Tanveer, Aimen; Usman, Syed Muhammad; Khalid, Shehzad; Imran, Ali Shariq; Zubair, Muhammad Multimodal Consumer Choice Prediction Using EEG Signals and Eye Tracking Journal Article In: Frontiers in Computational Neuroscience, vol. 18, pp. 1516440, 2025. @article{tanveer18multimodal,
title = {Multimodal Consumer Choice Prediction Using EEG Signals and Eye Tracking},
author = {Aimen Tanveer and Syed Muhammad Usman and Shehzad Khalid and Ali Shariq Imran and Muhammad Zubair},
doi = {https://doi.org/10.3389/fncom.2024.1516440},
year = {2025},
date = {2025-01-07},
journal = {Frontiers in Computational Neuroscience},
volume = {18},
pages = {1516440},
publisher = {Frontiers},
abstract = {Marketing plays a vital role in the success of a business, driving customer engagement, brand recognition, and revenue growth. Neuromarketing adds depth to this by employing insights into consumer behavior through brain activity and emotional responses to create more effective marketing strategies. Electroencephalogram (EEG) has typically been utilized by researchers for neuromarketing, whereas Eye Tracking (ET) has remained unexplored. To address this gap, we propose a novel multimodal approach to predict consumer choices by integrating EEG and ET data. Noise from EEG signals is mitigated using a bandpass filter, Artifact Subspace Reconstruction (ASR), and Fast Orthogonal Regression for Classification and Estimation (FORCE). Class imbalance is handled by employing the Synthetic Minority Over-sampling Technique (SMOTE). Handcrafted features, including statistical and wavelet features, and automated features from Convolutional Neural Network and Long Short-Term Memory (CNN-LSTM), have been extracted and concatenated to generate a feature space representation. For ET data, preprocessing involved interpolation, gaze plots, and SMOTE, followed by feature extraction using LeNet-5 and handcrafted features like fixations and saccades. Multimodal feature space representation was generated by performing feature-level fusion for EEG and ET, which was later fed into a meta-learner-based ensemble classifier with three base classifiers, including Random Forest, Extended Gradient Boosting, and Gradient Boosting, and Random Forest as the meta-classifier, to perform classification between buy vs. not buy. The performance of the proposed approach is evaluated using a variety of performance metrics, including accuracy, precision, recall, and F1 score. Our model demonstrated superior performance compared to competitors by achieving 84.01% accuracy in predicting consumer choices and 83% precision in identifying positive consumer preferences.
},
keywords = {DSI-24, Eye-Tracking, Neuromarketing},
pubstate = {published},
tppubtype = {article}
}
Marketing plays a vital role in the success of a business, driving customer engagement, brand recognition, and revenue growth. Neuromarketing adds depth to this by employing insights into consumer behavior through brain activity and emotional responses to create more effective marketing strategies. Electroencephalogram (EEG) has typically been utilized by researchers for neuromarketing, whereas Eye Tracking (ET) has remained unexplored. To address this gap, we propose a novel multimodal approach to predict consumer choices by integrating EEG and ET data. Noise from EEG signals is mitigated using a bandpass filter, Artifact Subspace Reconstruction (ASR), and Fast Orthogonal Regression for Classification and Estimation (FORCE). Class imbalance is handled by employing the Synthetic Minority Over-sampling Technique (SMOTE). Handcrafted features, including statistical and wavelet features, and automated features from Convolutional Neural Network and Long Short-Term Memory (CNN-LSTM), have been extracted and concatenated to generate a feature space representation. For ET data, preprocessing involved interpolation, gaze plots, and SMOTE, followed by feature extraction using LeNet-5 and handcrafted features like fixations and saccades. Multimodal feature space representation was generated by performing feature-level fusion for EEG and ET, which was later fed into a meta-learner-based ensemble classifier with three base classifiers, including Random Forest, Extended Gradient Boosting, and Gradient Boosting, and Random Forest as the meta-classifier, to perform classification between buy vs. not buy. The performance of the proposed approach is evaluated using a variety of performance metrics, including accuracy, precision, recall, and F1 score. Our model demonstrated superior performance compared to competitors by achieving 84.01% accuracy in predicting consumer choices and 83% precision in identifying positive consumer preferences.
|
Yfantidou, I; Tsourvakas, G; Oikonomou, VP; Kompatsiaris, I Consumer response to different discount sales promotional messages. An eye tracking and EEG experiment Miscellaneous 2024. @misc{yfantidouconsumer,
title = {Consumer response to different discount sales promotional messages. An eye tracking and EEG experiment},
author = {I Yfantidou and G Tsourvakas and VP Oikonomou and I Kompatsiaris},
url = {https://eurasip.org/Proceedings/Eusipco/Eusipco2024/pdfs/0000962.pdf},
year = {2024},
date = {2024-09-04},
abstract = {This article presents a study of consumer behavior during the selection of products from a supermarket’s leaflet. There are many factors that can determine whether a particular product attracts consumers’ attention, such as price, brand, and sales discount. This study is focused on consumers’ preferences among the three most common sales discount types. For the purpose of the study a leaflet that is identical to a real supermarket leaflet was designed, to resemble a real-life experience. Eye tracking and EEG were used to record participants’ gaze and emotions while viewing the leaflet. The behavior of 42 participants was investigated and it was identified how valuable the clarity of the promotional message is. Moreover, EEG helped us analyze basic nonconscious preferences and cognitive processes, such as the effect of memorization, approach-withdrawal and workload in decision making.},
keywords = {DSI-24, Eye-Tracking, Neuromarketing},
pubstate = {published},
tppubtype = {misc}
}
This article presents a study of consumer behavior during the selection of products from a supermarket’s leaflet. There are many factors that can determine whether a particular product attracts consumers’ attention, such as price, brand, and sales discount. This study is focused on consumers’ preferences among the three most common sales discount types. For the purpose of the study a leaflet that is identical to a real supermarket leaflet was designed, to resemble a real-life experience. Eye tracking and EEG were used to record participants’ gaze and emotions while viewing the leaflet. The behavior of 42 participants was investigated and it was identified how valuable the clarity of the promotional message is. Moreover, EEG helped us analyze basic nonconscious preferences and cognitive processes, such as the effect of memorization, approach-withdrawal and workload in decision making. |
Georgiadis, Kostas; Nikolopoulos, Spiros; Kalaganis, Fotis P; Kompatsiaris, Ioannis; Laskaris, Nikos A Assessing video advertising engagement via Nonlinear Intersubject Correlation Analysis of EEG and eye tracking dynamics Miscellaneous 2024. @misc{georgiadisassessing,
title = {Assessing video advertising engagement via Nonlinear Intersubject Correlation Analysis of EEG and eye tracking dynamics},
author = {Kostas Georgiadis and Spiros Nikolopoulos and Fotis P Kalaganis and Ioannis Kompatsiaris and Nikos A Laskaris},
url = {https://eurasip.org/Proceedings/Eusipco/Eusipco2024/pdfs/0000957.pdf},
year = {2024},
date = {2024-09-01},
abstract = {A novel framework for assessing engagement through video commercials is presented. Deviating from the current approaches, here we cast the problem as nonlinear intersubject correlation analysis and pursue the collective (i.e. across-participants) treatment of EEG signals and eye-tracking measurements. Regarding brain dynamics, two well-known descriptors, namely spatial covariance and phase locking value, undergo transcription to their ‘hyperscanning’ equivalents. Regarding eye-related measurements, individual paths and pupillometric measurements are summarized at population level. Using data from a recording paradigm, where each participant independently watched a cartoon video interrupted by a commercial clip, we show that our approach can provide signatures of engagement to the content being delivered and reconstruct the level of appreciation of the potential consumers.},
keywords = {DSI-24, Eye-Tracking, Neuromarketing},
pubstate = {published},
tppubtype = {misc}
}
A novel framework for assessing engagement through video commercials is presented. Deviating from the current approaches, here we cast the problem as nonlinear intersubject correlation analysis and pursue the collective (i.e. across-participants) treatment of EEG signals and eye-tracking measurements. Regarding brain dynamics, two well-known descriptors, namely spatial covariance and phase locking value, undergo transcription to their ‘hyperscanning’ equivalents. Regarding eye-related measurements, individual paths and pupillometric measurements are summarized at population level. Using data from a recording paradigm, where each participant independently watched a cartoon video interrupted by a commercial clip, we show that our approach can provide signatures of engagement to the content being delivered and reconstruct the level of appreciation of the potential consumers. |
Soussou, Walid; Rooksby, Michael; Forty, Charles; Weatherhead, James; Marshall, Sandra EEG and eye-tracking based measures for enhanced training Conference 2012 Annual International Conference of the IEEE Engineering in Medicine and Biology Society, IEEE 2012, ISSN: 1557-170X. @conference{soussou2012eeg,
title = {EEG and eye-tracking based measures for enhanced training},
author = {Walid Soussou and Michael Rooksby and Charles Forty and James Weatherhead and Sandra Marshall},
doi = {10.1109/EMBC.2012.6346256},
issn = {1557-170X},
year = {2012},
date = {2012-11-12},
booktitle = {2012 Annual International Conference of the IEEE Engineering in Medicine and Biology Society},
pages = {1623--1626},
organization = {IEEE},
abstract = {This paper describes a project whose goal was to establish the feasibility of using unobtrusive cognitive assessment methodologies in order to optimize efficiency and expediency of training. QUASAR, EyeTracking, Inc. (ETI), and Safe Passage International (SPI), teamed to demonstrate correlation between EEG and eye-tracking based cognitive workload, performance assessment and subject expertise on XRay screening tasks. Results indicate significant correlation between cognitive workload metrics based on EEG and eye-tracking measurements recorded during a simulated baggage screening task and subject expertise and error rates in that same task. These results suggest that cognitive monitoring could be useful in improving training efficiency by enabling training paradigms that adapts to increasing expertise.},
keywords = {Cognitive-Algorithm, DSI-24, Eye-Tracking},
pubstate = {published},
tppubtype = {conference}
}
This paper describes a project whose goal was to establish the feasibility of using unobtrusive cognitive assessment methodologies in order to optimize efficiency and expediency of training. QUASAR, EyeTracking, Inc. (ETI), and Safe Passage International (SPI), teamed to demonstrate correlation between EEG and eye-tracking based cognitive workload, performance assessment and subject expertise on XRay screening tasks. Results indicate significant correlation between cognitive workload metrics based on EEG and eye-tracking measurements recorded during a simulated baggage screening task and subject expertise and error rates in that same task. These results suggest that cognitive monitoring could be useful in improving training efficiency by enabling training paradigms that adapts to increasing expertise. |
