Classification of emotions based on electrodermal activity and transfer learning - a pilot study

This paper describes the development, execution and results of an experiment assessing emotions with electrodermal response measurements and machine learning. With ten participants, the study was carried out by eliciting emotions through film clips. The data was gathered with the Sudologger 3 and processed with continuous wavelet transformation. A machine learning algorithm was used to classify the data with the use of transfer learning and random forest classification. The results showed that the experiment lays a foundation for further exploration in the field. The addition of augmented data strengthened the classification and proved that more data would benefit the machine learning algorithm. The pilot study brought to light several areas to help with the expansion of the study for larger scale assessment of emotions with electrodermal response measurements and machine learning for the benefit of fields like psychology.

Acoustic Measures of Emotion in School-Age Children Who Stutter: Findings From a Single Subject

Purpose The purpose of this study was to encourage and justify the examination of acoustic measures of emotion (mean fundamental frequency [F0], F0 range, jitter, and shimmer) from school-age children who stutter (CWS) in a novel procedure combining psychophysiological measures of stress with acoustic analysis. Method One school-age CWS (aged 11;9 [years;months]) completed a cognitively stressful speech-language task and a control speech-language task. Vocal acoustic samples were collected during the stressful task and the control task. These samples were later analyzed for F0, F0 range, jitter, and shimmer. Physiological measures of emotional arousal, including electrodermal response frequency and electrodermal response amplitude, were also recorded prior to, during, and after each condition for manipulation check purposes. Physiological measures of emotion regulation, indexed by mean heart rate variability, were also collected prior to and after each condition for manipulation check purposes. Results Findings from the psychophysiological measures suggest that the CWS experienced increased stress during the stress-inducing task. Acoustic measures indicate that the CWS reduced rather than increased her mean F0, F0 range, jitter, and shimmer only for high vowels /i u/ during the control task compared to stressful task. Conclusions Overall, these pilot findings support the need for further study of vocal acoustic and psychophysiological measures of emotion from CWS as well as children who do not stutter.

Electrodermal Response Ratios: Scoring Against the Stronger of Two Comparison Questions in Search of an Optimal Minimum Threshold

Previously, Krapohl (2020) evaluated the Bigger-Is-Better Rule (BIBR) on the polygraph electrodermal channel to assess whether there was a best minimum ratio between response sizes for assigning a score. Performance peaked at a minimum ratio between 10% and 20%. The ratios had been calculated by comparing the electrodermal responses for each relevant question against those of the immediately preceding comparison question. The analysis did not consider whether the same optimal ratio would be found if the relevant question electrodermal responses are compared to those of the stronger of two adjacent comparison questions. To investigate we analyzed responses from an independent sample of 255 laboratory cases. The data from those cases found the highest correlation between scores and ground truth occurred when the minimum difference between two electrodermal responses was 30%.

Relationship between emotional reactivity to visual stimuli and basic personality traits

Two studies with the same goal, but different instruments, investigated the correlation between basic personality traits and electrodermal reactivity to aversive visual stimuli. Study 1 focused on the Five Factor Model traits, while in Study 2, we investigated the HEXACO model, and an additional trait, Disintegration. In Study 1, emotional reactivity was expressed using Polyscore, a composite polygraph measure in which electrodermal response (EDR) had the largest weight, and it was measured with respect to stimuli with positive, neutral, and negative valences. In Study 2, we employed several measures of EDR to stimuli with negative valence. In both experiments, Conscientiousness correlated positively with EDR to aversive stimuli. Additionally, in Study 2, there was a negative correlation between Disintegration and EDR to aversive stimuli. Other traits were not related to EDR to aversive stimuli, and, in Study 1, we found no relationship between personality traits and reactivity to stimuli with positive or neutral valence.

Event-Related Electrodermal Response to Stress: Results From a Realistic Driving Simulator Scenario

Objective: The study goal was to test whether induced stress during driving could be measured at the event level through electrodermal activity responses. Background: Stress measured in simulation scenarios could thus far show an overall change in the stress state, but not be well attributed to acute stressful events. Driving simulator scenarios that induce stress measurable at the event level in realistic situations are thus warranted. As such, acute stress reactions can be measured in the context of changing situational factors such as fatigue, substance abuse, or medical conditions. Method: Twelve healthy female participants drove the same route numerous times in a driving simulator, each time with different random traffic events occurring throughout. During one of the scenarios, unknown to the participants, 10 programmed neutral traffic events occurred, whereas in another scenario, at the same location, 10 stressful events occurred. Results: Electrodermal response results showed both effects of scenario type and of events. The amplitude of the electrodermal response was significantly correlated with subjective stress experience. Conclusion: We conclude that our developed ecological driving simulation scenarios can be used to induce and measure stress at the event level. Application: The developed simulator scenarios enable us to measure stress reactions in driving situations at the time when the event actually happens. With these scenarios, we can measure how situational factors, such as fatigue or substance abuse, can change immediate stress reactions when driving. We can further measure more specifically how induced driving stress can affect physical and mental functioning afterward.