Visual Elicitation of Brand Perception

Daria Dzyabura and Renana Peres ()
Additional contact information
Renana Peres: Hebrew University of Jerusalem, Israel

No w0260, Working Papers from New Economic School (NES)

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 (search for similar items in EconPapers)
Pages: 49 pages
Date: 2019-12
New Economics Papers: this item is included in nep-big, nep-cmp, nep-ipr, nep-mkt, nep-ore and nep-pay
References: Add references at CitEc
Citations: View citations in EconPapers (2)

Downloads: (external link)
https://www.nes.ru/files/Preprints-resh/WP260.pdf (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:abo:neswpt:w0260

Access Statistics for this paper

More papers in Working Papers from New Economic School (NES) Contact information at EDIRC.
Bibliographic data for series maintained by Vladimir Ivanyukhin ( this e-mail address is bad, please contact ).