Discrete classification technique applied to TV advertisements liking recognition system based on low-cost EEG...

Area of Science:

• Neuroscience
• Marketing Research
• Computational Intelligence

Background:

• Investigates brain activity during video advertisement visualization using electroencephalography (EEG).
• Explores the integration of neuroscience principles into marketing strategies.
• Addresses the utility and potential of neuroscience in enhancing marketing accuracy and user acceptance.

Purpose of the Study:

• To recognize brain activity responses during short video advertisement visualization.
• To apply discrete classification techniques for analyzing EEG data in marketing research.
• To evaluate the effectiveness of a novel approach in marketing analytics.

Main Methods:

• Utilized discrete classification techniques on EEG frequency bands.
• Applied C4.5, Artificial Neural Networks (ANN), and a new system based on the Ameva discretization algorithm.
• Generated a dataset and analyzed brain activity scores for TV ads.

Main Results:

• Achieved over 75% accuracy in recognizing brain activity patterns.
• Demonstrated a 30% reduction in algorithm's time consumption compared to other methods.
• Indicated excellent results given the use of low-cost EEG sensors.

Conclusions:

• The proposed technique offers significant improvements in accuracy and efficiency.
• The approach enhances device battery life, enabling extended use in ubiquitous contexts.
• Suggests a promising new direction for neuroscience-informed marketing research.