Visual Listening In: Extracting Brand Image Portrayed on Social Media

Images are close to surpassing text as the medium of choice for online conversations. They convey rich information about the consumption experience, attitudes, and feelings of the user. In this paper, we propose a “visual listening in” approach (i.e., mining visual content posted by users) to measure how brands are portrayed on social media. We develop BrandImageNet, a multi-label deep convolutional neural network model, to predict the presence of perceptual brand attributes in the images consumers post online. We validate BrandImageNet model performance using human judges and find a high degree of agreement between our model and human evaluations of images. We apply the BrandImageNet model to brand-related images posted on social media to extract brand portrayal based on model predictions for 56 national brands in the apparel and beverages categories. We find a strong link between brand portrayal in consumer-created images and consumer brand perceptions collected through traditional survey tools. Firms can use the BrandImageNet model to automatically monitor their brand portrayal in real time and better understand consumer brand perceptions and attitudes toward their and competitors’ brands.