Under pressure

Abstract

Recognizing when computer users are stressed can help reduce their frustration and prevent a large variety of negative health conditions associated with chronic stress. However, measuring stress non-invasively and continuously at work remains an open challenge. This work explores the possibility of using a pressure-sensitive keyboard and a capacitive mouse to discriminate between stressful and relaxed conditions in a laboratory study. During a 30-minute session, 24 participants performed several computerized tasks consisting of expressive writing, text transcription, and mouse clicking. During the stressful conditions, the large majority of the participants showed significantly increased typing pressure (>79% of the participants) and more contact with the surface of the mouse (75% of the participants). We discuss the potential implications of this work and provide recommendations for future work.

On the early diagnosis of Alzheimer's Disease from multimodal signals: A survey

“…Regarding CSF measurements, they are intrusive, costly and slow methods of analysis [300]. Furthermore, all of these current tests, are "usually administered in a physician's office or a rehabilitation facility, causing inconvenience for the patient, using valuable healthcare resources, making frequent monitoring unrealistic" [296] and therefore, precluding an early diagnosis.…”

Towards detecting programmers’ stress on the basis of keystroke dynamics

“…Another approach to stress detection has been presented in [15] where the possibility of using a pressure-sensitive keyboard and a capacitive mouse to discriminate between stressful and relaxed conditions was investigated. It turned out that under stress the typing pressure increased and more contact with the surface of mouse was observed.…”

“…visual [5], depth [6], audio [7], textual [8], physiological [9], standard input devices [10]- [15] or multi-modal input [16]. Not all of them seem practical in any situation, e.g.…”

Ratings are Overrated!

“…Although subjective reporting (first-or third-person) comes with several limitations, such as self-deception and memory-biases, it offers the most direct and popular approach to the annotation of subjective constructs. Thus, quantitative reports via questionnaires provide unique properties for evaluating the capacity of interactive systems (Bardram et al, 2013;Chen et al, 2014) and for constructing computational models of reported user states (Hernandez et al, 2014).…”