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

Abstract

Interest in improving advertisement impact on potential consumers has increased recently. One well-known strategy is to use emotion-based advertisement. In this approach, an emotional link with consumers is created, aiming to enhance the memorization process. In recent years, Neuromarketing techniques have allowed us to obtain more objective information on this process. However, the role of the autonomic nervous system (ANS) in the memorization process using emotional advertisement still needs further research. In this work, we propose the use of two physiological signals, namely, an electrocardiogram (heart rate variability, HRV) and electrodermal activity (EDA), to obtain indices assessing the ANS. We measured these signals in 43 subjects during the observation of six different spots, each conveying a different emotion (rational, disgust, anger, surprise, and sadness). After observing the spots, subjects were asked to answer a questionnaire to measure the spontaneous and induced recall. We propose the use of a statistical data-driven model based on Partial Least Squares-Path Modeling (PSL-PM), which allows us to incorporate contextual knowledge by defining a relational graph of unobservable variables (latent variables, LV), which are, in turn, estimated by measured variables (indices of the ANS). We defined four LVs, namely, sympathetic, vagal, ANS, and recall. Sympathetic and vagal are connected to the ANS, the latter being a measure of recall, estimated from a questionnaire. The model is then fitted to the data. Results showed that vagal activity (described by HRV indices) is the most critical factor to describe ANS activity; they are inversely related except for the spot, which is mainly rational. The model captured a moderate-to-high variability of ANS behavior, ranging from 38% up to 64% of the explained variance of the ANS. However, it can explain at most 11% of the recall score of the subjects. The proposed approach allows for the easy inclusion of more physiological measurements and provides an easy-to-interpret model of the ANS response to emotional advertisement.

Heart Rate Variability in Healthy Subjects During Monitored, Short-Term Stress Followed by 24-hour Cardiac Monitoring

“…Our results showed that DFA α 1 as a non-linear index of HRV did not distinguish the different affective image regimes under ultra-short recordings. Although previous work showed that there can be differences in HRV measures when comparing neutral and arousing sessions ( Valenza et al, 2012 ) or watching positive and negative videos ( Barquero-Pérez et al, 2020 ; Ghiasi et al, 2020 ), our findings are consistent with other works that showed the linear HRV metric RMSSD did not distinguish between positive and negative emotions using IAPS ( Schippers et al, 2018 ), and non-linear HRV metric DFA α 1 did not distinguish different emotionally arousing settings ( Marín-Morales et al, 2021 ). We hypothesize that because pure regime participants knew to expect images of the same type, there may not have been a sufficient change in emotional context to create significant variation in their heart rate.…”

“…These changes in the successive heartbeats are an integral component of physiological research and are becoming more standardized in the field ( Laborde et al, 2017 ; Berntson et al, 1997 ; Malik, 1996 ) to provide diagnostic information in certain medical conditions ( Yeh et al, 2009 ; Gronwald et al, 2019 ) and insights into the parasympathetic nervous system ( Malik, 1996 ). Past studies have shown that shifts in HRV can be induced by a variety of different types of affective stimuli such as watching positive and negative videos ( Barquero-Pérez et al, 2020 ; Ghiasi et al, 2020 ), the Cold Pressor Stress Test ( Ghiasi et al, 2018 ; Ghiasi et al, 2020 ), and imagining scenarios which evoke an emotional response ( McCraty et al, 1995 ). Using these different affective induction techniques, researchers have proposed various models to measure changes in the autonomic nervous system in reaction to an affective stimulus.…”

Biomedical Technology in Studying Consumers’ Subconscious Behavior

“…Physiological techniques, for example, ET can measure visual attention such as fixation, pupil dilation, eye movements [19]. GSR and ECG can measure emotional arousal (e.g., high/low) and heart rate [20]. EMG can only measure the unconscious responses of the emotional valence (e.g., pleasure/displeasure, sadness/excitement, and forth) [21].…”

“…The GSR is used to gauge the sweating level and ECG to measure the heart rate/heartbeat [77]. ECG can record the heartbeat activations during exposure to marketing stimuli [20]. Heart rate is considered a good scale of emotional valence, wherein the heartbeat's slowing down in the short term is associated with positive and negative emotions.…”

“…GSR is a suitable tool to measure the emotional dimensions (e.g., valence and arousal), sweat glands, and changes in skin conductance [20]. Dawson, et al [79] defined it as a tentative rise in the skin's electrical conductivity, which leads to increased activity in the sweat glands.…”