近年來，網路廣告已成為企業和品牌行銷不可或缺的重要平台；然而，目前以點擊率評估廣告效果的方法存在誤點擊問題，且並非所有觀看者都會點擊廣告。對企業而言，提升消費者對品牌的認知和記憶是廣告行銷的主要目標。研究指出，觀察視線軌跡是了解人類注意力與感興趣區域的有效指標。因此，若能結合機器學習與眼動數據來預測廣告效果，廣告業者或公司便可預先測試廣告並改進其設計，提升廣告效益。
此外，網路廣告的存在可能會使需要搜尋或閱讀網路資料的用戶產生心理上的不適與對廣告的迴避行為。如何讓用戶對廣告中的品牌產生印象，同時不會造成認知上的負擔，一直是一個挑戰。本研究旨在尋找既能留下印象又不會給用戶造成認知負擔的廣告類型。
本研究使用眼動儀蒐集60位受試者在瀏覽新聞網頁時之視覺活動數據，並以問卷紀錄受試者對於廣告之再認程度，透過統計分析探討網路廣告形式（靜態、動態）與位置（上、下、左、右）對注意力、再認力及閱讀新聞時專注度之影響，同時使用機器學習模型預測受試者對不同廣告類型的再認程度，提供廣告業者未來加入眼動數據作為廣告設計之參考。
實驗結果顯示，使用眼動數據搭配機器學習算法能夠大方向地預測用戶對於廣告的再認程度。本研究亦發現，用戶在瀏覽網頁時，對於上方和下方廣告有較多的注視次數，而動靜態之廣告形式對注意力分配和再認力的影響並不顯著。此外，位於左方靜態的廣告具有較高的再認力和閱覽專注力，建議公司企業或廣告業者將廣告投放於網頁左側位置，以加深用戶對廣告的印象。這些發現將協助廣告業者優化廣告策略，並為網站設計師提供創建用戶友好網站的參考。未來研究可以將眼動追蹤與其他心理及生理技術結合使用，以提供更全面的用戶反應分析，從而更深入地了解用戶對廣告的情緒反應和認知過程。

In recent years, online advertising has become an indispensable platform for corporate and brand marketing. However, the current method of evaluating advertisement effectiveness through click-through rates (CTR) is problematic due to accidental clicks, and not all viewers click on ads. For companies, enhancing consumer recognition and memory of the brand is a primary goal of advertising. Research has shown that tracking eye movements is an effective indicator of understanding human attention and areas of interest. Therefore, integrating machine learning with eye-tracking data to predict advertisement effectiveness can enable advertisers to pre-test ads and improve their design, thereby enhancing ad efficiency.
Moreover, online advertisements can cause psychological discomfort and avoidance behavior in users who need to search for or read information. Balancing the need to leave a lasting impression with the need to avoid cognitive overload for users is a persistent challenge. This study aims to identify advertisement types that leave a strong impression without causing cognitive burden.
This research collected visual activity data from 60 participants using eye-tracking devices while they browsed news websites. Participants' recognition of advertisements was recorded through questionnaires. Statistical analyses were conducted to examine the impact of ad formats (static, dynamic) and positions (top, bottom, left, right) on attention, recognition, and reading concentration. Machine learning models were also used to predict participants' recognition of different ad types, providing advertisers with references for incorporating eye-tracking data into ad design.
The experimental results indicate that eye-tracking data combined with machine learning algorithms can broadly predict users' recognition of advertisements. The study also found that users paid more attention to ads placed at the top and bottom of webpages, while the format of the ads (static or dynamic) had no significant impact on attention distribution and recognition. Additionally, static ads placed on the left side of the page had higher recognition and reading concentration. It is recommended that companies and advertisers position ads on the left side of webpages to enhance user impression. These findings will assist advertisers in optimizing ad strategies and offer website designers insights for creating user-friendly websites. Future research can integrate eye-tracking with other psychological and physiological techniques to provide a more comprehensive analysis of user responses, thereby gaining deeper insights into users' emotional and cognitive reactions to advertisements.

摘要 I
Abstract III
誌謝辭 V
目錄 VI
表目錄 IX
圖目錄 XI
第一章 緒論 1
1.1 研究背景與動機 1
1.2 研究範圍與目的 3
1.3 研究流程 4
第二章 文獻回顧 6
2.1 眼動追蹤技術 6
2.1.1 眼動追蹤技術及指標 6
2.1.2 廣告與眼動追蹤 7
2.1.3 閱讀與眼動追蹤 8
2.2 廣告與注意力、再認力 9
2.2.1 廣告形式 9
2.2.2 廣告位置 10
2.2.3 注意力與再認力之關係 11
2.3 機器學習 11
2.3.1 監督式學習 12
2.3.2 分類模型 13
2.3.3 眼動數據與機器學習 16
2.4 小結 17
第三章 研究方法 18
3.1 研究對象 18
3.2 實驗設備 18
3.3 實驗流程 19
3.4 實驗設計 22
3.4.1 實驗題材選擇與問卷設計 22
3.4.2 眼動數據 28
3.4.3 實驗環境設計 30
3.5 統計分析 30
3.5.1 注意力分配與廣告形式及位置 30
3.5.2 再認力與廣告形式及位置 31
3.5.3 閱覽專注力 32
3.6 機器學習眼動預測再認力模型架構 32
第四章 實驗結果 37
4.1 受試者基本資料 37
4.2 不同廣告類型對眼動數據的影響 43
4.2.1 注意力分配 43
4.2.2 廣告再認力 46
4.2.3 閱覽專注力 47
4.3 機器學習眼動預測再認力模型成效 51
第五章 討論 58
5.1 廣告形式與位置對注意力分配之影響 58
5.2 廣告形式與位置對再認力之影響 59
5.3 網頁呈現方式對閱覽專注力之影響 60
5.4 機器學習再認程度預測系統 60
5.5 研究限制 62
第六章 結論與未來方向 64
參考文獻 66
附錄一 研究倫理委員會簡易審查結果通知書 72
附錄二 廣告再認問卷 74

[1] D. T. Hawkins, "Electronic advertising on online information systems," Online, vol. 18, no. 2, pp. 26-35, 1994.
[2] "台灣數位媒體應用暨行銷協會2021年之統計報告," DMA, 2021. [Online]. Available: https://www.dma.org.tw/newsPost/1339
[3] J. Lee and J.-H. Ahn, "Attention to banner ads and their effectiveness: An eye-tracking approach," International Journal of Electronic Commerce, pp. 119-137, 2012.
[4] Y.-H. Hong, "Which one is more annoying? Comparing the cognitive, affective and conative effects of button ads and pop-up Ads," Journalof BusinessandEconomics, p. 2074, 2014.
[5] B. Ur, P. G. Leon, L. F. Cranor, R. Shay, and Y. Wang, "Smart, useful, scary, creepy: perceptions of online behavioral advertising," in proceedings of the eighth symposium on usable privacy and security, 2012, pp. 1-15.
[6] C. Gerber, M. Terblanche-Smit, and T. Crommelin, "Brand recognition in television advertising: The influence of brand presence and brand introduction," Acta Commercii, vol. 14, no. 1, pp. 1-8, 2014.
[7] 陳俊宏、楊東民, 視覺傳達設計概論. 臺北縣: 全華圖書, 2008.
[8] A. T. Duchowski, "A breadth-first survey of eye-tracking applications," Behavior Research Methods, Instruments, & Computers, vol. 34, no. 4, pp. 455-470, 2002.
[9] R. L. Solso, Cognition and the visual arts. MIT press, 1994.
[10] M. Resnick and W. Albert, "The impact of advertising location and user task on the emergence of banner ad blindness: An eye-tracking study," International Journal of Human-Computer Interaction, vol. 30, no. 3, pp. 206-219, 2014.
[11] K. Sharma, M. Giannakos, and P. Dillenbourg, "Eye-tracking and artificial intelligence to enhance motivation and learning," Smart Learning Environments, vol. 7, pp. 1-19, 2020.
[12] C. J. Haug and J. M. Drazen, "Artificial intelligence and machine learning in clinical medicine, 2023," New England Journal of Medicine, vol. 388, no. 13, pp. 1201-1208, 2023.
[13] S. M. Edwards, H. Li, and J.-H. Lee, "Forced exposure and psychological reactance: Antecedents and consequences of the perceived intrusiveness of pop-up ads," Journal of advertising, pp. 83-95, 2002.
[14] M. Burke, A. Hornof, E. Nilsen, and N. Gorman, "High-cost banner blindness: Ads increase perceived workload, hinder visual search, and are forgotten," ACM Transactions on Computer-Human Interaction (TOCHI), vol. 12, no. 4, pp. 423-445, 2005.
[15] R. S. Hessels and I. T. Hooge, "Eye tracking in developmental cognitive neuroscience–The good, the bad and the ugly," Developmental cognitive neuroscience, vol. 40, p. 100710, 2019.
[16] L. Dempere-Marco, X. Hu, and G.-Z. Yang, "A novel framework for the analysis of eye movements during visual search for knowledge gathering," Cognitive Computation, vol. 3, pp. 206-222, 2011.
[17] P. Bera, P. Soffer, and J. Parsons, "Using eye tracking to expose cognitive processes in understanding conceptual models," MIS quarterly, vol. 43, no. 4, pp. 1105-1126, 2019.
[18] M. S. Sanders and E. J. McCormick, Human factors in engineering and design, 7th ed (Human factors in engineering and design, 7th ed.). New York, NY, England: Mcgraw-Hill Book Company, 1993, pp. xiii, 790-xiii, 790.
[19] L. Katus et al., "Implementing neuroimaging and eye tracking methods to assess neurocognitive development of young infants in low-and middle-income countries," Gates Open Research, vol. 3, 2019.
[20] S. P. Devlin, N. L. Brown, S. Drollinger, C. Sibley, J. Alami, and S. L. Riggs, "Scan-based eye tracking measures are predictive of workload transition performance," Applied ergonomics, vol. 105, p. 103829, 2022.
[21] A. Moran, M. Campbell, and D. Ranieri, "Implications of eye tracking technology for applied sport psychology," Journal of Sport Psychology in Action, vol. 9, no. 4, pp. 249-259, 2018.
[22] M. Kuhar and T. Merčun, "Exploring user experience in digital libraries through questionnaire and eye-tracking data," Library & Information Science Research, vol. 44, no. 3, p. 101175, 2022.
[23] M. L. Mele and S. Federici, "Gaze and eye-tracking solutions for psychological research," Cognitive processing, vol. 13, pp. 261-265, 2012.
[24] M. Nückles, "Investigating visual perception in teaching and learning with advanced eye-tracking methodologies: Rewards and challenges of an innovative research paradigm," Educational Psychology Review, vol. 33, no. 1, pp. 149-167, 2021.
[25] 李寻, 张丙辰, 杨俞玲, 顾芮冰, and 韦懿洋, "基于熵权法的学龄前儿童教育 APP 角色绘图方式评价," 包装工程艺术版, vol. 43, no. 10, pp. 300-311, 2022.
[26] P. Majaranta and A. Bulling, "Eye tracking and eye-based human–computer interaction," in Advances in physiological computing: Springer, 2014, pp. 39-65.
[27] Y. Mashhadi Hashem Marandi and H. Sajedi, "Intelligent Web Advertisement Based on Eye-Tracking and Machine Learning," International Journal of Web Research, vol. 3, no. 2, pp. 31-44, 2020.
[28] V. Kumar and S. Gupta, "Conceptualizing the evolution and future of advertising," Journal of advertising, vol. 45, no. 3, pp. 302-317, 2016.
[29] L.-A. Casado-Aranda, J. Sánchez-Fernández, and J.-Á. Ibáñez-Zapata, "Evaluating communication effectiveness through eye tracking: Benefits, state of the art, and unresolved questions," International Journal of Business Communication, vol. 60, no. 1, pp. 24-61, 2023.
[30] E. Rosbergen, R. Pieters, and M. Wedel, "Visual attention to advertising: A segment-level analysis," Journal of consumer research, vol. 24, no. 3, pp. 305-314, 1997.
[31] C. Bebko, L. M. Sciulli, and P. Bhagat, "Using eye tracking to assess the impact of advertising appeals on donor behavior," Journal of Nonprofit & Public Sector Marketing, vol. 26, no. 4, pp. 354-371, 2014.
[32] F. De Keyzer, N. Dens, and P. De Pelsmacker, "The processing of native advertising compared to banner advertising: an eye-tracking experiment," Electronic Commerce Research, vol. 23, no. 3, pp. 1921-1940, 2023.
[33] L. Popa, O. Selejan, A. Scott, D. F. Mureşanu, M. Balea, and A. Rafila, "Reading beyond the glance: eye tracking in neurosciences," Neurological Sciences, vol. 36, no. 5, pp. 683-688, 2015.
[34] X. Li, Y. Liu, J. Mao, Z. He, M. Zhang, and S. Ma, "Understanding reading attention distribution during relevance judgement," in Proceedings of the 27th ACM international conference on information and knowledge management, 2018, pp. 733-742.
[35] K. Minakata and S. Beier, "The effect of font width on eye movements during reading," Applied ergonomics, vol. 97, p. 103523, 2021.
[36] E. R. Schotter, R. Tran, and K. Rayner, "Don’t believe what you read (only once) comprehension is supported by regressions during reading," Psychological science, vol. 25, no. 6, pp. 1218-1226, 2014.
[37] D. C. Mézière, L. Yu, E. D. Reichle, T. Von Der Malsburg, and G. McArthur, "Using Eye‐Tracking Measures to Predict Reading Comprehension," Reading Research Quarterly, vol. 58, no. 3, pp. 425-449, 2023.
[38] J.-H. Ahn, Y.-S. Bae, J. Ju, and W. Oh, "Attention adjustment, renewal, and equilibrium seeking in online search: an eye-tracking approach," Journal of Management Information Systems, vol. 35, no. 4, pp. 1218-1250, 2018.
[39] J. Kuisma, J. Simola, L. Uusitalo, and A. Öörni, "The effects of animation and format on the perception and memory of online advertising," Journal of Interactive Marketing, vol. 24, no. 4, pp. 269-282, 2010.
[40] M. E. Bayles, "Designing online banner advertisements: Should we animate?," in Proceedings of the SIGCHI conference on human factors in computing systems, 2002, pp. 363-366.
[41] J. Lee, J.-H. Ahn, and B. Park, "The effect of repetition in Internet banner ads and the moderating role of animation," Computers in human behavior, vol. 46, pp. 202-209, 2015.
[42] C. Y. Yoo, K. Kim, and P. A. Stout, "Assessing the effects of animation in online banner advertising: Hierarchy of effects model," Journal of interactive advertising, vol. 4, no. 2, pp. 49-60, 2004.
[43] Y.-L. Lai, K. K. Kuan, K.-L. Hui, and N. Liu, "The effects of moving animation on recall, hedonic and utilitarian perceptions, and attitude," IEEE Transactions on Engineering Management, vol. 56, no. 3, pp. 468-477, 2009.
[44] M. Naik, Y. Suryawanshi, and A. Atre, "UNLEASHING THE POWER OF ANIMATION IN MARKETING: INSIGHTS AND IMPLICATIONS," The Online Journal of Distance Education and e-Learning, vol. 11, no. 2, 2023.
[45] J. W. Owens, B. S. Chaparro, and E. M. Palmer, "Text advertising blindness: the new banner blindness?," Journal of usability studies, vol. 6, no. 3, pp. 172-197, 2011.
[46] K. Gidlöf, N. Holmberg, and H. Sandberg, "The use of eye-tracking and retrospective interviews to study teenagers’ exposure to online advertising," Visual Communication, vol. 11, no. 3, pp. 329-345, 2012.
[47] S. Heinz and E. D. Mekler, "The influence of banner placement and navigation style on the recognition of advertisement banners," in Proceedings of the 7th Nordic Conference on Human-Computer Interaction: Making Sense Through Design, 2012, pp. 803-804.
[48] D. H. Murphy and A. D. Castel, "Responsible attention: The effect of divided attention on metacognition and responsible remembering," Psychological Research, vol. 87, no. 4, pp. 1085-1100, 2023.
[49] J. M. Gardiner and A. J. Parkin, "Attention and recollective experience in recognition memory," Memory & Cognition, vol. 18, pp. 579-583, 1990.
[50] S. B. MacKenzie, "The role of attention in mediating the effect of advertising on attribute importance," Journal of Consumer Research, vol. 13, no. 2, pp. 174-195, 1986.
[51] M. I. Jordan and T. M. Mitchell, "Machine learning: Trends, perspectives, and prospects," Science, vol. 349, no. 6245, pp. 255-260, 2015.
[52] E. G. Learned-Miller, "Introduction to supervised learning," I: Department of Computer Science, University of Massachusetts, vol. 3, 2014.
[53] Y.-Y. Song and L. Ying, "Decision tree methods: applications for classification and prediction," Shanghai archives of psychiatry, vol. 27, no. 2, p. 130, 2015.
[54] B. E. Boser, I. M. Guyon, and V. N. Vapnik, "A training algorithm for optimal margin classifiers," in Proceedings of the fifth annual workshop on Computational learning theory, 1992, pp. 144-152.
[55] S. Suthaharan, "Support vector machine," Machine learning models and algorithms for big data classification: thinking with examples for effective learning, pp. 207-235, 2016.
[56] L. Breiman, "Random forests," Machine learning, vol. 45, pp. 5-32, 2001.
[57] L. Breiman, "Bagging predictors," Machine learning, vol. 24, pp. 123-140, 1996.
[58] T. Chen and C. Guestrin, "Xgboost: A scalable tree boosting system," in Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining, 2016, pp. 785-794.
[59] Q. Wei, H. Cao, Y. Shi, X. Xu, and T. Li, "Machine learning based on eye-tracking data to identify Autism Spectrum Disorder: A systematic review and meta-analysis," Journal of biomedical informatics, vol. 137, p. 104254, 2023.
[60] C. Schweikert, L. Gobin, S. Xie, S. Shimojo, and D. Frank Hsu, "Preference prediction based on eye movement using Multi-layer Combinatorial Fusion," in Brain Informatics: International Conference, BI 2018, Arlington, TX, USA, December 7–9, 2018, Proceedings 11, 2018: Springer, pp. 282-293.
[61] W. Liu, Y. Cao, and R. W. Proctor, "How do app icon color and border shape influence visual search efficiency and user experience? Evidence from an eye-tracking study," International Journal of Industrial Ergonomics, vol. 84, p. 103160, 2021.
[62] 蔡卓芳, 鍾珮琦, and 齊湘, "台灣新聞網站市場範圍與市場競爭初探---以《 聯合新聞網》,《 中時電子報》,《 東森新聞報》 三大新聞網站為例分析," 2003.
[63] M. O. AB, "Banner Sizes: The Must-Have Banners for 2023," in The Match2One Blog vol. 2023, ed, 2023.
[64] OKO, "Top Performing Ad Sizes and Placements in Google Ad Manager," in OKO, ed, 2019.
[65] GrowthSpot, "Google 多媒體廣告最佳尺寸懶人包," in GrowthSpot, ed, 2022.
[66] 蕭國淳, "網頁廣告呈現方式與瀏覽動機對於使用者視覺注意與項目記憶的影響," 2005.
[67] P. G. Zimbardo and 游恆山, "心理學, 五南出版, 台北," 1988.
[68] A. Lang, "The limited capacity model of mediated message processing," Journal of communication, vol. 50, no. 1, pp. 46-70, 2000.
[69] 楊秀敏, "線上遊戲產品置入傳播效果研究: 以線上遊戲創作 [kuso 世代] 為例," ed: 國立政治大學廣告學系研究所碩士論文, 2004.
[70] M. Lee and R. J. Faber, "Effects of product placement in on-line games on brand memory: A perspective of the limited-capacity model of attention," Journal of advertising, vol. 36, no. 4, pp. 75-90, 2007.
[71] K.-C. Hamborg, M. Bruns, F. Ollermann, and K. Kaspar, "The effect of banner animation on fixation behavior and recall performance in search tasks," Computers in Human Behavior, vol. 28, no. 2, pp. 576-582, 2012.
[72] M. Koester, M. Rüth, K. C. Hamborg, and K. Kaspar, "Effects of personalized banner ads on visual attention and recognition memory," Applied Cognitive Psychology, vol. 29, no. 2, pp. 181-192, 2015.
[73] 陳志銘 and 林惠卿, "大學圖書館網站讀者視覺注意力之眼動分析研究," 圖資與檔案學刊, no. 87, pp. 25-53, 2015.
[74] 李幸珊, "以眼動儀方法研究行動裝置上橫幅廣告之盲點效應," 撰者, 2020.
[75] 許惠晴, "利用眼動追蹤法探討網路使用習慣對專注力的影響," 2012.
[76] A. Durand and G. M. GOULD, "A method of determining ocular dominance," Journal of the American Medical Association, vol. 55, no. 5, pp. 369-370, 1910.
[77] 陳洋月, "反應時間的量測會受慣用手與慣用眼影響嗎?," 臺灣師範大學體育學系學位論文, vol. 2016, pp. 1-52, 2016.
[78] J. B. Rotter, "Generalized expectancies for internal versus external control of reinforcement," Psychological monographs: General and applied, vol. 80, no. 1, p. 1, 1966.
[79] 曾淑美, "社群媒體廣告特質對顧客購買意願的影響：以内外控人格特質為調節變數," Journal of Information, Technology and Society, vol. 22, pp. 1-20, 2022.
[80] R. A. Stebbins, The serious leisure perspective. Springer, 2015.
[81] J. Hartel, "The serious leisure frontier in library and information science: Hobby domains," Knowledge organization, vol. 30, no. 3/4, pp. 228-238, 2003.
[82] 洪佳盟, "數位繪本教學對國中生專注力, 創意思考能力與英語閱讀成效之影響," 2014.
[83] 張格瑜 and 佘曉清, "運用眼動儀探討不同學科背景大學生之細胞擴散和滲透作用的心智表徵建構," 2007.
[84] R. Pieters, E. Rosbergen, and M. Wedel, "Visual attention to repeated print advertising: A test of scanpath theory," Journal of marketing research, vol. 36, no. 4, pp. 424-438, 1999.
[85] C. Y. Yoo and K. Kim, "Processing of animation in online banner advertising: The roles of cognitive and emotional responses," Journal of Interactive marketing, vol. 19, no. 4, pp. 18-34, 2005.
[86] L.-A. Casado-Aranda, J. Sánchez-Fernández, and F. J. Montoro-Ríos, "Neural correlates of voice gender and message framing in advertising: A functional MRI study," Journal of Neuroscience, Psychology, and Economics, vol. 10, no. 4, p. 121, 2017.