本研究主要探討台灣機車產業在社群媒體中輿論與其銷售之間關係，試圖了解在不同社群媒體中輿論情感與銷售的相關程度，以及影響不同車廠品牌銷售之因素。在社群媒體中的資訊過於龐大，因此本研究採用網路爬蟲以及情感分析來提高資料結構化的效率，將情感分類結果視覺化來觀察車廠品牌事件發生，再透過皮爾森相關係數檢定兩變數之間是否具有線性相關。
     研究結果顯示不同的社群媒體會有不同的使用者特性，其輿論情感對於銷售數也會有不同程度的影響程度，而影響品牌銷售之因素不僅於網路輿論情感，透過Google引擎中的搜尋熱度高低也會與其銷售數有中至高度正相關性。管理者可提升社群媒體上的正面情感輿論，以及保持話題熱度使使用者提高搜尋熱度；在這社群媒體日益壯大的時代，企業如果能將行銷資源投入於社群媒體中，增加在社群媒體輿論中的正面情感及保持自身品牌的搜尋熱度，據本研究結果，社群媒體輿論情感與網路搜尋熱度和銷售之間具有一定程度相關性，亦可為企業實質上的利益。

This study focuses on the relationship between public opinion in the social media and sales Taiwan's motorcycle industry. We aim to understand the degree of sentiment in the reviews and sales from different social media as well as influential factors. This study uses web crawlers and sentiment analysis to improve the efficiency of data structure, visualize the results of sentiment classification to observe the occurrence of brand events, and examines the linear correlation between the two variables. The results show that different social media users have different characteristics and their sentiment of reviews will have different degrees of influence on sales. The factors that may affect brand sales are not only the sentiment of reviews but also the search trend on Google which has highly positive correlation with sales. Managers can enhance the positive emotions in the reviews on social media and keep the topic hot to increase hot searching behavior. On the other hand, enterprises can reallocate the marketing resources in social media to increase positive sentiment. In summary, sentiment in public reviews and online search may have certain degree of correlation between searching trend and sales.

目  錄
第一章 緒論	1
第一節 研究背景	1
第二節 研究動機	2
第三節 研究問題	3
第二章 文獻探討	5
第一節 社群媒體	5
第二節 情感分析	8
第三章 研究方法	11
第一節 研究架構	11
第二節 資料預處理	12
一、R軟體	12
二、社群網路爬蟲	12
三、文本斷詞系統	13
第三節 字詞情感分析	14
第四節 統計方法	15
一、皮爾森相關係數	15
二、假設檢定	16
第四章 資料分析	17
第一節 分析流程	17
第二節 資料蒐集流程	18
一、機車銷售資料庫	18
二、社群媒體爬蟲流程	20
三、資料內容說明	23
四、結巴(jiebaR)斷詞	25
五、文本情感分析計算	27
第三節 社群媒體平台分析	28
一、PTT biker	28
二、Mobile01	30
三、小老婆汽機車資訊網	31
四、Google Trend	32
第四節 社群媒體平台相關性分析	33
一、PTT正面情感數量與銷售相關性	33
二、mobile01正面情感數量與銷售相關性	35
三、小老婆汽機車資訊網正面情感數量與銷售相關性	36
第五節 影響品牌銷售之分析	38
一、三陽 (SYM)	38
二、光陽 (KYMCO)	40
三、山葉 (YAMAHA)	42
四、社群情感與台灣機車銷售相關性	44
五、Google Trend搜尋熱度與銷售相關性	48
第五節 虛無假設總攬	52
第五章 結論	54
第一節 研究結論	54
第二節 管理意涵	55
第三節 研究限制與建議	56
參考文獻	57

 
表目錄
表3-1 相關係數絕對值相關程度	15
表4-1 台灣區車輛工業同業公會網站資料	19
表4-2 機車銷售統計月報表(2018年12月)	19
表4-3 台灣區車輛工業同業公會季機車銷售	20
表4-4 資料型態	24
表4-5 PTT正面篇數與實際機車銷售相關係數	35
表4-6 PTT正面篇數與實際機車銷售相關係數之p-value	35
表4-7 Mobile01正面篇數與實際機車銷售相關係數之p-value 	36
表4-8 Mobile01正面篇數與實際機車銷售相關係數之p-value 	37
表4-9兩討論版正面情感合併與機車實際銷售相關係數	47
表4-10兩討論版正面情感合併與機車實際銷售相關係數之p-value	47
表4-11搜尋熱度的趨勢變化與機車實際銷售相關係數	51
表4-12 搜尋熱度的趨勢變化與機車實際銷售相關係數之p-value 	51
表4-13 虛無假設總攬表	53

 
圖目錄
圖3-1 研究架構圖	11
圖3-2 R軟體使用者介面	12
圖3-3 jiebaR斷詞範例	13
圖3-4 情感分析總分	14
圖4-1 研究流程圖	18
圖4-2 安裝rvest套件	21
圖4-3 PTT biker版網址	21
圖4-4 為文章標題文字所對應的HTML標籤	22
圖4-5 程式碼(網站xpath、網址迴圈)	23
圖4-6 安裝結巴(jiebaR)斷詞套件	25
圖4-7 結巴斷詞執行結果	26
圖4-8 台大情感極性辭典負面及正面詞	27
圖4-9 文本情感分析結果	28
圖4-10 PTT biker版情感趨勢圖	29
圖4-11 mobile01版情感趨勢圖	30
圖4-12 小老婆汽機車資訊網情感趨勢圖	31
圖4-13三車廠Google Trend熱度趨勢圖	32
圖4-14 PTT biker版正面情感篇數與機車銷售數量散佈圖	34
圖4-15 mobile01版正面情感篇數與機車銷售數量散佈圖	36
圖4-16 小老婆汽機車資訊網正面情感篇數與機車銷售數量散佈圖	37
圖4-17 Mobile01 三陽版情感趨勢圖	39
圖4-18 小老婆汽機車網三陽版情感趨勢圖	40
圖4-19 Mobile01 光陽版情感趨勢圖	41
圖4-20 小老婆汽機車網三陽版情感趨勢圖	42
圖4-21 Mobile01 山葉版情感趨勢圖	43
圖4-22小老婆汽機車網山葉版情感趨勢圖	44
圖4-23 兩討論版合併正面情感百分比與實際銷售之散布圖	45
圖4-24 Google關鍵字熱度與機車銷售數量相關係數圖	48
圖4-25 光陽Google搜尋熱度與機車銷售散佈圖	50
圖4-26 光陽Google搜尋熱度與機車銷售散佈圖(刪除離群值)	50

中文文獻
陳儷慧（2013）。影響個人提供線上社會支持因子之探討：以PTT癌症板為例。國立中山大學醫務管理研究所碩士論文。
黃彥霖（2018）。以深度學習實作情感分析於台灣股價指數趨勢之研究—以光電類股為例。國立政治大學資訊管理學系碩士論文。
趙玉娟（2015）。政治網路口碑的情感分析：語意關連性之觀點。交通大學傳播研究所碩士論文。
鍾智宇（2017）。PTT網站餐廳美食類別擷取之研究。國立中央大學資訊工程學系在職專班碩士論文。
吳忠武（主編）（民103）。現代統計學。臺北市：華泰文化事業股份有限公司。
英文文獻
Andreas, K. M., &Michael, H. (2010). Users of the world, unite! The challenges and opportunities of social media, Business Horizons, 53 (1), 59-68.
Barbosa, R. R. L., Sánchez-Alonso, S., & Sicilia-Urban, M. A. (2015). Evaluating hotels rating prediction based on sentiment analysis services, Aslib Journal of Information Management, 67 (4), 392-407.
Basant, A., Namita, M., Pooja, B., & Garg, S. (2015). Sentiment Analysis Using Common-Sense and Context Information, Computational intelligence and neuroscience, 30, 1-9. 
Blazevic, V., Hammedi, W., Garnefeld, I., Rust, R. T., Keiningham, T, Andreassen, T., Donthu, N., & Carl, W. (2013). Beyond traditional word‐of‐mouth: An expanded model of customer‐driven influence, Journal of Service Management, 24(3), 294-313.
Buda, A., & Jarynowski, A. (2010), Life-time of correlations and its applications vol.1, Wydawnictwo Niezalezne, 5–21.
C. Forman, A. Ghose, B. Wiesenfeld.(2008) Examining the relationship between reviews and sales: the role of reviewer identity disclosure in electronic markets, Information Systems Research, 19 (3), 291-313
D. Turney, P. (2002). Thumbs Up or Thumbs Down? Semantic Orientation Applied to Unsupervised Classification of Reviews, The 40th Annual Meeting of the Association for Computational Linguistics, 417–424.
Dhaoui, C., Webster, C. M., & Tan, L. P. (2017). Social media sentiment analysis: lexicon versus machine learning, Journal of Consumer Marketing, 34 (6), 480-488.
Diamantini, C., Mircoli, A., Potena, D., Storti E. (2019). Social information discovery enhanced by sentiment analysis techniques, Future Generation Computer Systems  95, 816-828.
Ding,  X., Liu, B., & Yu, P. S. (2008). A holistic lexicon-based approach to opinion mining, WSDM '08 Proceedings of the 2008 International Conference on Web Search and Data Mining, 231-240.
Fan, Z. P., Xi, Y., & Li, Y., (2018). Supporting the purchase decisions of consumers: A comprehensive method for selecting desirable online products, Kybernetes, 47(4), 689-715.
Gamboa, A. M., & Gonçalves, H. M. (2014). Customer loyalty through social networks: Lessons from Zara on Facebook, Business Horizons, 57 (6), 709-717.
Guohong, Fu., & Wang, X., (2010). Chinese Sentence-Level Sentiment Classification Based on Fuzzy Sets, COLING '10 Proceedings of the 23rd International Conference on Computational Linguistics: Posters, 312-219.
Huang, Y. T., & Su, Y. J. (2014). Global Marketing Conference 2014 Global Marketing Conference at Singapore , 2014 Global Marketing Conference at Singapore , 1874-1874.
Hussein, D, M. El-Din. (2018). A survey on sentiment analysis challenges, Journal of King Saud University - Engineering Sciences, 30(4), 330-338.
Ireland, R., & Liu, A. (2018). Application of data analytics for product design: Sentiment analysis of online product reviews, CIRP Journal of Manufacturing Science and Technology,23,128-144.
Jakic, A., Wagner. M. O., & Meyer, A. (2017). The impact of language style accommodation during social media interactions on brand trust, Journal of Service Management, 28(3), 418-441.
Jiangtao, Q., Chuanhui, L., Yinghong, L., & Zhangxi, L. (2018). Leveraging sentiment analysis at the aspects level to predict ratings of reviews, Information Sciences, 451–452, 295-309.
K. Kulkarni, K., D. Kalro, A., Sharma, D., & Sharma, P. (2019). A typology of viral ad sharers using sentiment analysis, Journal of Retailing and Consumer, (23),547-561. 
Kaplan., & Andreas, M. (2012). If you love something, let it go mobile: Mobile marketing and mobile social media 4x4, Business Horizons, 55 (2), 129–139.
Khan., & Gohar, F. (2017). Social Media for Government: A Practical Guide to Understanding, Implementing, and Managing Social Media Tools in the Public Sphere, Springer.
Kietzmann, Jan H., Hermkens, K.( 2011). Social media? Get serious! Understanding the functional building blocks of social media, Business Horizons (Submitted manuscript), 54 (3), 241–251.
Leaver, T., (2013). The Social Media Contradiction: Data Mining and Digital Death, M/C Journal: A Journal of Media and Culture, 16 (2) http://journal.mediaculture.org.au /index.php/mcjournal/article/viewArticle/625..
Li, X., Wu, C., & Mai, F. (2019) The effect of online reviews on product sales: A joint sentiment-topic analysis, Information & Management, 6(2), 172-184.
Li,X., Wu,C., & Mai,F.(2019), The effect of online reviews on product sales: A joint sentiment-topic analysis, Information & Management, 56(2), 172-184.
Liang, R., Guo, W., & Yang, D. (2017). Mining product problems from online feedback of Chinese users, Kybernetes, 46(3), 572-586. 
Łukasz, A., Piotr, S., Tomasz, K., & Włodzimierz, T. (2015). Comprehensive Study on Lexicon-based Ensemble Classification Sentiment Analysis, Entropy, 18(1), 4-29.
M. Kaplan, A., & Michael, H (2010). Users of the world, unite! The challenges and opportunities of social media, Business Horizons, 53(1), 59-68.
M.Boyd, D., & Ellison, N, B. (2007). Social Network Sites: Definition, History, and Scholarship, Journal of Computer-Mediated Communication, 13 (1), 210–30.
Manaman, H. S., Jamali, S., & AleAhmad, A. (2016), Online reputation measurement of companies based on user-generated content in online social networks, Computers in Human Behavior, 54, 94-100.
Martins, C. S., & Patrício, L. (2013). Understanding participation in company social networks, Journal of Service Management, 24(5), 567-587.
Metzger, Justin. (April , 2016).  "Cell phones". Retrieved from https://marketingland. com/facebook-usage-accounts-1-5-minutes-spent-mobile-171561. (May 2,2019).
Mostafa, M. (2013), More than words: Social networks' text mining for consumer brand sentiments, Expert systems with applications, 40 (10), 4241-4251.
Mukherjee, A., & Dubé, L., (2012). Mixing emotions: The use of humor in fear advertising, Journal of Consumer Behaviour, 11(2), 147-161.
N. Hu, L. Liu.,& J.J. Zhang.(2008) Do online reviews affect product sales? The role of reviewer characteristics and temporal effects, Inf. Technol. Management., 9, 201-214
Obar, J. A., & Wildman, S. (2015). Social media definition and the governance challenge: An introduction to the special issue. Telecommunications Policy, 39(9), 745-750.
O'Keeffe, G. S., Clarke-Pearson, K., Council on Communications and Media. (2011). The Impact of Social Media on Children, Adolescents, and Families, Pediatrics,127 (4), 800–804.
P.K. Chintagunta, S. Gopinath, S. Venkataraman. (2010),The effects of online user reviews on movie box office performance: accounting for sequential rollout and aggregation across local markets, Marketing Science, 29 (5) , 944-957
S. Xiao, C.P. Wei.,& M. Dong.(2016) Crowd intelligence: analyzing online product reviews for preference measurement, Information & Management., 53 (2016), 169-182, 
Schejter,  A.M., & Tirosh, N. (2015). Seek the meek, seek the just : Social media and social justice, Telecommunications Policy, 39 (9), 796–803.
Taboada, M., Brooke, J., Tofiloski, M., Voll, K., & Stede, M. (2011). Lexicon-based methods for sentiment analysis, Computational Linguistics, 37(2), 272–274.
Vryniotis, V. (September,2013). The importance of Neutral Class in Sentiment Analysis. Retrieved from http://blog.datumbox.com/the-importance-of-neutral-class-in-senti ment-analysis/ (May 2,2019).
Wang, H., & Wang, W. (2014). Product weakness finder: an opinion-aware system through sentiment analysis, Industrial Management & Data Systems, 114(8), 1301-1320.
Wang, Z., Li, H., Yec, Q., & Rob, L.(2016) Saliency effects of online reviews embedded in the description on sales: Moderating role of reputation，Decision Support Systems,87, 50-58.
Yoo, S. Y., Song, J., & Jeong, O, R. (2018). Social media contents based sentiment analysis and prediction system, Expert Systems with Applications, 105, 102-111.
Zhang, S., Wei, Z., Wang, Y., & Liao, T. (2018). Sentiment analysis of Chinese micro-blog text based on extended sentiment dictionary, Future Generation Computer Systems (81), 395-403.
Zhang, W., Xu, H., & Wan, W. (2012). Weakness Finder: Find product weakness from Chinese reviews by using aspects based sentiment analysis, Expert Systems with Applications, 39(11), 10283-10291.
Zhao,K., Stylianou,A., & Zheng,Y.(2018),Sources and impacts of social influence from online anonymous user reviews, Information & Management, 55(1), 16-30.
Zhong, Q., Liang, S., Cui, L., Chan, H. K., & Qiu, Y.(2018). Using online reviews to explore consumer purchasing behaviour in different cultural settings, Kybernetes, 48(6), 1242-1263.