論文使用權限 Thesis access permission:自定論文開放時間 user define
開放時間 Available:
校內 Campus: 已公開 available
校外 Off-campus: 已公開 available
論文名稱 Title |
基於情緒分析對電商平台定價之影響-以筆記型電腦資料為例 An impact on E-commerce retailer pricing by community platform using sentiment analysis-taking laptop for instance |
||
系所名稱 Department |
|||
畢業學年期 Year, semester |
語文別 Language |
||
學位類別 Degree |
頁數 Number of pages |
62 |
|
研究生 Author |
|||
指導教授 Advisor |
|||
召集委員 Convenor |
|||
口試委員 Advisory Committee |
|||
口試日期 Date of Exam |
2022-07-14 |
繳交日期 Date of Submission |
2022-07-24 |
關鍵字 Keywords |
電子商務、情緒分析、機器學習、自然語言處理、固定效果模型 E-commerce, sensitivity analyst, machine learning, nature language processing, fixed effect model |
||
統計 Statistics |
本論文已被瀏覽 354 次,被下載 0 次 The thesis/dissertation has been browsed 354 times, has been downloaded 0 times. |
中文摘要 |
隨著時代迅速的發展,3C類電子產品不同於以往,種類繁多且可滿足各種使用場景,進而影響了消費者對於筆記型電腦的需求,本研究將以國內某知名電商的交易紀錄探討現今消費者會參考筆記型電腦的何種規格作為購買依據。 本研究將以國內某知名電商2019/6/13到2020/2/28號共28,393筆的筆記型電腦交易紀錄作為資料來源,且另外整併2019/5/31到2020/02/14的各大虛擬貨幣價格做為變數放入模型中,並加入顯示卡算力數據額外檢驗是否算力會影響筆記型電腦的價格,最後爬取PTT及Dcard等社群媒體的消費者情緒指標,研究消費者對顯示卡及筆記型電腦等字眼的社群情緒是否會影響筆電價格。 研究結果得出將情緒分數做兩週的遞延後,並將其與顯示卡算力作交叉項處理加入非線性模型中,迴歸模型得出來的結果呈現出”顯示卡”字眼的情緒分數會對模型有顯著性影響,而”筆記型電腦”以及其他品牌的關鍵字不會有顯著影響,而另外加入的自變數如顯示卡算力、是否為電競型、比特幣價格皆會對筆記型電腦的價格有顯著影響,另外在固定時間效果的情況下,不同的月份都會對筆記型電腦的價格有顯著影響。 |
Abstract |
With the rapid development of this generation, 3C electronic products are different from the past, with a wide variety and can meet various usage scenarios, which in turn affects consumers' demand for notebook computers. Consumers will refer to the specifications of the notebook computer as the basis for purchasing. This research will use a total of 28,393ebook computer transaction records from a well-known domestic e-commerce company from 2019/6/13 to 2020/2/28 as the data source. Besides, the price of major virtual currencies from 2019/5/31 to 2020/2/14 is put into the model as a variable, and the hashrate data of the GPU is added to additionally check whether the hashrate will affect the price of the notebook. Finally, the consumer sentiment indicators of social media such as PTT and Dcard are crawled to study. To examine whether consumer sentiment towards terms such as graphics cards and laptops affects laptop prices. The research results show that after the emotional score is deferred for two weeks, it is processed as an intersection with the graphics card computing power and added to the nonlinear model. The results obtained by the regression model show that the emotional score of the word "GPU" will affect the model has a significant impact, while the keywords of "laptop" and other brands will not have a significant impact, and additional independent variables such as the hashrate, whether it is an e-sports type, and the price of Bitcoin will all significantly affect the price of the laptop. And in the case of a fixed time effect, the different months will have a significant impact on the price of the laptop. |
目次 Table of Contents |
學位論文審定書 ................................................................................................. i 摘要 .................................................................................................................. ii Abstract ............................................................................................................ iii 目錄 ................................................................................................................. iv 圖次 ................................................................................................................. vi 表次 ................................................................................................................ vii 壹、 緒論 ................................................................................................... 1 一、 研究背景 ......................................................................................... 1 (一) 筆電市場概述 .......................................................................... 1 (二) 筆電硬體概述 .......................................................................... 2 二、 研究動機與目的 .............................................................................. 5 三、 研究缺口 ......................................................................................... 6 四、 研究問題 ......................................................................................... 6 五、 研究步驟與流程 .............................................................................. 7 貳、 文獻回顧 ............................................................................................ 8 一、 特徵價格分析 ................................................................................. 8 二、 筆記型電腦特徵模型 ....................................................................... 9 (一) 模型簡介 ................................................................................. 9 (二) 模型展示 ................................................................................. 9 三、 情緒分析 ....................................................................................... 11 (一) 意見定義 ............................................................................... 12 (三) 意見的主客觀性與情緒 .......................................................... 12 (四) 監督與非監督式學習 .............................................................. 13 (五) 小結 ....................................................................................... 14 參、 研究方法 .......................................................................................... 16 一、 資料來源 ....................................................................................... 16 (一) 網路電商平台交易資料 .......................................................... 16 (二) 外部連接資料 ........................................................................ 18 二、 資料清理流程 ............................................................................... 18 (一) 資料蒐集 ............................................................................... 18 (二) 資料清洗 ............................................................................... 19 (三) 情緒資料處理 ........................................................................ 22 三、 研究變數總覽 ............................................................................... 24 四、 研究分析工具 ............................................................................... 26 肆、 研究結果 .......................................................................................... 29 一、 敘述性統計 ................................................................................... 29 二、 模型結果 ....................................................................................... 39 三、 非線性模型結果 ............................................................................ 41 伍、 結論與建議 ....................................................................................... 47 一、研究結論 ........................................................................................... 47 二、研究建議 ........................................................................................... 48 (一) 社群資訊蒐集 ........................................................................ 48 (二) 分離零件效能 ........................................................................ 48 (三) 分析其他市場資訊 ................................................................. 49 三、研究限制與未來應用 ......................................................................... 49 (一) 納入更多的社群平台做情緒分數 ............................................ 49 (二) 更長時間的資料 ..................................................................... 49 (三) 不同平台的交易資料 .............................................................. 50 參考文獻 ........................................................................................................ 51 |
參考文獻 References |
一、 英文文獻 Bakshi, R. K., et al. (2016). Opinion mining and sentiment analysis. 2016 3rd International Conference on Computing for Sustainable Global Development (INDIACom), IEEE. Berndt, Ernst R., Zvi Griliches and Neal Rappaport. (1995). Econometric Estimates of Prices in Indexes for Personal Computers in the 1990s. Journal of Econometrics (pp. 243-68). Chen, M., Wang, S., Liang, P. P., Baltrušaitis, T., Zadeh, A., & Morency, L. P. (2017, November). Multimodal sentiment analysis with word-level fusion and reinforcement learning. In Proceedings of the 19th ACM international conference on multimodal interaction (pp. 163-171). Chevalier, J. A. and D. Mayzlin (2006). "The effect of word of mouth on sales: Online book reviews." Journal of marketing research 43(3): 345-354. Fang, X. and J. Zhan (2015). "Sentiment analysis using product review data." Journal of Big Data 2(1): 5. Jacob Devlin, Ming-Wei Chang, Kenton Lee, Kristina Toutanova. (2018). "Bert: Pre-training of deep bidirectional transformers for language understanding." arXiv preprint arXiv:1810.04805. K. Mishev, A. Gjorgjevikj, I. Vodenska, L. T. Chitkushev and D. Trajanov, "Evaluation of Sentiment Analysis in Finance: From Lexicons to Transformers," in IEEE Access, vol. 8, pp. 131662-131682, 2020, doi:10.1109/ACCESS.2020.3009626. Laith Almaqableh, Damien Wallace, Vijay Pereira, Vikash Ramiah, Geoffrey Wood, Jose Francisco Veron, Imad Moosa, Alastair Watson.(2022) Is it possible to establish the link between drug busts and the cryptocurrency market? Yes, we can, International Journal of Information Management, ISSN 0268-4012, https://doi.org/10.1016/j.ijinfomgt.2022.102488. Liu, B. (2012). "Sentiment analysis and opinion mining." Synthesis lectures on human language technologies 5(1): 1-167. Liu, B., Zhang, L. (2012). A Survey of Opinion Mining and Sentiment Analysis. In: Aggarwal, C., Zhai, C. (eds) Mining Text Data. Springer, Boston, MA. https://doi.org/10.1007/978-1-4614-3223-4_13 Mishev, Kostadin & Gjorgjevikj, Ana & Vodenska, Irena & Chitkushev, Lubomir & Trajanov, Dimitar. (2020). Evaluation of Sentiment Analysis in Finance: From Lexicons to Transformers. IEEE Access. PP. 1-1. Muhammad Waseem Ahmad, Monjur Mourshed, Yacine Rezgui,Trees vs Neurons: Comparison between random forest and ANN for high-resolution prediction of building energy consumption, Energy and Buildings,Volume 147,2017,Pages 77-89,ISSN 0378-7788. Okamoto, Masato and Tomohiko Sato. (2001). Comparison of Hedonic Method and Matched Models Method Using Scanner Data: The Case of PCs, TVs and 34 Digital Cameras. Canberra, Australia: presented at the Sixth Meeting of the International Working Group on Price Indices. Plutchik, R. (1980). A general psychoevolutionary theory of emotion. Theories of emotion, Elsevier: 3-33. Prem Melville, Wojciech Gryc, and Richard D. Lawrence. (2009). Sentiment analysis of blogs by combining lexical knowledge with text classification. In Proceedings of the 15th ACM SIGKDD international conference on Knowledge discovery and data mining (KDD '09). Association for Computing Machinery, New York, NY, USA, 1275–1284. https://doi.org/10.1145/1557019.1557156 Rosen, S. (1974). Hedonic Prices and Implicit Markets: Product Differentiation in Pure Competition. Journal of Political Economy, 82(1), 34–55. http://www.jstor.org/stable/1830899 Rutherford, D. P., and Wilhelm, W. E. (1999) “Forecasting Notebook Computer Price as a Function of Constituent Features,” Comput. Ind. Eng., 37(4), pp. 823–845. Senecal, S. and J. Nantel (2004). "The influence of online product recommendations on consumers’ online choices." Journal of retailing 80(2): 159-169. Seo-Hui Park; Byung-Chull Bae; Yun-Gyung Cheong. (2020). Emotion Recognition from Text Stories Using an Emotion Embedding Model. 2020 IEEE International Conference on Big Data and Smart Computing (BigComp), IEEE. Von Helversen, B., et al. (2018). "Influence of consumer reviews on online purchasing decisions in older and younger adults." Decision Support Systems 113: 1-10. 二、 中文文獻 郭建賢(2021)。電子口碑研究:旅館業者應如何看待與處理線上評論。國立中山大學企業管理學系研究所碩士論文,高雄市。 取自https://hdl.handle.net/11296/9vw8uy 徐孟暉(2021)。建構筆記型電腦之消費者物價指數與實質銷售成長率指標。國立中山大學企業管理學系研究所碩士論文,高雄市。 取自https://hdl.handle.net/11296/92vm37 三、 網路資源 CoinMarketCap(2022) Ethereum 上網日期:2022年2月18號。檢自:https://coinmarketcap.com/zh-tw/ TrendForce (2021) 2021年全球筆電出貨量預估達2.17億台 上網日期:2022年5月3號。檢自:https://www.trendforce.com.tw/presscenter/news/20210106-10631.html 未來流通研究所(2021) 【商業數據圖解】2020台灣「零售&電商」產業市佔率英雄榜 上網日期:2022年5月3號。檢自: https://www.mirai.com.tw/2020-taiwan-retail-ec-market-share-analysis/ 鉅亨網(2021) 輝達看GPU成長動能到年底 板卡廠營運受惠 上網日期:2021年12月2號。檢自: https://news.cnyes.com/news/id/4652481 數位時代(2020) 【圖解】一款產品救慘業!筆電產業為何迎8年來最豐收?銷量前五品牌會是誰? 上網日期:2022年1月20號。檢自: https://www.bnext.com.tw/article/59202/notebook-8-years-the-best-of |
電子全文 Fulltext |
本電子全文僅授權使用者為學術研究之目的,進行個人非營利性質之檢索、閱讀、列印。請遵守中華民國著作權法之相關規定,切勿任意重製、散佈、改作、轉貼、播送,以免觸法。 論文使用權限 Thesis access permission:自定論文開放時間 user define 開放時間 Available: 校內 Campus: 已公開 available 校外 Off-campus: 已公開 available |
紙本論文 Printed copies |
紙本論文的公開資訊在102學年度以後相對較為完整。如果需要查詢101學年度以前的紙本論文公開資訊,請聯繫圖資處紙本論文服務櫃台。如有不便之處敬請見諒。 開放時間 available 已公開 available |
QR Code |