Visual Listening In: Extracting Brand Image Portrayed on Social Media
Liu Liu, Daria Dzyabura, and Natalie Mizik, 2020, 20-113
Images are close to surpassing text as the medium of choice for online conversations, and many of the photos that consumers share on social media are brand-related. These consumer-created brand images convey rich information about the consumption experience, attitudes, and feelings of the user, and offer a new avenue to study brand associations and consumers’ brand perceptions.
Here, Liu Liu, Daria Dzyabura, and Natalie Mizik propose an approach that enables managers to monitor how their brands are portrayed on image-based social platforms. Using a deep-learning framework, they develop a multi-label convolutional neural network model, BrandImageNet, to predict the presence of perceptual brand attributes in the images that consumers post online. They apply their model to brand-related images posted on social media, and compute a brand-portrayal metric based on model predictions for 56 national brands in the apparel and beverages categories.
They find that consumer-created brand images contain valuable brand information. In particular, they find that the brand-portrayal metrics derived from consumer-created brand images are strongly correlated with survey-based metrics of consumer brand perceptions.
Put into Practice
Many firms have started to look into consumer-created visual content on social media, but most efforts are focused on brand logo detection and tracking brand mentions. This study shows that deeper insights can be extracted from consumer-created images.
Firms can use the BrandImageNet model to automatically monitor in real time their brand portrayal, better understand consumer brand perceptions and attitudes toward theirs and competitors’ brands, and assess the effectiveness of their positioning strategies.
- Corporate: FREE
- Academic: FREE
- Subscribers: FREE
- Public: $18.00
3 WAYS to GET CONNECTED
Employees of MSI Member Companies enjoy the benefits of complete online access to content, member conferences and networking with the MSI community.
Qualified academics benefit from a relationship with MSI through access to msi.org, conferences and research opportunities.
The public is invited to enjoy partial access to msi.org content, a free e-newsletter, selected reports and more.