一画胜千言:图像数据在营销领域的应用

A Picture Is Worth a Thousand Words: The Application of Image Data in Marketing

徐婕,肖莉

2022 第 44 卷 第 09 期 页码 51-69

DOI: 10.16538/j.cnki.fem.20220621.301

PDF全文下载 HTML全文

摘要

随着图像生成、存储技术的发展,图像数据已成为越来越重要的信息载体,尤其是在社交媒体平台上,用户生成的图像内容包含了比文字更丰富的信息,是企业获取消费者洞察的重要数据来源。本文首先介绍了图像的定义和分类以及图像数据的存储方式,然后介绍了图像数据的分析方法以及分析步骤,接下来从营销活动的产品、价格和推广三大方面分别回顾了国内外利用图像数据开展的相关营销实践以及相关营销学术研究,并在此基础上提炼出基于图像分析的重要研究课题和前沿方向。

With the vigorous development of image generation, storage technology and social media, image data has become an increasingly important information carrier and an important data source for enterprises to obtain consumer insight. However, image data is difficult to analyze and process because of its unstructured data characteristics, and there are few marketing studies on image analytics at present. Therefore, there is a certain gap between research and practice, and the existing theoretical results are difficult to give full guidance to the booming marketing practice.

This paper first combs the relevant concepts of image analytics and the relevant marketing practice carried out by image analytics at home and abroad. Then, it reviews the relevant marketing literature based on image analytics, extracts important topics and cutting-edge directions, analyzes the theoretical gaps in the current research, and looks forward to future research.

In the relevant marketing research field, we select 20 representative core papers from 19 international top journals in the field of marketing, management science, and information systems. Some well-cited working papers are also included to represent the cutting-edge marketing research utilizing image analytics. Generally speaking, the marketing research literature utilizing image analytics is somewhat sparse and mostly published after 2017, which mainly focuses on the fields of brand management, communication management and customer relationship management, and deep learning methods are ubiquitously used.

Based on the review of relevant marketing research and practice, this paper further proposes and discusses six potential directions for future research: Consumer behavioral research that utilizes image analytics to investigate theoretical mechanisms; product design with artificial intelligence; real-time responses to customer needs; how to increase model interpretability; multi-type image data and multi-modal data; and how to improve the fairness of products or services.

The main contributions of this paper are as follows: First, it reviews the fundamental concepts and methods of image analytics, providing guidance for marketing scholars to carry out relevant research. Second, it identifies and discusses some major research streams in marketing that image analytics could potentially be utilized. Third, it proposes several potential directions for future research, hoping to provide inspirations for domestic marketing scholars and call on more scholars to participate in this type of research.

参考文献

2 费显政, 肖登洋. 移动端应用软件图标的触觉心象对消费者偏好的影响研究[J]. 管理世界,2020, 36(7): 153-170. DOI:10.19744/j.cnki.11-1235/f.2020.0108
8 刘业政, 孙见山, 姜元春, 等. 大数据的价值发现: 4C模型[J]. 管理世界,2020, 36(2): 129-138. DOI:10.3969/j.issn.1002-5502.2020.02.012
10 钱明辉, 徐志轩. 基于机器学习的消费者品牌决策偏好动态识别与效果验证研究[J]. 南开管理评论,2019, 22(3): 66-76. DOI:10.3969/j.issn.1008-3448.2019.03.007
12 朱翊敏. 慈善营销中契合类型与信息框架对消费者响应的影响[J]. 南开管理评论,2014, 17(4): 128-139. DOI:10.3969/j.issn.1008-3448.2014.04.014
13 Aouf R S. Algorithm designs seven million different jars of Nutella[EB/OL]. https://www.dezeen.com/2017/06/01/algorithm-seven-million-different-jars-nutella-packaging-design, 2017-06-01.
14 Balducci B, Marinova D. Unstructured data in marketing[J]. Journal of the Academy of Marketing Science,2018, 46(4): 557-590. DOI:10.1007/s11747-018-0581-x
15 Berry D S, McArthur L Z. Some components and consequences of a babyface[J]. Journal of Personality and Social Psychology,1985, 48(2): 312-323. DOI:10.1037/0022-3514.48.2.312
16 Burnap A, Hauser J R, Timoshenko A. Design and evaluation of product aesthetics: A human-machine hybrid approach[EB/OL]. http://dx.doi.org/10.2139/ssrn.3421771, 2019-07-19.
17 Chintagunta P, Hanssens D M, Hauser J R. Editorial—marketing science and big data[J]. Marketing Science,2016, 35(3): 341-342. DOI:10.1287/mksc.2016.0996
18 Davenport T, Guha A, Grewal D, et al. How artificial intelligence will change the future of marketing[J]. Journal of the Academy of Marketing Science,2020, 48(1): 24-42. DOI:10.1007/s11747-019-00696-0
19 Dew R, Ansari A, Toubia O. Letting logos speak: Leveraging multiview representation learning for data-driven branding and logo design[J]. Marketing Science,2022, 41(2): 401-425. DOI:10.1287/mksc.2021.1326
20 Diehl K, Zauberman G, Barasch A. How taking photos increases enjoyment of experiences[J]. Journal of Personality and Social Psychology,2016, 111(2): 119-140. DOI:10.1037/pspa0000055
21 Dzyabura D, El Kihal S, Hauser J R, et al. Leveraging the power of images in managing product return rates[EB/OL]. http://dx.doi.org/10.2139/ssrn.3209307, 2019-09-04.
22 Dzyabura D, Peres R. Visual elicitation of brand perception[J]. Journal of Marketing,2021, 85(4): 44-66. DOI:10.1177/0022242921996661
23 Gabel S, Timoshenko A. Product choice with large assortments: A scalable deep-learning model[J]. Management Science,2022, 68(3): 1808-1827. DOI:10.1287/mnsc.2021.3969
24 Gaudin S. At Stitch Fix, data scientists and A. I. become personal stylist[EB/OL]. https://www.cmo.com.au/article/599435/stitch-fix-data-scientists-become-personal-stylists, 2016-05-07.
25 Goodfellow I, Bengio Y, Courville A. Deep learning[M]. Cambridge, MA: MIT Press, 2016.
26 Goodfellow I J, Pouget-Abadie J, Mirza M, et al. Generative adversarial networks[J]. Communications of the ACM,2020, 63(11): 139-144. DOI:10.1145/3422622
27 Guan Y, Tan Y, Wei Q, et al. Information or distortion? The effect of customer generated images on product rating dynamics[EB/OL]. http://dx.doi.org/10.2139/ssrn.3633590, 2020-06-23.
28 Hall P, Gill N. An introduction to machine learning interpretability[M]. 2nd ed. Newton, MA: O’Reilly Media, Inc. , 2019.
29 Hartmann J, Heitmann M, Schamp C, et al. The power of brand selfies[J]. Journal of Marketing Research,2021, 58(6): 1159-1177. DOI:10.1177/00222437211037258
30 Hastie T, Tibshirani R, Friedman J. The elements of statistical learning: Data mining, inference, and prediction[M]. 2nd ed. New York: Springer, 2009.
31 Hauser J R. Phenomena, theory, application, data, and methods all have impact[J]. Journal of the Academy of Marketing Science,2017, 45(1): 7-9. DOI:10.1007/s11747-016-0498-1
32 Heater B. Amazon’s new Echo Look has a built-in camera for style selfies[EB/OL]. https://techcrunch.com/2017/04/26/amazons-new-echo-look-has-a-built-in-camera-for-style-selfies, 2017-04-26.
33 Huetter J. Tractable photo-analyzing AI to assess vehicle damage for Mitchell[EB/OL]. https://www.repairerdrivennews.com/2016/10/11/tractable-ceo-says-ai-will-assess-vehicle-damage-for-mitchell-company-specializes-in-ai-photo-analysis, 2016-10-11.
34 Jindal R P, Sarangee K R, Echambadi R, et al. Designed to succeed: Dimensions of product design and their impact on market share[J]. Journal of Marketing,2016, 80(4): 72-89. DOI:10.1509/jm.15.0036
35 Jones A. The full picture: Using image analysis for consumer research[EB/OL]. https://www.brandwatch.com/blog/image-analysis-consumer-research, 2017-06-07.
36 Jordan M I, Mitchell T M. Machine learning: Trends, perspectives, and prospects[J]. Science,2015, 349(6245): 255-260. DOI:10.1126/science.aaa8415
37 Karras T, Laine S, Aila T. A style-based generator architecture for generative adversarial networks[A]. Proceedings of the IEEE/CVF conference on computer vision and pattern recognition[C]. Long Beach: IEEE, 2019.
38 Karras T, Laine S, Aittala M, et al. Analyzing and improving the image quality of StyleGAN[A]. Proceedings of the IEEE/CVF conference on computer vision and pattern recognition[C]. Seattle: IEEE, 2020.
39 Kazemi V, Sullivan J. One millisecond face alignment with an ensemble of regression trees[A]. Proceedings of the IEEE conference on computer vision and pattern recognition[C]. Columbus: IEEE, 2014.
40 Klostermann J, Plumeyer A, Böger D, et al. Extracting brand information from social networks: Integrating image, text, and social tagging data[J]. International Journal of Research in Marketing,2018, 35(4): 538-556. DOI:10.1016/j.ijresmar.2018.08.002
41 Kreuzbauer R, Malter A J. Embodied cognition and new product design: Changing product form to influence brand categorization[J]. Journal of Product Innovation Management,2005, 22(2): 165-176. DOI:10.1111/j.0737-6782.2005.00112.x
42 Krizhevsky A, Sutskever I, Hinton G E. ImageNet classification with deep convolutional neural networks[A]. Proceedings of the 25th international conference on neural information processing systems[C]. Lake Tahoe: Curran Associates Inc. , 2012.
43 Landwehr J R, Labroo A A, Herrmann A. Gut liking for the ordinary: Incorporating design fluency improves automobile sales forecasts[J]. Marketing Science,2011, 30(3): 416-429. DOI:10.1287/mksc.1110.0633
44 LeCun Y, Bengio Y, Hinton G. Deep learning[J]. Nature,2015, 521(7553): 436-444. DOI:10.1038/nature14539
45 LeCun Y, Bottou L, Bengio Y, et al. Gradient-based learning applied to document recognition[J]. Proceedings of the IEEE,1998, 86(11): 2278-2324. DOI:10.1109/5.726791
46 Li H W, Simchi-Levi D, Wu M X, et al. Estimating and exploiting the impact of photo layout: A structural approach[EB/OL]. http://dx.doi.org/10.2139/ssrn.3470877, 2019-10-16.
47 Li Y Y, Xie Y. Is a picture worth a thousand words? An empirical study of image content and social media engagement[J]. Journal of Marketing Research,2020, 57(1): 1-19. DOI:10.1177/0022243719881113
48 Liesa. Introducing image recognition: The future of social listening[EB/OL]. https://www.talkwalker.com/blog/introducing-image-recognition-the-future-of-social-listening, 2016-03-09.
49 Liu L, Dzyabura D, Mizik N. Visual listening in: Extracting brand image portrayed on social media[J]. Marketing Science,2020, 39(4): 669-686. DOI:10.1287/mksc.2020.1226
50 Liu Y, Li K J, Chen H P, et al. The effects of products’ aesthetic design on demand and marketing-mix effectiveness: The role of segment prototypicality and brand consistency[J]. Journal of Marketing,2017, 81(1): 83-102. DOI:10.1509/jm.15.0315
51 Minaee S, Boykov Y, Porikli F, et al. Image segmentation using deep learning: A survey[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2022, 44(7): 3523-3542.
52 Mitchell T M. Machine learning[M]. Maidenhead: McGraw-Hill, 1997.
53 Mnih V, Kavukcuoglu K, Silver D, et al. Human-level control through deep reinforcement learning[J]. Nature,2015, 518(7540): 529-533. DOI:10.1038/nature14236
54 Murphy K P. Machine learning: A probabilistic perspective[M]. Cambridge: MIT Press, 2012.
55 Nissan. AI technology brings excitement to Nissan Japan[EB/OL]. https://global.nissanstories.com/en/releases/nissan-ai-technology, 2022-01-21.
56 Peng L, Cui G, Chung Y, et al. The faces of success: Beauty and ugliness premiums in e-commerce platforms[J]. Journal of Marketing,2020, 84(4): 67-85. DOI:10.1177/0022242920914861
57 Pieters R, Wedel M, Batra R. The stopping power of advertising: Measures and effects of visual complexity[J]. Journal of Marketing,2010, 74(5): 48-60. DOI:10.1509/jmkg.74.5.048
58 Raghubir P, Greenleaf E A. Ratios in proportion: What should the shape of the package be?[J]. Journal of Marketing,2006, 70(2): 95-107. DOI:10.1509/jmkg.70.2.095
59 Reppel A E, Szmigin I, Gruber T. The iPod phenomenon: Identifying a market leaders’ secrets through qualitative marketing research[J]. Journal of Product & Brand Management,2006, 15(4): 239-249.
60 Rizkallah, J. The big (unstructured) data problem[EB/OL]. https://www.forbes.com/sites/forbestechcouncil/2017/06/05/the-big-unstructured-data-problem/?sh=da78e05493a3, 2017-06-05.
61 Rumelhart D E, Hinton G E, Williams R J. Learning representations by back-propagating errors[J]. Nature,1986, 323(6088): 533-536. DOI:10.1038/323533a0
62 Shin D, He S, Lee G M, et al. Enhancing social media analysis with visual data analytics: A deep learning approach[J]. MIS Quarterly,2020, 44(4): 1459-1492. DOI:10.25300/MISQ/2020/14870
63 Shorten C, Khoshgoftaar T M. A survey on image data augmentation for deep learning[J]. Journal of Big Data,2019, 6(1): 60. DOI:10.1186/s40537-019-0197-0
64 Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition[A]. 3rd international conference on learning representations[C]. San Diego, 2015.
65 Sutton R S, Barto A G. Reinforcement learning: An introduction[M]. Cambridge, Massachusetts: MIT Press, 1998.
66 Tkachenko Y, Jedidi K. What personal information can a consumer facial image reveal? Implications for marketing ROI and consumer privacy[EB/OL]. http://dx.doi.org/10.2139/ssrn.3616470, 2020-06-01.
67 Trafton A. In the blink of an eye[EB/OL]. https://news.mit.edu/2014/in-the-blink-of-an-eye-0116, 2014-01-16.
68 Troncoso I, Luo L. Look the part? The role of profile pictures in online labor markets[EB/OL]. http://dx.doi.org/10.2139/ssrn.3709554, 2020-11-25.
69 Urban G, Timoshenko A, Dhillon P, et al. Is deep learning a game changer for marketing analytics?[J]. MIT Sloan Management Review,2020, 61(2): 71-76.
70 Verganti R, Vendraminelli L, Iansiti M. Innovation and design in the age of artificial intelligence[J]. Journal of Product Innovation Management,2020, 37(3): 212-227. DOI:10.1111/jpim.12523
71 Vogel D R, Dickson G W, Lehman J A. Persuasion and the role of visual presentation support: The UM/3M study[R]. Working Paper No. MISRC-WP-86-11, 1986.
72 Wedel M, Kannan P K. Marketing analytics for data-rich environments[J]. Journal of Marketing,2016, 80(6): 97-121. DOI:10.1509/jm.15.0413
73 Wedel M, Pieters R. The buffer effect: The role of color when advertising exposures are brief and blurred[J]. Marketing Science,2015, 34(1): 134-143. DOI:10.1287/mksc.2014.0882
74 Xia F H, Chatterjee R, May J H. Using conditional restricted Boltzmann machines to model complex consumer shopping patterns[J]. Marketing Science,2019, 38(4): 711-727. DOI:10.1287/mksc.2019.1162
75 Xiao L, Ding M. Just the faces: Exploring the effects of facial features in print advertising[J]. Marketing Science,2014, 33(3): 338-352. DOI:10.1287/mksc.2013.0837
76 Xiao L, Kim H J, Ding M. An introduction to audio and visual research and applications in marketing[J]. Review of Marketing Research,2013, 10: 213-253.
77 Xu J, Ding M. Transparent model of unabridged data (TMUD)[EB/OL]. https://doi.org/10.48550/arXiv.2106.07558, 2021-05-23.
78 Zhang J, Wedel M, Pieters R. Sales effects of attention to feature advertisements: A Bayesian mediation analysis[J]. Journal of Marketing Research,2009, 46(5): 669-681. DOI:10.1509/jmkr.46.5.669
79 Zhang M X, Luo L. Can consumer-posted photos serve as a leading indicator of restaurant survival? Evidence from Yelp[J]. Management Science, 2022, doi: 10.1287/MNSC.2022.4359.
80 Zhang S Y, Lee D, Singh P V, et al. What makes a good image? Airbnb demand analytics leveraging interpretable image features[J]. Management Science, 2021a, doi: 10.1287/mnsc.2021.4175.
81 Zhang S Y, Mehta N, Singh P V, et al. Frontiers: Can an artificial intelligence algorithm mitigate racial economic inequality? An analysis in the context of Airbnb[J]. Marketing Science,2021b, 40(5): 813-820.