• Publications
  • Influence
Affect Detection: An Interdisciplinary Review of Models, Methods, and Their Applications
TLDR
This survey explicitly explores the multidisciplinary foundation that underlies all AC applications by describing how AC researchers have incorporated psychological theories of emotion and how these theories affect research questions, methods, results, and their interpretations.
Positive Computing: Technology for Wellbeing and Human Potential
On the eve of Google's IPO in 2004, Larry Page and Sergey Brin vowed not to be evil. Today, a growing number of technologists would go further, trying to ensure that their work actively improves
Automated Detection of Engagement Using Video-Based Estimation of Facial Expressions and Heart Rate
TLDR
This work explored how computer vision techniques can be used to detect engagement while students completed a structured writing activity similar to activities encountered in educational settings, and obtained an AUC of .758 for concurrent annotations and AUC = .733 for retrospective annotations.
Detecting Naturalistic Expressions of Nonbasic Affect Using Physiological Signals
TLDR
This study develops and evaluates user-independent and user-dependent physiology-based detectors of nonbasic affective states that were trained and validated on naturalistic data collected during interactions between 27 students and AutoTutor, an intelligent tutoring system with conversational dialogues.
Designing for Motivation, Engagement and Wellbeing in Digital Experience
TLDR
A model is introduced that provides a framework grounded in psychological research that can allow HCI researchers and practitioners to form actionable insights with respect to how technology designs support or undermine basic psychological needs, thereby increasing motivation and engagement, and ultimately, improving user wellbeing.
Using galvanic skin response for cognitive load measurement in arithmetic and reading tasks
TLDR
Assessment of GSR data captured from two different experiments, one including text reading tasks and the other using arithmetic tasks, each imposing multiple cognitive load levels shows the strong significance of the explored features, especially the spectral ones, in cognitive workload measurement in the two studied experiments.
Evaluation of Unsupervised Emotion Models to Textual Affect Recognition
TLDR
Experiments show that a categorical model using NMF results in better performances for SemEval and fairy tales, whereas a dimensional model performs better with ISEAR.
Prevalence of PTSD and common mental disorders amongst ambulance personnel: a systematic review and meta-analysis
TLDR
Ambulance personnel worldwide have a prevalence of PTSD considerably higher than rates seen in the general population, although there is some evidence that rates of PTSD may have decreased over recent decades.
...
...