Published March 1, 2017
| Version v1
Publication
Discrete classification technique applied to TV advertisements liking recognition system based on low‑cost EEG headsets
Description
Background: In this paper a new approach is applied to the area of marketing
research. The aim of this paper is to recognize how brain activity responds during the
visualization of short video advertisements using discrete classification techniques. By
means of low cost electroencephalography devices (EEG), the activation level of some
brain regions have been studied while the ads are shown to users. We may wonder
about how useful is the use of neuroscience knowledge in marketing, or what could
provide neuroscience to marketing sector, or why this approach can improve the accuracy
and the final user acceptance compared to other works.
Methods: By using discrete techniques over EEG frequency bands of a generated
dataset, C4.5, ANN and the new recognition system based on Ameva, a discretization
algorithm, is applied to obtain the score given by subjects to each TV ad.
Results: The proposed technique allows to reach more than 75 % of accuracy, which
is an excellent result taking into account the typology of EEG sensors used in this work.
Furthermore, the time consumption of the algorithm proposed is reduced up to 30 %
compared to other techniques presented in this paper.
Conclusions: This bring about a battery lifetime improvement on the devices where
the algorithm is running, extending the experience in the ubiquitous context where
the new approach has been tested.
Abstract
Ministerio de Economía y Competitividad HERMES TIN2013-46801-C4-1-rAbstract
Junta de Andalucia Simon TIC-8052Additional details
Identifiers
- URL
- https://idus.us.es/handle/11441/54997
- URN
- urn:oai:idus.us.es:11441/54997