AUTHOR=Barquero-Pérez Óscar , Cámara-Vázquez Miguel Angel , Vadillo-Valderrama Alba , Goya-Esteban Rebeca 

TITLE=Autonomic Nervous System and Recall Modeling in Audiovisual Emotion-Mediated Advertising Using Partial Least Squares-Path Modeling

JOURNAL=Frontiers in Psychology

VOLUME=Volume 11 - 2020

YEAR=2020

URL=https://www.frontiersin.org/journals/psychology/articles/10.3389/fpsyg.2020.576771

DOI=10.3389/fpsyg.2020.576771

ISSN=1664-1078

ABSTRACT=Interest in improving advertisement impact on potential consumers has increased a lot recently.
One well-known strategy is to use emotion-based advertisements to create an emotional link with
consumers and enhance the memorization process. In recent years, the use of Neuromarketing
techniques allowed us to obtain more objective information on this process. However, the role of
the autonomic nervous systems in the memorization process using emotional advertisement still
needs further investigation. In this work, we propose to use two physiological signals, namely,
the electrocardiogram (heart rate variability, HRV) and the electrodermal activity (EDA) to obtain
objective indices of the ANS. We measured these signals in 43 subjects during the observation
of 6 different spots, each one conveying a different emotion (rational, disgust, anger, surprise
and sadness). After observing the spots, the subjects were asked to answer a questionnaire to
measure the spontaneous and induced recall. We propose to use a statistical data-driven model
based on Partial Least Squares - Path Modeling (PSL-PM), which allows to incorporate context
knowledge by defining a relational graph of unobservable variables (latent variables, LV), which
in turn are estimated by the measured variable. We defined four LVs, namely, sympathetic and
vagal, which are connected with the third LV, ANS, and finally, the fourth LV being a measure of
the recall estimated from the questionnaire. The model is then fitted to the data. Results showed
that the vagal activity (described by HRV indices) is the most important to describe the ANS
activity, and they are inversely related, except for the clearly rational spot (without emotion). The
model is able to explain, at most, 12% of the recall score of the subjects. This approach will allow
to easily incorporate more physiological measurements, and provide with an easy to interpret
model of the ANS response to emotional advertisements.