This survey describes recent progress in the field of Affective Computing (AC), with a focus on affect detection. Although many AC researchers have traditionally attempted to remain agnostic different emotion theories proposed by psychologists, affective technologies being developed are rife theoretical assumptions that impact their effectiveness. Hence, an informed and integrated examination from multiple areas will need become part computing practice if truly effective real-world systems...

Research in psychology has shown that both motivation and wellbeing are contingent on the satisfaction of certain psychological needs. Yet, despite a long-standing pursuit human-computer interaction (HCI) for design strategies foster sustained engagement, behavior change wellbeing, basic needs to mediate these outcomes rarely taken into account. This is possibly due lack clear model explain context HCI. Herein we introduce such model: Motivation, Engagement Thriving User Experience (METUX)....

We explored how computer vision techniques can be used to detect engagement while students (N = 22) completed a structured writing activity (draft-feedback-review) similar activities encountered in educational settings. Students provided annotations both concurrently during the and retrospectively from videos of their faces after activity. extract three sets features videos, heart rate, Animation Units (from Microsoft Kinect Face Tracker), local binary patterns orthogonal planes (LBP-TOP)....

Abstract Natural language processing (NLP) techniques can be used to make inferences about peoples’ mental states from what they write on Facebook, Twitter and other social media. These then create online pathways direct people health information assistance also generate personalized interventions. Regrettably, the computational methods collect, process utilize writing data, as well evaluations of these techniques, are still dispersed in literature. This paper provides a taxonomy data...

On the eve of Google's IPO in 2004, Larry Page and Sergey Brin vowed not to be evil. Today, a growing number technologists would go further, trying ensure that their work actively improves people's lives. Technology, so pervasive ubiquitous, has capacity increase stress suffering; but it also less-heralded potential improve well-being individuals, society, planet. In this book, Rafael Calvo Dorian Peters investigate what they term positive computing -- design development technology support...

In 2019, the IEEE launched P7000 standards projects intended to address ethical issues in design of autonomous and intelligent systems. This move came amidst a growing public concern over unintended consequences artificial intelligence (AI), compounded by lack an anticipatory process for attending impact within professional practice. However, difficulty moving from principles practice presents significant challenge implementation guidelines. Herein, we describe two complementary frameworks...

Societies are responding to the covid-19 pandemic at breathtaking speed.Many of these ad hoc responses will have long lasting consequences, and we must make sure that today's efforts do not threaten our future wellbeing.The most consequential transformations may come from new health surveillance technologies use machine learning automated decision making parse people's digital footprints, identify those who potentially infected, trace their contacts, enforce social distancing.Some argued...

Background: The current COVID-19 pandemic requires sustainable behaviour change to mitigate the impact of virus. A phenomenon which has arisen in parallel with this is an infodemic – over-abundance information, some accurate and not, making it hard for people find trustworthy reliable guidance make informed decisions. This also been found create distress increase risks mental health disorders, such as depression anxiety. Aim: To propose practical guidelines public risk communication that...

Text often expresses the writer's emotional state or evokes emotions in reader. The nature of phenomena like reading and writing can be interpreted different ways represented with computational models. Affective computing (AC) researchers use a categorical model which text data are associated labels. We introduce new way using normative databases as processing dimensional compare it approaches. approach is evaluated four sets texts reflecting phenomena. An thesaurus bag‐of‐words used to...

Galvanic Skin Response (GSR) has recently attracted researchers' attention as a prospective physiological indicator of cognitive load and emotions. However, it commonly been investigated through single or few measures in one experimental scenario. In this research, aiming to perform comprehensive study, we have assessed GSR data captured from two different experiments, including text reading tasks the other using arithmetic tasks, each imposing multiple levels. We examined temporal spectral...

Unobtrusive, contactless recordings of physiological signals are very important for many health and human-computer interaction applications. Most current systems require sensors which intrusively touch the user's skin. Recent advances in contact-free open door to new types This technology promises measure heart rate (HR) respiration using video only. The effectiveness this technology, its limitations, ways overcoming them deserves particular attention. In paper, we evaluate technique...

Academic writing, individual or collaborative, is an essential skill for today's graduates. Unfortunately, managing writing activities and providing feedback to students very labor intensive academics often opt out of including such learning experiences in their teaching. We describe the architecture a new collaborative support environment used embed engineering courses. iWrite provides tools assignments large cohorts. It outsources storage student content third party cloud-computing vendors...

Signals from peripheral physiology (e.g., ECG, EMG, and GSR) in conjunction with machine learning techniques can be used for the automatic detection of affective states. The affect detector user-independent, where it is expected to generalize novel users, or user-dependent, tailored a specific user. Previous studies have reported some success detecting physiological signals, but much work has focused on induced acted expressions instead contextually constrained spontaneous affect. This study...