Using electrodermal activity to recognize ease of engagement in children during social interactions

Hernández, Javier; Riobo, Ivan; Rozga, Agata; Abowd, Gregory D.; Picard, Rosalind W.

doi:10.1145/2632048.2636065

Cited by 124 publications

(98 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This is of particular interest because the absence of the necessity to provide a rating could be beneficial and positive also for the leader, thus leading to a more symmetrical and cooperative social exchange. Moreover, aside from organizational research, this kind of affective synchrony was explored in previous social and clinical studies: In particular, similar methods have been applied to assess the quality of interaction referred to mother–infant communication (Ham & Tronick, ), couples' affective exchange (Ekman et al, ), and psychotherapy research (Marci, Ham, Moran, & Orr, ), where results revealed that the two parts had significantly more positive social–emotional responses during high autonomic concordance, which has thus become a key marker of social engagement (Hernandez, Riobo, Rozga, Abowd, & Picard, ). This idea can be applied to both the positive engagement related to increased electrodermal responses and the stressful condition of rating assignment (increased HR).…”

Section: Discussionmentioning

confidence: 99%

Who's boss? Physiological measures during performance assessment

et al. 2018

View full text Add to dashboard Cite

Leadership in organizations consists of a complex process, which includes the interpersonal relationship with collaborators. By using a neuroscientific approach, we evaluated the effect of the presence of unidirectional versus reciprocal feedback (provided only by the leader or by both figures), as well as the assignment of a quantitative or just a qualitative assessment. Skin conductance level and response (SCL and SCR), as well as heart rate (HR), have been recorded during a role playing. Results revealed increased emotional engagement (SCL/SCR) during no rating and reciprocal condition, as well as a stressful response (increased HR) during rating and unidirectional condition.

show abstract

Section: Discussionmentioning

confidence: 99%

Who's boss? Physiological measures during performance assessment

et al. 2018

View full text Add to dashboard Cite

show abstract

“…MacHardy et al [47] classified the engagement states of audience members for an online lecture based on information from facial feature detectors; the overall performance was around 72% on this binary classification task. Hernandez et al [29] used wearable electrodermal activity sensors to detect the engagement of children during social interactions with adults. Their goal was to automatically predict which children are difficult to engage with in social interactions.…”

Section: Related Workmentioning

confidence: 99%

Automatically Classifying User Engagement for Dynamic Multi-party Human–Robot Interaction

Foster

Gaschler

Giuliani

2017

Int J of Soc Robotics

View full text Add to dashboard Cite

A robot agent designed to engage in real-world human-robot joint action must be able to understand the social states of the human users it interacts with in order to behave appropriately. In particular, in a dynamic public space, a crucial task for the robot is to determine the needs and intentions of all of the people in the scene, so that it only interacts with people who intend to interact with it. We address the task of estimating the engagement state of customers for a robot bartender based on the data from audiovisual sensors. We begin with an offline experiment using hidden Markov models, confirming that the sensor data contains the information necessary to estimate user state. We then present two strategies for online state estimation: a rule-based classifier based on observed human behaviour in real bars, and a set of supervised classifiers trained on a labelled corpus. These strategies are compared in offline cross-validation, in an online user study, and through validation against a separate test corpus. These studies show that while the trained classifiers are best in a cross-validation setting, the rule-based classifier performs best with novel data; however, all classiThis article integrates and extends the work described in the following conference papers: [17,20,23,24 Bristol Robotics Laboratory, University of the West of England, Bristol, UK fiers also change their estimate too frequently for practical use. To address this issue, we present a final classifier based on Conditional Random Fields: this model has comparable performance on the test data, with increased stability. In summary, though, the rule-based classifier shows competitive performance with the trained classifiers, suggesting that for this task, such a simple model could actually be a preferred option, providing useful online performance while avoiding the implementation and data-scarcity issues involved in using machine learning for this task.

show abstract

“…They are 1024-point low-pass Hamming filtering (cutoff frequency = 3 Hz) [24], [25], Hanning filtering with a 1 second window [15] and exponential smoothing ( α = 0.8) [14]. …”

Section: Resultsmentioning

confidence: 99%

“…Correcting solutions will be more reasonable, if data are short in length or continuity of data is indispensable. There are a few methods previously taken to correct motion artifacts, such as exponential smoothing [14] and other low-pass filters [24], [25], [15]. However, these non-adaptive methods are unable to compensate for artifacts abruptly appearing with much larger intensity than EDA, and the whole time series are filtered indiscriminately, which may distort SC signals without artifacts.…”

Section: Introductionmentioning

confidence: 99%

Wavelet-based motion artifact removal for electrodermal activity

Chen

Jaques

Taylor

et al. 2015

2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)

Self Cite

View full text Add to dashboard Cite

Electrodermal activity (EDA) recording is a powerful, widely used tool for monitoring psychological or physiological arousal. However, analysis of EDA is hampered by its sensitivity to motion artifacts. We propose a method for removing motion artifacts from EDA, measured as skin conductance (SC), using a stationary wavelet transform (SWT). We modeled the wavelet coefficients as a Gaussian mixture distribution corresponding to the underlying skin conductance level (SCL) and skin conductance responses (SCRs). The goodness-of-fit of the model was validated on ambulatory SC data. We evaluated the proposed method in comparison with three previous approaches. Our method achieved a greater reduction of artifacts while retaining motion-artifact-free data.

show abstract

Using electrodermal activity to recognize ease of engagement in children during social interactions

Cited by 124 publications

References 29 publications

Who's boss? Physiological measures during performance assessment

Who's boss? Physiological measures during performance assessment

Automatically Classifying User Engagement for Dynamic Multi-party Human–Robot Interaction

Wavelet-based motion artifact removal for electrodermal activity

Contact Info

Product

Resources

About