簡易檢索 / 詳目顯示

回結果列表
研究生： 王婕恩
Jeh-An Wang
論文名稱： 基於機器學習的社群媒體行銷圖像設計分析與推薦系統：母嬰護理產品行業案例研究
A machine learning based image design analysis and recommendation system for social media marketing – a case study in maternity and baby care product industry
指導教授： 王孔政
Kung-Jeng Wang
口試委員: 杜志挺
Zhi-Ting, Du
王孔政
Kung-Jeng, Wang
郭人介
Ren-Jieh, Kuo
學位類別： 碩士
Master
系所名稱： 管理學院 - 工業管理系
Department of Industrial Management
論文出版年： 2023
畢業學年度： 112
語文別： 英文
論文頁數： 61
中文關鍵詞： 母嬰護理產業 、數位影響者 、數位行銷 、視覺分析 、消費者行為 、機器學習 、電子商務
外文關鍵詞： maternity and baby care industry, digital marketing, Instagram, machine learning, visual analysis, e-commerce, consumer behavior, digital influencers
相關次數： 點閱：64  下載：11 
分享至:
查詢本校圖書館目錄 查詢臺灣博碩士論文知識加值系統 勘誤回報

    • 數位行銷領域正在迅速發展，然而視覺內容的整合仍然嚴重依賴於人類專業知識，探索用戶上傳的圖像中哪些元素能夠激起共鳴並產生吸引力，是值得探討的主題。本研究旨在通過應用機器學習於Instagram上母嬰護理產品領域的視覺內容分析，來彌合這一差距。出於對創新行銷策略的追求，這些策略需與以家庭為導向的消費者產生共鳴，本研究採用了一系列機器學習技術（包特徵檢測、全景分割、自定義實例分割及面部檢測計算方法）來分析並預測圖像對提升用戶參與度的吸引力。通過提取關鍵圖像特徵和應用預測模型，本研究揭示視覺行銷在母嬰護理產品行業中的新見解。結論提出了一系列可行的建議，協助社群媒體用戶在上傳圖像前進行評估和優化，使其有望激發顧客參與度並培養品牌忠誠度。本研究在母嬰護理行銷領域的圖像識別方面做出了重要貢獻，填補了該產業在此類分析方法上的空白。

    Purpose: The digital marketing landscape is rapidly advancing, yet the integration of visual content remains heavily reliant on human expertise. Motivated by the pursuit of innovative marketing strategies that resonate with family-oriented consumers, this study aims to bridge this gap by applying machine learning to the analysis of visual content in the maternity and baby care product sector.
    Methods: This study integrates a suite of machine learning techniques (including open science framework feature detection, panoptic segmentation, customized instance segmentation, and face detection calculation methods) to analyze and predict the appeal of images to enhance user engagement and parent-child intimacy.
    Results: The investigation of an array of ML models, including DT, LightGBM, RIPPER algorithm, and CNNs has provided a comparative analysis that fills a methodological void in the extant literature which often relies on isolated model evaluations. In line with our quadrant analysis, for real-world applications, the choice of model hinges on the trade-off between performance and interpretability.
    Conclusion: The proposed system presents a series of actionable recommendations that promise to invigorate customer interaction and foster brand loyalty. This study makes a contribution to image design in maternity and baby care marketing in an analytical way.

    Table of content Abstract i 摘要 ii 誌謝 iii Table of content iv List of figures vi List of table vii Chapter 1. Introduction 1 Chapter 2. Literature review 4 2.1 Image features and their relevance in social media 4 2.2 ML classifier 5 2.3 Research gap 6 Chapter 3. Method 7 3.1 Research framework 7 3.2 Data collection and process module 8 3.3 Image features extraction module 10 3.3.1 Open science framework features 10 3.3.2 Features by panoptic segmentation 11 3.3.3 Customized features by instance segmentation 13 3.3.4 Face detection module 13 3.3.5 Dimensionality reduction module 15 3.4 Target variables 17 3.5 Modelling and validation 20 Chapter 4. Experiment results and discussion 23 4.1 Model comparison and discussion 23 4.2 DT based IDARS and illustrations 25 4.3 Customized illustrations for maternity and baby care industry 27 Chapter 5. Conclusion 31 References 33 Appendix 1. The performance of customized IS by X101-FPN 37 Appendix 2. Model training and parameter optimization 37 1. LightGBM 37 2. RIPPER 38 3. CNNs model 39 Appendix 3: RIPPER generated recommendation rules and corresponding image examples 40 Appendix 4. Feature importance charts of LightGBM model 43

    Altindis, S. F., Dalva, Y., Pehlivan, H., & Dundar, A. (2021). Benchmarking the robustness of instance segmentation models. arXiv preprint arXiv:2109.01123.
    Aum, J., Kim, J., & Park, E. (2023). Can we predict the Billboard music chart winner? Machine learning prediction based on Twitter artist-fan interactions. Behaviour & Information Technology, 42(6), 775-788.
    Caesar, H., Uijlings, J., & Ferrari, V. (2018). Coco-stuff: Thing and stuff classes in context. Proceedings of the IEEE conference on computer vision and pattern recognition, https://doi.org/10.48550/arXiv.1612.03716
    Casaló, L. V., Flavián, C., & Ibáñez-Sánchez, S. (2020). Influencers on Instagram: Antecedents and consequences of opinion leadership. Journal of Business Research, 117, 510-519.
    Chan, I. C. C., Chen, Z., & Leung, D. (2023). The more the better? Strategizing visual elements in social media marketing. Journal of Hospitality and Tourism Management, 54, 268-289.
    ChangDa, H., & Bhaumik, A. (2023). Colour psychology's impact on marketing, advertising, and promotion. International Journal of Management and Human Science, 7(1), 24-32.
    Chen, Z., Chan, I. C. C., & Egger, R. (2023). Gastronomic image in the foodstagrammer’s eyes–A machine learning approach. Tourism Management, 99, 104784.
    Chen, Y., Sherren, K., Smit, M., & Lee, K. Y. (2023). Using social media images as data in social science research. New Media & Society, 25(4), 849-871.
    Cheung, M. L., Pires, G., & Rosenberger, P. J. (2020). The influence of perceived social media marketing elements on consumer–brand engagement and brand knowledge. Asia Pacific Journal of Marketing and Logistics, 32(3), 695-720.
    Cohen, W. W. (1995). Fast effective rule induction. In Machine learning proceedings 1995 (pp. 115-123). Elsevier.
    Djafarova, E., & Rushworth, C. (2017). Exploring the credibility of online celebrities' Instagram profiles in influencing the purchase decisions of young female users. Computers in Human Behavior, 68, 1-7.
    Dzyabura, D., El Kihal, S., & Peres, R. (2021). Image analytics in marketing. In Handbook of market research (pp. 665-692). Springer.
    Eckler, P., & Bolls, P. (2011). Spreading the virus: Emotional tone of viral advertising and its effect on forwarding intentions and attitudes. Journal of Interactive Advertising, 11(2), 1-11.
    Ghosh, A., Jana, N. D., Mallik, S., & Zhao, Z. (2022). Designing optimal convolutional neural network architecture using differential evolution algorithm. Patterns, 3(9), 100567.
    Hastie, T., Tibshirani, R., Friedman, J. H., & Friedman, J. H. (2009). The elements of statistical learning: data mining, inference, and prediction (Vol. 2). Springer.
    Hu, Y., Manikonda, L., & Kambhampati, S. (2014). What we instagram: A first analysis of instagram photo content and user types. Proceedings of the international AAAI conference on web and social media, 8(1), https://doi.org/10.1609/icwsm.v8i1.14578
    Jia, Y., Shelhamer, E., Donahue, J., Karayev, S., Long, J., Girshick, R., Guadarrama, S., & Darrell, T. (2014). Caffe: Convolutional architecture for fast feature embedding. Proceedings of the 22nd ACM international conference on Multimedia, https://doi.org/10.48550/arXiv.1408.5093
    Joshi, Y., Lim, W. M., Jagani, K., & Kumar, S. (2023). Social media influencer marketing: foundations, trends, and ways forward. Electronic Commerce Research, 1-55.
    Khan, M.U., Javed, A.R., Ihsan, M. et al. (2023). A novel category detection of social media reviews in the restaurant industry. Multimedia Systems 29, 1825–1838.
    Ke, G., Meng, Q., Finley, T., Wang, T., Chen, W., Ma, W., ... & Liu, T. Y. (2017). Lightgbm: A highly efficient gradient boosting decision tree. 31st Conference on Neural Information Processing Systems (NIPS 2017), Long Beach, CA, USA.
    Li, X., & Chen, D. (2022). A survey on deep learning-based panoptic segmentation. Digital Signal Processing, 120, 103283.
    Li, Y., & Xie, Y. (2020). Is a picture worth a thousand words? An empirical study of image content and social media engagement. Journal of Marketing Research, 57(1), 1-19.
    Lou, C., & Yuan, S. (2019). Influencer marketing: How message value and credibility affect consumer trust of branded content on social media. Journal of Interactive Advertising, 19(1), 58-73.
    Malthouse, E. C., Haenlein, M., Skiera, B., Wege, E., & Zhang, M. (2013). Managing customer relationships in the social media era: Introducing the social CRM house. Journal of Interactive Marketing, 27(4), 270-280.
    Matz, S. C., Segalin, C., Stillwell, D., Müller, S. R., & Bos, M. W. (2019). Predicting the personal appeal of marketing images using computational methods. Journal of Consumer Psychology, 29(3), 370-390.
    Nixon, L., Apostolidis, K., Apostolidis, E. et al. (2024). AI and data-driven media analysis of TV content for optimised digital content marketing. Multimedia Systems 30, 25.
    Ouyang, C., Sindhgatta, R., & Moreira, C. (2021). Explainable AI enabled inspection of business process prediction models. arXiv preprint arXiv:2107.09767.
    Pakkala, K., & Bhat, K. S. (2022). Factors influencing consumer buying behavior on baby care products. International Journal of Case Studies in Business, IT and Education, 6(2), 459-468.
    Rogers, R. (2021). Visual media analysis for Instagram and other online platforms. Big Data & Society, 8(1), 20539517211022370.
    Sindhgatta, R., Ouyang, C., & Moreira, C. (2020). Exploring interpretability for predictive process analytics. International Conference on Service-Oriented Computing, Lecture Notes in Computer Science book series (LNPSE,volume 12571) 439–447.
    Smirnov, S. (2020). The impact of the COVID-19 pandemic on the Russian consumer market: statistical analysis. Social novelties and Social sciences. (2), 149-159.
    Yu, C.-E., Xie, S. Y., & Wen, J. (2020). Coloring the destination: The role of color psychology on Instagram. Tourism Management, 80, 104110.
    沈宗達（2023）。基於監督式學習之社群媒體圖像分析與建議系統。﹝碩士論文。國立臺灣科技大學﹞臺灣博碩士論文知識加值系統。 https://hdl.handle.net/11296/9m7284。

    QR CODE