Developing a model to identify consumer processing styles from EEG signals during ad viewing
Loading...
Date
2025-02-25
Authors
Καλαϊτζή, Ειρήνη
Journal Title
Journal ISSN
Volume Title
Publisher
Abstract
This thesis aims to investigate the relationship between advertisements and the consumer’s processing style. Using Childer’s et al.1985 Style of Processing Scale we designed an experiment framework that collected the EEG signals of 22 subjects as they viewed three sets of ads; verbal, textual and combined. Participants were categorized into verbalizers, those who prefer verbal processing of information and visualizers, those who prefer visual processing of information. The EEG signals were pre-processed and the five EEG frequency bands were extracted. We employed three classification models for every set of ads, SVM, Decision Tree and kNN. While all three classifiers performed around the same with accuracy between 86-92%, during cross-validation SVM proved to be the more effective model, with kNN and Decision Tree showing sensitivity to data imbalances. Although no significant differences were observed between ad types during classification this framework effectively predicts the consumer’s processing style through advertisements and offers opportunities for more personalized advertisements in the neuromarketing field.
Description
Keywords
Electroencephalography (EEG), Neuromarketing, Style of processing scale, Classification, Machine learning