ORIGINAL RESEARCH article
Front. Hum. Neurosci.
Sec. Cognitive Neuroscience
Volume 19 - 2025 | doi: 10.3389/fnhum.2025.1542574
This article is part of the Research TopicMachine-Learning/Deep-Learning methods in Neuromarketing and Consumer Neuroscience: Volume IIView all articles
Machine Learning-based viewer preference prediction on social awareness advertisements using EEG
Provisionally accepted
Farhan Ishtiaque1
Mohammad Tohidul Islam Miya1
Fazla Rabbi Mashrur2
Khandoker Mahmudur Rahman1
Ravi Vaidyanathan3Syed Ferhat Anwar4
Farhana Sarker5Noor Azman Ali6Hu Hon Tat6
Khondaker A Mamun1*- 1United International University, Dhaka, Bangladesh
- 2University of Rochester, Rochester, New York, United States
- 3Imperial College London, London, England, United Kingdom
- 4University of Dhaka, Dhaka, Dhaka, Bangladesh
- 5Southeast University, Dhaka, Bangladesh
- 6Putra Business School, Selangor, Malaysia
Select one of your emails
You have multiple emails registered with Frontiers:
Notify me on publication
Please enter your email address:
If you already have an account, please login
You don't have a Frontiers account ? You can register here
One of the most promising applications of neuromarketing is to predict true consumer preference for advertisements to quantify the efficacy of the advertisement. Researchers have already established such neuromarketing systems for static advertisements and ecommerce products. However, more research is required to develop such a system in terms of dynamic advertisements. In this study, we predicted consumer preference for awareness advertisements and explored neural clues that may generate new insights on how we can evaluate advertisements using neuromarketing techniques. Awareness advertisements were used for the first time for such a task since these advertisements are free from any sort of product and brand bias. This ensures that the evaluation of the advertisements was solely comprised of the design and storytelling. For this study, we took 4 awareness topics and selected 2 advertisements from each topic having 2 types of storytelling ('shock' and 'comic'); giving us a total of 8 advertisements. We prepared a custom 14-channel EEG dataset of 20 individual watching these ads along with their preferences and other self-reported measures. We used machine learning to perform binary classification on viewer's preference, where we achieved the highest average accuracy of 93%72% using the leave-one-ad-out method. Further analysis confirms the engagement index (beta/alpha + theta) and (beta/alpha) is an important indicator of self-reported ratings for these advertisements which have been reported previously.
Keywords: neuromarketing, EEG, Consumer preference prediction, machine learning, consumer neuroscience
Received: 10 Dec 2024; Accepted: 06 May 2025.
Copyright: © 2025 Ishtiaque, Miya, Mashrur, Rahman, Vaidyanathan, Anwar, Sarker, Ali, Tat and Mamun. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
* Correspondence: Khondaker A Mamun, United International University, Dhaka, Bangladesh
Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.