2023
|
Georgiadis, Kostas; Kalaganis, Fotis P; Oikonomou, Vangelis P; Nikolopoulos, Spiros; Laskaris, Nikos A; Kompatsiaris, Ioannis Harneshing the Potential of EEG in Neuromarketing with Deep Learning and Riemannian Geometry Conference International Conference on Brain Informatics, Springer 2023. @conference{georgiadis2023harneshing,
title = {Harneshing the Potential of EEG in Neuromarketing with Deep Learning and Riemannian Geometry},
author = {Kostas Georgiadis and Fotis P Kalaganis and Vangelis P Oikonomou and Spiros Nikolopoulos and Nikos A Laskaris and Ioannis Kompatsiaris},
url = {https://link.springer.com/chapter/10.1007/978-3-031-43075-6_3},
year = {2023},
date = {2023-09-13},
urldate = {2023-01-01},
booktitle = {International Conference on Brain Informatics},
pages = {21–32},
organization = {Springer},
abstract = {Neuromarketing exploits neuroimaging techniques to study consumers’ responses to various marketing aspects, with the goal of gaining a more thorough understanding of the decision-making process. The neuroimaging technology encountered the most in neuromarketing studies is Electroencephalography (EEG), mainly due to its non-invasiveness, low cost and portability. Opposed to typical neuromarketing practices, which rely on signal-power related features, we introduce an efficient decoding scheme that is based on the principles of Riemannian Geometry and realized by means of a suitable deep learning (DL) architecture (i.e., SPDNet). We take advantage of a recently released, multi-subject, neuromarketing dataset to train SPDNet under the close-to-real-life scenario of product selection from a supermarket leaflet and compare its performance against standard tools in EEG-based neuromarketing. The sample covariance is used as an estimator of the ‘quasi-instantaneous’, brain activation pattern and derived from the multichannel signal recorded while the subject is gazing at a given product. Pattern derivation is followed by proper re-alignment to reduce covariate shift (inter-subject variability) before SPDNet casts its binary decision (i.e., “Buy”-“NoBuy”). The proposed decoder is characterized by sufficient generalizability to derive valid predictions upon unseen brain signals. Overall, our experimental results provide clear evidence about the superiority of the DL-decoder relatively to both conventional neuromarketing and alternative Riemannian Geometry-based approaches, and further demonstrate how neuromarketing can benefit from recent advances in data-centric machine learning and the availability of relevant experimental datasets.},
keywords = {DSI-24, Neuromarketing},
pubstate = {published},
tppubtype = {conference}
}
Neuromarketing exploits neuroimaging techniques to study consumers’ responses to various marketing aspects, with the goal of gaining a more thorough understanding of the decision-making process. The neuroimaging technology encountered the most in neuromarketing studies is Electroencephalography (EEG), mainly due to its non-invasiveness, low cost and portability. Opposed to typical neuromarketing practices, which rely on signal-power related features, we introduce an efficient decoding scheme that is based on the principles of Riemannian Geometry and realized by means of a suitable deep learning (DL) architecture (i.e., SPDNet). We take advantage of a recently released, multi-subject, neuromarketing dataset to train SPDNet under the close-to-real-life scenario of product selection from a supermarket leaflet and compare its performance against standard tools in EEG-based neuromarketing. The sample covariance is used as an estimator of the ‘quasi-instantaneous’, brain activation pattern and derived from the multichannel signal recorded while the subject is gazing at a given product. Pattern derivation is followed by proper re-alignment to reduce covariate shift (inter-subject variability) before SPDNet casts its binary decision (i.e., “Buy”-“NoBuy”). The proposed decoder is characterized by sufficient generalizability to derive valid predictions upon unseen brain signals. Overall, our experimental results provide clear evidence about the superiority of the DL-decoder relatively to both conventional neuromarketing and alternative Riemannian Geometry-based approaches, and further demonstrate how neuromarketing can benefit from recent advances in data-centric machine learning and the availability of relevant experimental datasets. |
Georgiadis, Kostas; Kalaganis, Fotis P; Riskos, Kyriakos; Matta, Eleftheria; Oikonomou, Vangelis P; Yfantidou, Ioanna; Chantziaras, Dimitris; Pantouvakis, Kyriakos; Nikolopoulos, Spiros; Laskaris, Nikos A; others, NeuMa-the absolute Neuromarketing dataset en route to an holistic understanding of consumer behaviour Journal Article In: Scientific Data, vol. 10, no. 1, pp. 508, 2023. @article{georgiadis2023neuma,
title = {NeuMa-the absolute Neuromarketing dataset en route to an holistic understanding of consumer behaviour},
author = {Kostas Georgiadis and Fotis P Kalaganis and Kyriakos Riskos and Eleftheria Matta and Vangelis P Oikonomou and Ioanna Yfantidou and Dimitris Chantziaras and Kyriakos Pantouvakis and Spiros Nikolopoulos and Nikos A Laskaris and others},
doi = {https://doi.org/10.1038/s41597-023-02392-9},
year = {2023},
date = {2023-08-03},
urldate = {2023-01-01},
journal = {Scientific Data},
volume = {10},
number = {1},
pages = {508},
publisher = {Nature Publishing Group UK London},
abstract = {Neuromarketing is a continuously evolving field that utilises neuroimaging technologies to explore consumers’ behavioural responses to specific marketing-related stimulation, and furthermore introduces novel marketing tools that could complement the traditional ones like questionnaires. In this context, the present paper introduces a multimodal Neuromarketing dataset that encompasses the data from 42 individuals who participated in an advertising brochure-browsing scenario. In more detail, participants were exposed to a series of supermarket brochures (containing various products) and instructed to select the products they intended to buy. The data collected for each individual executing this protocol included: (i) encephalographic (EEG) recordings, (ii) eye tracking (ET) recordings, (iii) questionnaire responses (demographic, profiling and product related questions), and (iv) computer mouse data. NeuMa dataset has both dynamic and multimodal nature and, due to the narrow availability of open relevant datasets, provides new and unique opportunities for researchers in the field to attempt a more holistic approach to neuromarketing.},
keywords = {DSI-24, Neuromarketing},
pubstate = {published},
tppubtype = {article}
}
Neuromarketing is a continuously evolving field that utilises neuroimaging technologies to explore consumers’ behavioural responses to specific marketing-related stimulation, and furthermore introduces novel marketing tools that could complement the traditional ones like questionnaires. In this context, the present paper introduces a multimodal Neuromarketing dataset that encompasses the data from 42 individuals who participated in an advertising brochure-browsing scenario. In more detail, participants were exposed to a series of supermarket brochures (containing various products) and instructed to select the products they intended to buy. The data collected for each individual executing this protocol included: (i) encephalographic (EEG) recordings, (ii) eye tracking (ET) recordings, (iii) questionnaire responses (demographic, profiling and product related questions), and (iv) computer mouse data. NeuMa dataset has both dynamic and multimodal nature and, due to the narrow availability of open relevant datasets, provides new and unique opportunities for researchers in the field to attempt a more holistic approach to neuromarketing. |
2022
|
Chanpornpakdi, Ingon; Noda, Motoi; Tanaka, Toshihisa; Harpaz, Yuval; Geva, Amir B Clustering of advertising images using electroencephalogram Conference Proceedings of 2022 APSIPA Annual Summit and Conference, 2022. @conference{chanpornpakdiclustering,
title = {Clustering of advertising images using electroencephalogram},
author = {Ingon Chanpornpakdi and Motoi Noda and Toshihisa Tanaka and Yuval Harpaz and Amir B Geva},
url = {http://www.apsipa.org/proceedings/2022/APSIPA%202022/TuAM1-8/1570840214.pdf},
year = {2022},
date = {2022-11-07},
booktitle = {Proceedings of 2022 APSIPA Annual Summit and Conference},
abstract = {Packaging and advertisements of brands affect customers’ decision-making on purchasing products and could lead to business loss. Hence, neuromarketing, the application of neuroscience in the marketing field, is introduced aiming to understand customers’ cognitive functions toward advertisements or products. Our study focused on identifying how the brain respond to different types of advertising image of the same brand were perceived using electroencephalogram (EEG). We performed an experiment using 33 different Coca-Cola advertising images in RSVP (rapid serial visual presentation) task on 23 participants. A seven channels EEG dry headset was used to record the visual event-related potential (ERP), specifically, the positive peak found at 300 to 700 ms after image onset; P300, to compare the perception response. We applied k-means and hierarchical clustering to the obtained EEG data, and achieved the best clustering for three clusters, yielding different P300 amplitudes and latencies. The typical Coca-Cola ads, red color with Cola-cola text on the ads, induced a faster and larger response, implying better perception than the unconventional or black color ads. We conclude that ERP clustering may be a useful tool for neuromarketing. However, the relationship between the EEG-based cluster and the image-based cluster should be further investigated to confirm the suggestion.},
keywords = {DSI-7, Neuromarketing},
pubstate = {published},
tppubtype = {conference}
}
Packaging and advertisements of brands affect customers’ decision-making on purchasing products and could lead to business loss. Hence, neuromarketing, the application of neuroscience in the marketing field, is introduced aiming to understand customers’ cognitive functions toward advertisements or products. Our study focused on identifying how the brain respond to different types of advertising image of the same brand were perceived using electroencephalogram (EEG). We performed an experiment using 33 different Coca-Cola advertising images in RSVP (rapid serial visual presentation) task on 23 participants. A seven channels EEG dry headset was used to record the visual event-related potential (ERP), specifically, the positive peak found at 300 to 700 ms after image onset; P300, to compare the perception response. We applied k-means and hierarchical clustering to the obtained EEG data, and achieved the best clustering for three clusters, yielding different P300 amplitudes and latencies. The typical Coca-Cola ads, red color with Cola-cola text on the ads, induced a faster and larger response, implying better perception than the unconventional or black color ads. We conclude that ERP clustering may be a useful tool for neuromarketing. However, the relationship between the EEG-based cluster and the image-based cluster should be further investigated to confirm the suggestion. |
2018
|
Camp, Marieke Van; Boeck, Muriel De; Verwulgen, Stijn; Bruyne, Guido De EEG Technology for UX Evaluation: A Multisensory Perspective Conference International Conference on Applied Human Factors and Ergonomics, vol. 775, Springer Advances in Intelligent Systems and Computing , 2018. @conference{van2018eeg,
title = {EEG Technology for UX Evaluation: A Multisensory Perspective},
author = {Marieke Van Camp and Muriel De Boeck and Stijn Verwulgen and Guido De Bruyne},
url = {https://link.springer.com/chapter/10.1007/978-3-319-94866-9_34},
year = {2018},
date = {2018-06-28},
booktitle = {International Conference on Applied Human Factors and Ergonomics},
volume = {775},
pages = {337--343},
publisher = {Advances in Intelligent Systems and Computing },
organization = {Springer},
abstract = {Along with a growing interest in experience-driven design, interest in measuring user experience has progressively increased. This study explores the use of EEG for empirical UX evaluation. A first experimental test was conducted to measure and understand the effect of sensory stimuli on the user experience. A first experimental test was carried out with eight participants. A series of videos, eliciting positive and negative emotional responses, were presented to the participants. Subsequently, auditory stimuli were introduced and the effect on the user experience was evaluated using EEG measurements techniques and analysis software. After the tests the participants were questioned to verify whether the subjective results matched the objective measurements.},
keywords = {Cognitive-Algorithm, DSI-24, Neuromarketing},
pubstate = {published},
tppubtype = {conference}
}
Along with a growing interest in experience-driven design, interest in measuring user experience has progressively increased. This study explores the use of EEG for empirical UX evaluation. A first experimental test was conducted to measure and understand the effect of sensory stimuli on the user experience. A first experimental test was carried out with eight participants. A series of videos, eliciting positive and negative emotional responses, were presented to the participants. Subsequently, auditory stimuli were introduced and the effect on the user experience was evaluated using EEG measurements techniques and analysis software. After the tests the participants were questioned to verify whether the subjective results matched the objective measurements. |
2015
|
Kang, Dayoon; Kim, Jinsoo; Jang, Dong-Pyo; Cho, Yang Seok; Kim, Sung-Phil Investigation of engagement of viewers in movie trailers using electroencephalography Journal Article In: Brain-Computer Interfaces, vol. 2, no. 4, pp. 193–201, 2015. @article{kang2015investigation,
title = {Investigation of engagement of viewers in movie trailers using electroencephalography},
author = {Dayoon Kang and Jinsoo Kim and Dong-Pyo Jang and Yang Seok Cho and Sung-Phil Kim},
doi = {https://doi.org/10.1080/2326263X.2015.1103591},
year = {2015},
date = {2015-11-10},
journal = {Brain-Computer Interfaces},
volume = {2},
number = {4},
pages = {193--201},
publisher = {Taylor & Francis},
abstract = {Brain-computer interfaces (BCIs) have been focused on providing direct communications to the disabled. Recently, BCI researchers have expanded BCI applications to non-medical uses and categorized them as active BCI, reactive BCI, and passive BCI. Neurocinematics, a new application of reactive BCIs, aims to understand viewers’ cognitive and affective responses to movies from neural activity, providing more objective information than traditional subjective self-reports. However, studies on analytical indices for neurocinematics have verified their indices by comparisons with self-reports. To overcome this contradictory issue, we proposed using an independent psychophysical index to evaluate a neural engagement index (NEI). We made use of the secondary task reaction time (STRT), which measures participants’ engagement in a primary task by their reaction time to a secondary task; here, responding to a tactile stimulus was the secondary task and watching a movie trailer was the primary task. NEI was developed as changes in the difference between frontal beta and alpha activity of EEG. We evaluated movie trailers using NEI, STRT, and self-reports and found a significant correlation between STRT and NEI across trailers but no correlation between any of the self-report results and STRT or NEI. Our results suggest that NEI developed for neurocinematics may conform well with more objective psychophysical assessments but not with subjective self-reports.},
keywords = {BCI, DSI-24, Neuromarketing},
pubstate = {published},
tppubtype = {article}
}
Brain-computer interfaces (BCIs) have been focused on providing direct communications to the disabled. Recently, BCI researchers have expanded BCI applications to non-medical uses and categorized them as active BCI, reactive BCI, and passive BCI. Neurocinematics, a new application of reactive BCIs, aims to understand viewers’ cognitive and affective responses to movies from neural activity, providing more objective information than traditional subjective self-reports. However, studies on analytical indices for neurocinematics have verified their indices by comparisons with self-reports. To overcome this contradictory issue, we proposed using an independent psychophysical index to evaluate a neural engagement index (NEI). We made use of the secondary task reaction time (STRT), which measures participants’ engagement in a primary task by their reaction time to a secondary task; here, responding to a tactile stimulus was the secondary task and watching a movie trailer was the primary task. NEI was developed as changes in the difference between frontal beta and alpha activity of EEG. We evaluated movie trailers using NEI, STRT, and self-reports and found a significant correlation between STRT and NEI across trailers but no correlation between any of the self-report results and STRT or NEI. Our results suggest that NEI developed for neurocinematics may conform well with more objective psychophysical assessments but not with subjective self-reports. |
