Basic Search / Detailed Display

Author: 林金微
Chin-Wei Lin
Thesis Title: 消費者臉部表情與消費意向關係之研究-以消費者之旅遊網站行程瀏覽過程為例
A study on the relationship between consumers' facial expressions and consumption intention - A case of consumers' browsing process of online travel agency.
Advisor: 盧希鵬
Hsi-Peng Lu
羅天一
Tain-Yi Luor
Committee: 盧希鵬
Hsi-Peng Lu
羅天一
Tain-Yi Luor
黃世禎
Sun-Jen Huang
Degree: 碩士
Master
Department: 管理學院 - 管理研究所
Graduate Institute of Management
Thesis Publication Year: 2023
Graduation Academic Year: 111
Language: 中文
Pages: 67
Keywords (in Chinese): 深度學習購物意向臉部情緒分析理性行為理論
Keywords (in other languages): Deep Learning, Shopping Intention, Facial Emotion Analysis, Theory of Reasoned Action
Reference times: Clicks: 356Downloads: 8
Share:
School Collection Retrieve National Library Collection Retrieve Error Report
  • 電子商務發展至今約 30 年,各企業持續不斷地使用各種方式收集消費者行為,以進一步了解消費者意向與行為,並建立預測模型,透過這些模型工具來推播行銷手段以吸引更多的顧客並創造營收,本研究透過實驗法,記錄並觀察消費者或潛在顧客在搜尋、瀏覽有興趣的旅遊行程時的瀏覽行為時與臉部情緒是否有相關性?
    近年來科技技術不斷進步,電腦擁有更快的運算速度,相機提供更高解析度的相素圖片,也讓人工智慧 Artificial Intelligence 的技術不斷推陳出新,逐漸並進而發展出臉部表情之情緒識別等功能。本研究透過深度神經網路(DNN, Deep Neural Network)及 OpenVINO 軟體所提供 Face-detection-adas-0001 模型可適切地找出影像或圖片中臉部的位置,再透過Emotion-recognition-retail-0003 模型(Intel®,2023),辨識臉部的五大情緒:快樂 Happy、生氣 Anger、傷心 Sad、驚訝 Surprise 及面無表情Neutral。研究過程中計算所收集的使用者瀏覽與購買行為(含歷程)並進行分析比對,以觀察消費者或顧客在購買行為或意願與情緒上的關係。
    研究過程中,提供數個不同的旅遊行程樣本,並記錄受測者線上瀏覽過程及行為,再配合偵測其臉部情緒以收集相關數據進行統計分析,以驗證購買旅遊行程的行為與臉部情緒之相關性。
    最後,本研究結論消費者臉部情緒與意向無顯著的相關性。


    In this study, we use an experimental method to record and observe the behavior of consumers or potential customers when they search for and browse travel itineraries of interest. Is there any correlation with facial emotion?
    In recent years, technology has been advancing, computers have faster computing speed, cameras provide higher resolution pixel images, and Artificial Intelligence (AI) technology has been evolving to gradually develop emotion recognition of facial expressions. In this study, the Face-detection-adas-0001 model provided by DNN (Deep Neural Network) and OpenVINO software can appropriately identify the position of the face in the image or picture, and then the Emotion-recognition-retail-0003 model (Intel®,2023). During the study, the collected user browsing and purchasing behaviors (including history) were calculated and compared to observe the relationship between consumers' or customers' purchasing behaviors or intentions and emotions.
    During the study, several samples of travel itineraries were provided, and the subjects' online browsing and behaviors were recorded, and their facial emotions were detected to collect relevant data for statistical analysis to verify the correlation between travel purchase behavior and facial emotions.
    Finally, the study concludes that there is no significant correlation between consumers' facial emotion and intention.

    中文摘要 I ABSTRACT II 誌謝詞 III 目錄 IV 圖目錄 VI 表目錄 VIII 第一章 緒論 1 第一節 研究背景及動機 1 第二節 研究目的 2 第三節 論文架構 2 第二章 文獻探討 3 第一節 數位足跡 4 第二節 理性行為理論 7 第三節 OPENVINO TOOLKIT 10 第四節 臉部表情識別之應用 14 第三章 系統設計 18 第一節 系統架構 18 第二節 情緒監測系統規劃 19 第三節 旅遊網站瀏覽行為系統規劃 23 第四章 研究結果 27 第一節 觀測個案實驗結果 28 第二節 實驗分析 40 第五章 研究結論、限制與未來研究建議 45 第一節 研究結論與貢獻 45 第二節 研究限制與未來研究參考 47 參考文獻 50 中文文獻 50 英文文獻 51 參考網站 53

    李沂倩(2021)。基於理性行為理論探討假新聞第三人效果對恐慌性購買意圖的影響 - 以 COVID-19 臺灣口罩搶購事件為例。﹝碩士論文。國立中山大學﹞臺灣博碩士論文知識加值系統。https://hdl.handle.net/11296/cjqj87。
    侯昶仲(2017)。微表情辨識分析與訓練之研究。﹝碩士論文。中央警察大學﹞臺灣博碩士論文知識加值系統。https://hdl.handle.net/11296/t3kx96。
    徐曼萱(2016)。建立消費者輪廓系統幫助廣告商在廣告交易平台上競標。﹝碩士論文。國立中正大學﹞臺灣博碩士論文知識加值系統。 https://hdl.handle.net/11296/vufc9a。
    徐睿廷(2012)。應用臉部情意運算於互動情感介面增進情感溝通之設計與評估〔碩士論文,國立臺中科技大學〕。華藝線上圖書館。https://doi.org/10.6826/NUTC.2012.00105
    袁如華(2020)。整合交易網路特徵來強化機器學習模型於財務欺詐檢測。﹝碩士論文。東吳大學﹞臺灣博碩士論文知識加值系統。https://hdl.handle.net/11296/fnu8ue。
    莊祐軒、羅乃維(2013)。物聯網安全的現況與挑戰。資訊安全通訊,19(4),16-29。https://www.airitilibrary.com/Publication/alDetailedMesh?DocID=a0000270-201310-201311150022-201311150022-16-29
    許又壬(2016)。Facebook 數位足跡為基之消費者購買決策型態預測方法發展。﹝碩士論文。國立成功大學﹞臺灣博碩士論文知識加值系統。 https://hdl.handle.net/11296/26kf3f。
    郭戎晉(2012)。論數位環境下個人資料保護法制之發展與難題-以「數位足跡」之評價為核心。科技法律透析,24(4),18-39。https://doi.org/10.7062/STLR.201204.0018。
    盧希鵬(2018)。隨經濟:第二曲線的 77 個思維模型。天下文化。
    羅天一、郭錦駩(2021)。 企業長青術 : 魔數 1 到 9。新陸書局 。
    羅凱揚、蘇宇暉、鍾皓軒(2019)。行銷資料科學|大數據 x 市場分析 x人工智慧。碁峰。
    Azucar, D., Marengo, D., & Settanni, M. (2018). Predicting the Big 5 personality traits from digital footprints on social media: A meta-analysis. PERSONALITY AND INDIVIDUAL DIFFERENCES, 124, 150-159. https://doi.org/10.1016/j.paid.2017.12.018
    Bernabé, S., González, C., Fernández, A., & Bhangale, U. (2021). Portability and Acceleration of Deep Learning Inferences to Detect Rapid Earthquake Damage From VHR Remote Sensing Images Using Intel OpenVINO Toolkit. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 14, 6906-6915.
    https://doi.org/10.1109/JSTARS.2021.3075961
    Brynjolfsson, E., Hitt, L. M., & Kim, H. H. (2011). Strength in Numbers: How Does Data-Driven Decisionmaking Affect Firm Performance? SSRN Electronic Journal, 1. https://doi.org/10.2139/ssrn.1819486
    Ekman, P., & Friesen, W. V. (1978). Facial action coding system. Environmental Psychology & Nonverbal Behavior.
    Elepu, Gabriel & Mazzocco, Michael A., (2010). Consumer Segments in Urban and Suburban Farmers Markets. INTERNATIONAL FOOD AND AGRIBUSINESS MANAGEMENT REVIEW, 13(2), 1-17.
    Weaver, S. D., & Gahegan, M. (2007). Constructing, Visualizing, and Analyzing A Digital Footprint. Geographical Review, 97(3), 324-350. https://doi.org/10.1111/j.1931-0846.2007.tb00509.x
    Shen, Guangyao & Wang, Xin & Duan, Xuguang & Li, Hongzhi & Zhu, Wenwu. (2020, October 12-16). MEmoR: A Dataset for Multimodal Emotion Reasoning in Videos [Conference presentation]. In Proceedings of the 28th ACM International Conference on Multimedia
    (MM '20). Association for Computing Machinery, New York, NY, USA, 493–502 493-502. https://doi.org/10.1145/3394171.3413909.
    Zhou, J., Zhai, L. L., & Pantelous, A. A. (2020). Market segmentation using high-dimensional sparse consumers data. EXPERT SYSTEMS WITH APPLICATIONS, 145, Article 113136. https://doi.org/10.1016/j.eswa.2019.113136
    Carstensen, N. (2019, January 31). 6 Incredible Real-Life Examples of Data-
    Driven Marketing in Action. Adverity. https://www.adverity.com/blog/examples-data-driven-marketing
    Ekman, P. (2020, April 09). Lie To Me . Paul Ekman Group. https://www.paulekman.com/projects/lie-to-me/
    Google. (2010, May 19 ). BigQuery. Google. https://cloud.google.com/bigquery
    Google. (2016, May 18). Google 代碼管理工具總覽。Google. https://support.google.com/tagmanager/answer/6102821?hl=zh-Hant
    Google. (2005, November 14). Google Analytics. Google. https://developers.google.com/analytics?hl=zh-tw
    Google. (2008, April 7). Google Cloud Platform. Google. https://cloud.google.com/?hl=zh-tw
    Intel®. (2018, May 16). Intel® Distribution of OpenVINO™ Toolkit. Intel. https://www.intel.com/content/www/us/en/developer/tools/openvino-toolkit/overview.html
    Intel®. (2019a). Emotion-recognition-retail-0003. Openvino. 線上檢索日期:2023 年 2 月 5 日。https://docs.openvino.ai/2019_R1/_emotions_recognition_retail_0003
    _description_emotions_recognition_retail_0003.html
    Intel®. (2019b). Face-detection-adas-0001. Openvino. 線上檢索日期:2023 年 2 月 5 日。
    https://docs.openvino.ai/2019_R1/_face_detection_adas_0001_descrip
    tion_face_detection_adas_0001.html
    Intel®. (2019c). Model Optimization Guide. Openvino. 線上檢索日期:2023 年 2 月 5 日。https://docs.openvino.ai/latest/openvino_docs_model_optimization_guide.html
    Intel®. (2019d). OpenVINO System Requirements. Intel. 線上檢索日期:2023 年 2 月 5 日。https://www.intel.com/content/www/us/en/developer/tools/openvino-toolkit/system-requirements.html
    Intel®. (2019e). Overview of OpenVINO™ Toolkit Pre-Trained Models - OpenVINO Toolkit. Openvino. 線上檢索日期:2023 年 2 月 5 日。https://docs.openvino.ai/2019_R1/_docs_Pre_Trained_Models.html
    Jami Oetting. (2021, January 19). Emotional Advertising: How Brands Use Feelings to Get People to Buy. Hubspot. https://blog.hubspot.com/marketing/emotions-in-advertising-examples
    Mary. (2021, October 07). Get faster performance for Deep Learning Models with the help of Intel® Distribution of OpenVINO™ toolkit Execution Provider and Intel® DevCloud. Intel. https://community.intel.com/t5/Blogs/Tech-Innovation/Artificial-Intelligence-AI/Get-faster-performance-for-Deep-Learning-Models-with-the-help-of/post/1335740
    Tableau. (2003)。資料導向 (又稱為資料驅動) 的決策過程:在數位時代中獲致成功。 Tableau. 線上檢索日期:2023 年 2 月 25 日。https://www.tableau.com/zh-tw/learn/articles/data-driven-decision-making
    TWNIC.(2022 年 07 月 21 日)。2022台灣網路報告 - 整體使用現況。Twnic. https://report.twnic.tw/2022/TrendAnalysis_internetUsage.html
    陳箴(2020 年 05 月 06 日)。情緒辨識 AI 技術介紹。壹灣人工智慧行動網。 https://ai.iias.sinica.edu.tw/emotion-ai-tech-intro/
    張佩芬(2021 年 03 月 24 日)。台灣大車隊用大數據打造 AI 神器預測「叫車熱點」載客不漏接。工商時報。https://ctee.com.tw/livenews/aj/ctee/A98623002021032422484352

    QR CODE