Smartphones have made sharing images of branded experiences nearly effortless. This research classifies social media brand imagery and studies user response. Aside from packshots (standalone product images), two types of brand-related selfie images appear online: consumer selfies (featuring brands and consumers' faces) and an emerging phenomenon we term brand selfies (invisible consumers holding a branded product). We use convolutional neural networks to identify these archetypes and train language models to infer social media response to more than a quarter million brand-image posts (185 brands on Twitter and Instagram). We find consumer-selfie images receive more sender engagement (i.e., likes and comments), whereas brand selfies result in more brand engagement, expressed by purchase intentions. These results cast doubt on whether conventional social media metrics are appropriate indicators of brand engagement. Results for display ads are consistent with this observation, with higher click-through rates for brand selfies than for consumer selfies. A controlled lab experiment suggests self-reference is driving the differential response to selfie images. Collectively, these results demonstrate how (interpretable) machine learning helps to extract marketing-relevant information from unstructured multimedia content and that selfie images are a matter of perspective in terms of actual brand engagement.

智能手机几乎可以毫不费力地分享品牌体验的图像。这项研究对社交媒体品牌形象进行分类并研究用户反应。除了包装照片（独立的产品图片），网上还会出现两种与品牌相关的自拍图片：消费者自拍（展示品牌和消费者的面孔）和一种我们称之为品牌自拍的新兴现象（持有品牌产品的隐形消费者）。我们使用卷积神经网络来识别这些原型并训练语言模型来推断社交媒体对超过 25 万个品牌形象帖子（Twitter 和 Instagram 上的 185 个品牌）的反应。我们发现消费者自拍图像获得了更多的发送者参与度（即喜欢和评论），而品牌自拍导致更多的品牌参与度，由购买意图表达。这些结果让人怀疑传统的社交媒体指标是否是品牌参与度的适当指标。展示广告的结果与这一观察结果一致，品牌自拍照的点击率高于消费者自拍照。一项受控实验室实验表明，自我参考正在推动对自拍图像的不同反应。总的来说，