近年來，由於資訊科技的發達，以及新冠疫情的肆虐，各國消費者的消費習慣逐漸由實體購物轉型成線上購物，因此網路零售業之銷售額逐年攀升，成長力道逐漸增強。線上交易之優勢即為能夠透過網站資料庫紀錄用戶資料，以及用戶之瀏覽歷史、購物歷史，經由推薦系統大數據之計算，推算出用戶可能感興趣之商品，提供商品推薦。
現今推薦系統之運作主要是由用戶資料及過去瀏覽、購物歷史共同計算並推薦，此方式即為有點擊、有行為，才有資料，缺乏直接、動態接收用戶與網站互動的管道，因此無法得知用戶使用網站當下的感受和想法。而有研究指出視覺刺激影響人類感受最為強烈，並且證實眼動追蹤數據與消費者興趣存在著相關性，因此本研究將以眼動追蹤探討消費者在線上購物時的購物歷程及購物偏好。
本研究以眼動儀蒐集60位無眼部疾病之受試者在線上購物時的視覺活動，並記錄受試者欲購買的商品，後以統計分析及機器學習分類模型搭配視覺數據分析出用戶欲購買的商品、圖片複雜度的影響，及消費者購物時的考量因子，提供電商平台開發及設計之參考。
實驗結果顯示：以眼動數據搭配機器學習算法能夠大方向預測消費者會購買的商品，因此電商平台推薦系統加入眼動數據是有其應用價值的，且機器學習算法能夠在眼動數據的分類上有良好的表現。在商品圖片、商品價格、商品評價及銷售量此三商品資訊中，受試者在選購享樂性商品時，較關注的是商品的圖片，而在選購實用性商品時，受試者在此三個商品資訊上皆有所關注，此結果可應用在電商平台的行銷活動上，讓平台更有效地將產品推銷給消費者。未來研究建議可將消費者性格納入眼動預測研究中，將不同性格之消費者進行區分後，再以眼動數據計算消費者在每個商品的喜愛程度，同時與消費者的其他資訊聯合分析，提供更個人化的推薦。

In recent years, due to the development of information technology and the ravages of the COVID-19 pandemic, the consumption habits of consumers in various countries have gradually shifted from physical shopping to online shopping. As a result, the sales of the online retail industry have been increasing year by year, and the growth momentum has gradually strengthened. The advantage of online transactions is that it can record user information through the website database, as well as the user's browsing history and shopping history. Through the calculation of the big data of the recommendation system, it can calculate the products that the user may be interested in and provide product recommendations.
The operation of the current recommendation system is mainly calculated by user data, past browsing history, and shopping history. This method means that if there are clicks and behaviors, there exist data. There is no direct and dynamic channel for receiving user interaction with the website, so it is impossible to understand the user's current feelings and thoughts when using the website. Some studies have pointed out that visual stimuli have the strongest impact on human perception, and have confirmed the correlation between eye-tracking data and consumer interests. Therefore, this study will use eye tracker to explore consumers' shopping journeys and shopping preferences when shopping online.
In this study, the eye tracker was used to collect the visual activities of 60 subjects without eye diseases when they shopping online, and we also recorded the items that the subjects wanted to buy. Then used statistical analysis and machine learning classification models with visual data to analyze the users’ desired products purchased, the effect of complexity of the pictures, and the consideration factors that affect consumers' shopping, which can provide results and suggestion for the development and design of e-commerce platforms.
The research results showed that: the use of eye-tracking data and machine learning algorithms can predict the products that consumers will buy in a general direction. Therefore, adding eye tracking data to the e-commerce platform’s recommendation system has its application value, and also the machine learning algorithm had good performance of classification with eye-tracking data. Among three product information, product pictures, product prices, product reviews and sales volume, the subjects paid more attention to the pictures of the products when purchasing hedonic products, while when purchasing utilitarian products, the subjects paid equal attention to three product information. This result can be applied to the marketing activities of the e-commerce platform, so that the platform can sell products to consumers more effectively. For future studies, consumer personality can be included in eye movement prediction research. After distinguishing consumers with different personalities, eye-tracking data can be used to calculate consumers’ preference for each product, and at the same time, it can be jointly analyzed with other information of consumers to make more personalized recommendations.

[1] 產業經濟統計. [Online] Available: https://www.moea.gov.tw/Mns/dos/bulletin/Bulletin.aspx?kind=9&html=1&menu_id=18808&bull_id=9673
[2] McKinsey&Company, "How retailers can keep up with consumers," 2013. [Online]. Available: https://www.mckinsey.com/industries/retail/our-insights/how-retailers-can-keep-up-with-consumers
[3] R. Rathee and M. P. Rajain, "Sensory marketing-investigating the use of five senses," International Journal of Research in Finance and Marketing, vol. 7, no. 5, pp. 124-133, 2017.
[4] 野村順一, 色彩的秘密–最新色彩學入門. 東京：文藝春秋, 1996.
[5] L. N. van der Laan, I. T. Hooge, D. T. De Ridder, M. A. Viergever, and P. A. Smeets, "Do you like what you see? The role of first fixation and total fixation duration in consumer choice," Food Quality and Preference, vol. 39, pp. 46-55, 2015.
[6] S. Jantathai, L. Danner, M. Joechl, and K. Dürrschmid, "Gazing behavior, choice and color of food: Does gazing behavior predict choice?," Food Research International, vol. 54, no. 2, pp. 1621-1626, 2013.
[7] L. Sharma and A. Gera, "A survey of recommendation system: Research challenges," International Journal of Engineering Trends and Technology (IJETT), vol. 4, no. 5, pp. 1989-1992, 2013.
[8] A. L. Montgomery, S. Li, K. Srinivasan, and J. C. Liechty, "Modeling online browsing and path analysis using clickstream data," Marketing science, vol. 23, no. 4, pp. 579-595, 2004.
[9] A. Papoutsaki, "Scalable Webcam Eye Tracking by Learning from User Interactions," in Proceedings of the 33rd Annual ACM Conference Extended Abstracts on Human Factors in Computing Systems, 2015, pp. 219-222.
[10] I. Portugal, P. Alencar, and D. Cowan, "The use of machine learning algorithms in recommender systems: A systematic review," Expert Systems with Applications, vol. 97, pp. 205-227, 2018.
[11] K. Tsuji, F. Yoshikane, S. Sato, and H. Itsumura, "Book recommendation using machine learning methods based on library loan records and bibliographic information," in 2014 IIAI 3rd International Conference on Advanced Applied Informatics, 2014: IEEE, pp. 76-79.
[12] S. Zahra, M. A. Ghazanfar, A. Khalid, M. A. Azam, U. Naeem, and A. Prugel-Bennett, "Novel centroid selection approaches for KMeans-clustering based recommender systems," Information sciences, vol. 320, pp. 156-189, 2015.
[13] M. Nilashi, K. Bagherifard, M. Rahmani, and V. Rafe, "A recommender system for tourism industry using cluster ensemble and prediction machine learning techniques," Computers & industrial engineering, vol. 109, pp. 357-368, 2017.
[14] M. Krol and M. Krol, "A novel approach to studying strategic decisions with eye-tracking and machine learning," Judgment and Decision Making, vol. 12, no. 6, p. 596, 2017.
[15] Y. Lou, Y. Liu, J. K. Kaakinen, and X. Li, "Using support vector machines to identify literacy skills: Evidence from eye movements," Behavior research methods, vol. 49, no. 3, pp. 887-895, 2017.
[16] S. Hoppe, T. Loetscher, S. A. Morey, and A. Bulling, "Eye movements during everyday behavior predict personality traits," Frontiers in human neuroscience, p. 105, 2018.
[17] Z. Zhao, H. Tang, X. Zhang, X. Qu, X. Hu, and J. Lu, "Classification of children with autism and typical development using eye-tracking data from face-to-face conversations: Machine learning model development and performance evaluation," Journal of Medical Internet Research, vol. 23, no. 8, p. e29328, 2021.
[18] J. Pfeiffer, T. Pfeiffer, M. Meißner, and E. Weiß, "Eye-tracking-based classification of information search behavior using machine learning: evidence from experiments in physical shops and virtual reality shopping environments," Information Systems Research, vol. 31, no. 3, pp. 675-691, 2020.
[19] M. Shepherd, J. M. Findlay, and R. J. Hockey, "The relationship between eye movements and spatial attention," The Quarterly Journal of Experimental Psychology, vol. 38, no. 3, pp. 475-491, 1986.
[20] H. Deubel and W. X. Schneider, "Saccade target selection and object recognition: Evidence for a common attentional mechanism," Vision research, vol. 36, no. 12, pp. 1827-1837, 1996.
[21] J. L. Orquin and S. M. Loose, "Attention and choice: A review on eye movements in decision making," Acta psychologica, vol. 144, no. 1, pp. 190-206, 2013.
[22] 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.
[23] 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.
[24] 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.
[25] 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.
[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] B. K. Behe, M. Bae, P. T. Huddleston, and L. Sage, "The effect of involvement on visual attention and product choice," Journal of Retailing and Consumer Services, vol. 24, pp. 10-21, 2015.
[28] P. Chandon, J. Hutchinson, E. Bradlow, and S. H. Young, "Measuring the value of point-of-purchase marketing with commercial eye-tracking data," INSEAD Business School Research Paper, no. 2007/22, 2006.
[29] J. N. Sari, L. E. Nugroho, P. I. Santosa, and R. Ferdiana, "The measurement of consumer interest and prediction of product selection in E-commerce using eye tracking method," International Journal of Intelligent Engineering and Systems, vol. 11, no. 1, pp. 30-40, 2018.
[30] Y. M. Hwang and K. C. Lee, "Using an eye-tracking approach to explore gender differences in visual attention and shopping attitudes in an online shopping environment," International Journal of Human–Computer Interaction, vol. 34, no. 1, pp. 15-24, 2018.
[31] Q. Wang, D. Ma, H. Chen, X. Ye, and Q. Xu, "Effects of background complexity on consumer visual processing: An eye-tracking study," Journal of Business Research, vol. 111, pp. 270-280, 2020.
[32] T. M. H. Vu, V. P. Tu, and K. Duerrschmid, "Design factors influence consumers’ gazing behaviour and decision time in an eye-tracking test: A study on food images," Food Quality and Preference, vol. 47, pp. 130-138, 2016.
[33] M. I. Jordan and T. M. Mitchell, "Machine learning: Trends, perspectives, and prospects," Science, vol. 349, no. 6245, pp. 255-260, 2015.
[34] E. G. Learned-Miller, "Introduction to supervised learning," I: Department of Computer Science, University of Massachusetts, p. 3, 2014.
[35] 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.
[36] S. Suthaharan, "Support vector machine," in Machine learning models and algorithms for big data classification: Springer, 2016, pp. 207-235.
[37] L. Breiman, "Random forests," Machine learning, vol. 45, no. 1, pp. 5-32, 2001.
[38] L. Breiman, "Bagging predictors," Machine learning, vol. 24, no. 2, pp. 123-140, 1996.
[39] 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.
[40] C. Schweikert, L. Gobin, S. Xie, S. Shimojo, and D. Frank Hsu, "Preference prediction based on eye movement using Multi-layer Combinatorial Fusion," in International Conference on Brain Informatics, 2018: Springer, pp. 282-293.
[41] D. Das, L. Sahoo, and S. Datta, "A survey on recommendation system," International Journal of Computer Applications, vol. 160, no. 7, 2017.
[42] P. Resnick, N. Iacovou, M. Suchak, P. Bergstrom, and J. Riedl, "Grouplens: An open architecture for collaborative filtering of netnews," in Proceedings of the 1994 ACM conference on Computer supported cooperative work, 1994, pp. 175-186.
[43] J. B. Schafer, D. Frankowski, J. Herlocker, and S. Sen, "Collaborative filtering recommender systems," in The adaptive web: Springer, 2007, pp. 291-324.
[44] P. B. Thorat, R. M. Goudar, and S. Barve, "Survey on collaborative filtering, content-based filtering and hybrid recommendation system," International Journal of Computer Applications, vol. 110, no. 4, pp. 31-36, 2015.
[45] A. B. Barragáns-Martínez, E. Costa-Montenegro, J. C. Burguillo, M. Rey-López, F. A. Mikic-Fonte, and A. Peleteiro, "A hybrid content-based and item-based collaborative filtering approach to recommend TV programs enhanced with singular value decomposition," Information Sciences, vol. 180, no. 22, pp. 4290-4311, 2010.
[46] R. Burke, "Hybrid recommender systems: Survey and experiments," User modeling and user-adapted interaction, vol. 12, no. 4, pp. 331-370, 2002.
[47] D. Filev and R. R. Yager, "On the issue of obtaining OWA operator weights," Fuzzy sets and systems, vol. 94, no. 2, pp. 157-169, 1998.
[48] J. Basiri, A. Shakery, B. Moshiri, and M. Z. Hayat, "Alleviating the cold-start problem of recommender systems using a new hybrid approach," in 2010 5th International Symposium on Telecommunications, 2010: IEEE, pp. 962-967.
[49] B. Walek and V. Fojtik, "A hybrid recommender system for recommending relevant movies using an expert system," Expert Systems with Applications, vol. 158, p. 113452, 2020.
[50] H. Song and N. Moon, "Eye-tracking and social behavior preference-based recommendation system," The Journal of Supercomputing, vol. 75, no. 4, pp. 1990-2006, 2019.
[51] S. Jaiswal, S. Virmani, V. Sethi, K. De, and P. P. Roy, "An intelligent recommendation system using gaze and emotion detection," Multimedia Tools and Applications, vol. 78, no. 11, pp. 14231-14250, 2019.
[52] R. Dhar and K. Wertenbroch, "Consumer choice between hedonic and utilitarian goods," Journal of marketing research, vol. 37, no. 1, pp. 60-71, 2000.
[53] A. Gere, L. Danner, N. de Antoni, S. Kovács, K. Dürrschmid, and L. Sipos, "Visual attention accompanying food decision process: An alternative approach to choose the best models," Food Quality and Preference, vol. 51, pp. 1-7, 2016.
[54] O. Sagi and L. Rokach, "Ensemble learning: A survey," Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery, vol. 8, no. 4, p. e1249, 2018.
[55] K. Humphrey and G. Underwood, "The potency of people in pictures: Evidence from sequences of eye fixations," Journal of Vision, vol. 10, no. 10, pp. 19-19, 2010.
[56] Q. Wang, Y. Yang, Q. Wang, and Q. Ma, "The effect of human image in B2C website design: an eye-tracking study," Enterprise Information Systems, vol. 8, no. 5, pp. 582-605, 2014.
[57] A. Furnham and H. C. Boo, "A literature review of the anchoring effect," The journal of socio-economics, vol. 40, no. 1, pp. 35-42, 2011.
[58] P. W. Miniard, S. Bhatla, K. R. Lord, P. R. Dickson, and H. R. Unnava, "Picture-based persuasion processes and the moderating role of involvement," Journal of consumer research, vol. 18, no. 1, pp. 92-107, 1991.
[59] Y. Li and Y. Xie, "Is a picture worth a thousand words? An empirical study of image content and social media engagement," Journal of Marketing Research, vol. 57, no. 1, pp. 1-19, 2020.