臺灣博碩士論文加值系統

　　隨著現代網路的普遍化，一般人使用網路的時間也大大的增加，社群媒體的成熟、資訊傳遞方法的改變，也使得廣告產業近幾年在網路上有著蓬勃的發展。

　　網路廣告則通常根據點擊率(Click through rate，縮寫CTR)，又稱點閱率，也就是根據廣告被使用者點擊的次數與廣告顯示的次數，來衡量廣告的成效；然而實際上，當人們受到網路上的廣告吸引時，滑鼠的點擊卻並非必要的動作，「觀看者視線」是否有在廣告上才是真正的判斷依據，而現今的廣告成效計算方法並未考量到「觀看者視線」這個因素。

　　因此，本論文使用「眼動儀」進行眼睛追蹤，透過我們所開發的系統，直接蒐集觀看者觀看廣告的資料並整理成適合我們分析的資料集，從而使我們能以更專業且客觀的角度，來了解眼睛視線與廣告之間的互動關係，同時，我們還使用人工智慧機器學習方法，進一步的對於我們所蒐集的資料進行分析，讓機器去判斷、預測廣告的成效，使我們能知道觀看者是否對該廣告有了注意或是從中產生了興趣。

　　Thanks to the popularity of modern networks, the number of Internet users has been growing high. More people watch videos on the Internet than that on televisions. Advertising industry on the Internet experience a vigorous growth in recent years. At the same time, people come to perceive different opinions and thoughts on the efficiency of video advertisements.

　　Online advertising is usually based on “CTR”, an abbreviation of “Click through Rate”, to measure the efficiency of the advertisements or the total length of footage that advertisements showed to the viewers and the number of times each advertisement is actually clicked by the viewers. However, these evaluation methods are generally considered only reference-worthy. There is a more promising way to confirm the advertisements are actually watched by people. It is eye tracking technology.

　　Our research discusses the application of eye tracking device, through the visual analysis system we developed, to collect the information from viewers’ sight line, which directly allows us to recognize in which objects or details that video viewers are interested and to further acknowledge the efficiency of video advertisements. Furthermore, we also employ the technology of Artificial Intelligence - Machine Learning in the system, so the machine can analyze the final result and to further predict more information from data we have collected in the advertisements.

摘要 I
Abstract II
目錄 III
圖目錄 IV
表目錄 V
第一章 前言 1
第二章 文獻探討 3
2.1 影像廣告的效益 3
2.2 眼動追蹤技術 4
2.3 影像廣告與眼動追蹤的互動關係 7
2.4 Area of Interest (AOI) 9
2.5 人工智慧機器學習 11
第三章 研究方法與設計 17
3.1 視覺分析系統 17
3.1.1 影像控制與AOI繪製 18
3.1.2 視點紀錄與資料處理 23
3.2 眼動儀的連結與資料蒐集的方法 25
3.2.1 眼動儀的連結 26
3.2.2 資料蒐集的方法 27
3.3 資料前處理 32
3.4 機器學習的訓練和演算法模型 35
第四章 研究結果與發現 37
第五章 結論 40
參考文獻 42
附錄一：廣告觀後問卷 45

1.Aga Bojko (2013). Eye Tracking the User Experience. Rosenfeld Media, Brooklyn, New York.
2.Alex Poole, Linden J Ball, and Peter Phillips (2004). In search of salience: A response time and eye-movement analysis of book mark recognition. People and Computers XVIII - Desgin for Life: Proceedings of HCI, pp. 363-378.
3.B. Edelman, M. Ostrovsky, and M. Schwarz (2007). Internet Advertising and the Generalized Second Price Auction: Selling Billions of Dollars Worth Of Keywords. Benjamin Edelman & Michael Ostrovsky & Michael Schwarz, pp. 242-259.
4.B. Wooley (2015). The influence of dynamic content on visual attention during television commercials, Murdoch Univ., Dubai, United Arab Emirates.
5.Bergstrom, J. R., and Schall, A. (Eds.) (2012). Eye tracking in user experience design. Elsevier, pp.81-85.
6.Chenyu Li, Jun Liu, and Shuxin Ouyang (2016). Characterizing and Predicting the Popularity of Online Videos. IEEE Access, (Volume: 4), pp. 1630-1641.
7.Edward K Strong (1925). The Psychology of Selling and Advertising. McGraw-Hill Book Co., New York.
8.Gazepoint GP3 Eye Tracker [Online]. Available: https://www.gazept.com/product/gazepoint-gp3-eye-tracker/
9.J. R. Quinlan (1986). Induction of decision trees. Machine Learning, Springer US, pp. 81-106.
10.Joseph Redmon, Santosh Divvala, Ross Girshick, and Ali Farhadi (2016). You Only Look Once: Unified, Real-Time Object Detection. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 27-30.
11.K. C. Yang, C. Yang, C. H. Huang, P. H. Shih, and S. Y. Yang (2014). Consumer attitudes toward online video advertising: An empirical study on YouTube as platform, IEEE International Conference on Industrial Engineering and Engineering Management, pp. 9-12.
12.L. Breiman (2001), Random Forests, Machine Learning, pp. 5-32.
13.Mao Wang, Yoichiro Maeda, and Yasutake Takahashi (2012). Human intention recognition via eye tracking based on fuzzy inference. The 6th International Conference on Soft Computing and Intelligent Systems, and The 13th International Symposium on Advanced Intelligence Systems, pp. 20-24.
14.Marco Porta, Alice Ravarelli, and Francesco Spaghi (2012). Online newspapers and ad banners: an eye tracking study on the effects of congruity. Online Information Review, Vol. 37 Issue: 3, pp.405-423.
15.Panos Louridas, and Christof Ebert (2016). Machine Learning. IEEE Software, pp. 110-115.
16.Pei-Shan Wei, and Hsi-Peng Lu (2013). An examination of the celebrity endorsements and online customer reviews influence female consumers’ shopping behavior. Computers in Human Behavior, 29, pp.193-201.
17.R. Alexander et al. (2000). Systems and methods for displaying and recording control interface with television programs, video, advertising information and program scheduling information. U.S. Patent 6177931.
18.R. J. K. Jacob, and K. S. Karn (2003). Eye tracking in human-computer interaction and usability research: Ready to deliver the promises. Mind, vol. 2, no. 3, pp. 4.
19.Rik Pieters, and Michel Wedel (2004). Attention Capture and Transfer in Advertising: Brand, Pictorial, and Text-Size Effects. Journal of Marketing, pp. 36-50.
20.Ritu Lohtia, Naveen Donthu, and Idil Yaveroglu (2017). Evaluating the efficiency of Internet banner advertisements. Journal of Business Research, Volume 60, Issue 4, pp. 365-370.
21.Satoshi Kono (2009). From the marketers' perspective: The interactive media situation in Japan. Television Goes Digital, pp.57-59.
22.Sohil Jain, and Dr. Deepak Garg (2014). Evaluating Quality Score of New Ads. International Conference on Advances in Computing, Communications and Informatics (ICACCI), pp. 24-27.
23.Tin Kam Ho (1995). Random decision forests. ICDAR '95 Proceedings of the Third International Conference on Document Analysis and Recognition, pp. 278.
24.Tukur Dahiru (2008). P-value, a true test of statistical significance? a cautionary note. Annals of Ibadan Postgraduate Medicine 6(1), pp. 21-26.
25.Wedel, M., and Pieters, R. (2007). A Review of Eye-Tracking Research in Marketing, Review of Marketing Research, pp. 123-147.
26.White SJ (2012). Eye Movement Control during Reading: Effects of Word Frequency and Orthographic Familiarity. Journal of Experimental Psychology Human Perception & Performance, pp.205-223.
27.Xuebai Zhang, and Shyan-Ming Yuan (2018). An Eye Tracking Analysis for Video Advertising: Relationship between Advertisement Elements and Effectiveness, IEEE Access, pp. 10699-10707.
28.Y. C. Hsieh, and K. H. Chen (2011). How different information types affect viewer’s attention on Internet advertising. Computers in Human Behavior, vol. 27, no. 2, pp. 935-945.
29.Zhang, J., Wedel, M., and Pieters, R. (2009). Sales Effects of Attention to Feature Advertisements: A Bayesian Mediation Analysis. Journal of Marketing Research, pp. 669-681.