
Qiao, Z., Wang, G. A., Zhou, M., & Fan, W. (2018). The impact of customer reviews on product innovation: empirical evidence in mobile apps.
Stone, P. J., Dunphy, D. C., Smith, M. S., & Ogilvie, D. M. (1966). The general inquirer: A computer approach to content analysis. MIT Press.
Salton, G. and M. J. McGill (1986), Introduction to Modern Information Retrieval, New York: McGraw-Hill.
Steenkamp (1990) proposed a conceptual model of the quality perception process.doi: https://doi.org/10.1016/0148-2963(90)90019-A

 
Tan,A.-H.(1999). Text mining: The state of the art and the challenges. In Proceedings of PAKDD Workshop on Knowledge discovery from Advanced Databases(pp.71-76).Beijing:Springer.
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.
二、網路資料
”Natural Language, ”Google, 2018. [Online]. Available: https://cloud.google.com/natural-language.
”Mobile01論壇”, 維基百科(2022),
https://zh.wikipedia.org/zh-tw/Mobile01#%E5%8F%83%E8%80%83%E6%96%87%E7%8D%BB