| By: |
Daria Dzyabura (New Economic School, Moscow, Russia);
Renana Peres (Hebrew University of Jerusalem, Israel) |
| Abstract: |
Understanding how consumers perceive brands is at the core of effective brand
management. In this paper, we present the Brand Visual Elicitation Platform
(B-VEP), an electronic tool we developed that allows consumers to create
online collages of images that represent how they view a brand. Respondents
select images for the collage from a searchable repository of tens of
thousands of images. We implement an unsupervised machine-learning approach to
analyze the collages and elicit the associations they describe. We demonstrate
the platform’s operation by collecting large, unaided, directly elicited
data for 303 large US brands from 1,851 respondents. Using machine learning
and image-processing approaches to extract from these images systematic
content associations, we obtain a rich set of associations for each brand. We
combine the collage-making task with well-established brand-perception
measures such as brand personality and brand equity, and suggest various
applications for brand management. |
| Keywords: |
Image processing, machine learning, branding, brand associations, brand collages, Latent Dirichlet Allocation |
| Date: |
2019–12 |
| URL: |
http://d.repec.org/n?u=RePEc:abo:neswpt:w0260&r=all |