Selecting Cover Images for Restaurant Reviews: AI vs. Wisdom of the Crowd

IF 4.8 3区管理学 Q1 MANAGEMENT

M&som-Manufacturing & Service Operations Management Pub Date : 2023-09-07 DOI:10.1287/msom.2021.0531

Warut Khern-am-nuai, Hyunji So, Maxime C. Cohen, Yossiri Adulyasak

{"title":"Selecting Cover Images for Restaurant Reviews: AI vs. Wisdom of the Crowd","authors":"Warut Khern-am-nuai, Hyunji So, Maxime C. Cohen, Yossiri Adulyasak","doi":"10.1287/msom.2021.0531","DOIUrl":null,"url":null,"abstract":"Problem definition: Restaurant review platforms, such as Yelp and TripAdvisor, routinely receive large numbers of photos in their review submissions. These photos provide significant value for users who seek to compare restaurants. In this context, the choice of cover images (i.e., representative photos of the restaurants) can greatly influence the level of user engagement on the platform. Unfortunately, selecting these images can be time consuming and often requires human intervention. At the same time, it is challenging to develop a systematic approach to assess the effectiveness of the selected images. Methodology/results: In this paper, we collaborate with a large review platform in Asia to investigate this problem. We discuss two image selection approaches, namely crowd-based and artificial intelligence (AI)-based systems. The AI-based system we use learns complex latent image features, which are further enhanced by transfer learning to overcome the scarcity of labeled data. We collaborate with the platform to deploy our AI-based system through a randomized field experiment to carefully compare both systems. We find that the AI-based system outperforms the crowd-based counterpart and boosts user engagement by 12.43%–16.05% on average. We then conduct empirical analyses on observational data to identify the underlying mechanisms that drive the superior performance of the AI-based system. Managerial implications: Finally, we infer from our findings that the AI-based system outperforms the crowd-based system for restaurants with (i) a longer tenure on the platform, (ii) a limited number of user-generated photos, (iii) a lower star rating, and (iv) lower user engagement during the crowd-based system. Funding: The authors acknowledge financial support from the Social Sciences and Humanities Research Council [Grant 430-2020-00106]. Supplemental Material: The online appendix is available at https://doi.org/10.1287/msom.2021.0531 .","PeriodicalId":49901,"journal":{"name":"M&som-Manufacturing & Service Operations Management","volume":"10 1","pages":"0"},"PeriodicalIF":4.8000,"publicationDate":"2023-09-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"M&som-Manufacturing & Service Operations Management","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1287/msom.2021.0531","RegionNum":3,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"MANAGEMENT","Score":null,"Total":0}

引用次数: 0

Abstract

Problem definition: Restaurant review platforms, such as Yelp and TripAdvisor, routinely receive large numbers of photos in their review submissions. These photos provide significant value for users who seek to compare restaurants. In this context, the choice of cover images (i.e., representative photos of the restaurants) can greatly influence the level of user engagement on the platform. Unfortunately, selecting these images can be time consuming and often requires human intervention. At the same time, it is challenging to develop a systematic approach to assess the effectiveness of the selected images. Methodology/results: In this paper, we collaborate with a large review platform in Asia to investigate this problem. We discuss two image selection approaches, namely crowd-based and artificial intelligence (AI)-based systems. The AI-based system we use learns complex latent image features, which are further enhanced by transfer learning to overcome the scarcity of labeled data. We collaborate with the platform to deploy our AI-based system through a randomized field experiment to carefully compare both systems. We find that the AI-based system outperforms the crowd-based counterpart and boosts user engagement by 12.43%–16.05% on average. We then conduct empirical analyses on observational data to identify the underlying mechanisms that drive the superior performance of the AI-based system. Managerial implications: Finally, we infer from our findings that the AI-based system outperforms the crowd-based system for restaurants with (i) a longer tenure on the platform, (ii) a limited number of user-generated photos, (iii) a lower star rating, and (iv) lower user engagement during the crowd-based system. Funding: The authors acknowledge financial support from the Social Sciences and Humanities Research Council [Grant 430-2020-00106]. Supplemental Material: The online appendix is available at https://doi.org/10.1287/msom.2021.0531 .

查看原文本刊更多论文

为餐厅评论选择封面图片:人工智能vs.人群智慧

问题定义:餐厅评论平台，如Yelp和TripAdvisor，通常会在他们提交的评论中收到大量的照片。这些照片为那些想要比较餐馆的用户提供了重要的价值。在这种情况下，封面图片(即餐厅的代表性照片)的选择可以极大地影响平台上的用户参与度。不幸的是，选择这些图像非常耗时，而且通常需要人工干预。同时，开发一种系统的方法来评估所选图像的有效性是具有挑战性的。方法/结果:在本文中，我们与亚洲的一个大型审查平台合作来调查这个问题。我们讨论了两种图像选择方法，即基于人群和基于人工智能(AI)的系统。我们使用的基于人工智能的系统学习复杂的潜在图像特征，并通过迁移学习进一步增强这些特征，以克服标记数据的稀缺性。我们与平台合作，通过随机现场实验部署基于人工智能的系统，仔细比较两种系统。我们发现，基于人工智能的系统优于基于人群的系统，平均提高了12.43%-16.05%的用户参与度。然后，我们对观测数据进行实证分析，以确定驱动基于人工智能的系统优越性能的潜在机制。管理意义:最后，我们从我们的研究结果中推断，对于(i)在平台上的使用时间较长，(ii)用户生成的照片数量有限，(iii)星级较低，以及(iv)在基于人群的系统中用户参与度较低的餐厅，基于人工智能的系统优于基于人群的系统。资助:作者感谢社会科学与人文科学研究委员会的财政支持[Grant 430-2020-00106]。补充材料:在线附录可在https://doi.org/10.1287/msom.2021.0531上获得。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

M&som-Manufacturing & Service Operations Management 管理科学-运筹学与管理科学

CiteScore

9.30

自引率

12.70%

发文量

184

审稿时长

12 months

期刊介绍： M&SOM is the INFORMS journal for operations management. The purpose of the journal is to publish high-impact manuscripts that report relevant research on important problems in operations management (OM). The field of OM is the study of the innovative or traditional processes for the design, procurement, production, delivery, and recovery of goods and services. OM research entails the control, planning, design, and improvement of these processes. This research can be prescriptive, descriptive, or predictive; however, the intent of the research is ultimately to develop some form of enduring knowledge that can lead to more efficient or effective processes for the creation and delivery of goods and services. M&SOM encourages a variety of methodological approaches to OM research; papers may be theoretical or empirical, analytical or computational, and may be based on a range of established research disciplines. M&SOM encourages contributions in OM across the full spectrum of decision making: strategic, tactical, and operational. Furthermore, the journal supports research that examines pertinent issues at the interfaces between OM and other functional areas.