Hey CLIP, can you capture semantics in brand names?

Subtitle
Evaluation of CLIP’s multi-modal space using brand names, logos and brand descriptions
Publication date
2023
Document type
Master thesis
Author
Advisor
Cassani, Giovanni
Referee
Garrido Alhama, Raquel
Granting institution
Tilburg University
Exam date
2023
Organisational unit
Tilburg University
Abstract
Congruence between brand names and other flagships of a brand are important tools to effectively communicate to, and set the right expectations in consumers. In this study, we explore congruence of brand features as a problem that could potentially be evaluated by computational models trained on cross-modal stimuli such as CLIP. As a by-product we explore to what extent these models capture sound symbolic associations in our stimuli set, and analyse the relationship between (sub-) lexical information and shape dimensions in brand logos. Instead of human participants, we employ CLIP- and BERT-based computational models to make decisions about similarity between a multitude of brand names, brand descriptions and brand logos. We show that our results support proposals of statistical co-occurrence as an underlying mechanism of sound symbolic associations, and argue that CLIP can be carefully used as a tool for maneuvering through naming and logo design decisions.
Description
Zweitveröffentlichung (Erscheinungsdatum: 2025)
Die Erstveröffentlichung ist unter der URL https://tilburguniversity.on.worldcat.org/oclc/1456539509 einsehbar.
DOI der Zweitveröffentlichung: 10.24405/17327
Version
Published version
Access right on openHSU
Open access