The SWELL Knowledge Work Dataset for Stress and User Modeling Research

This paper describes the new multimodal SWELL knowledge work (SWELL-KW) dataset for research on stress and user modeling. The dataset was collected in an experiment, in which 25 people performed typical knowledge work (writing reports, making presentations, reading e-mail, searching for information). We manipulated their working conditions with the stressors: email interruptions and time pressure. A varied set of data was recorded: computer logging, facial expression from camera recordings, body postures from a Kinect 3D sensor and heart rate (variability) and skin conductance from body sensors. The dataset made available not only contains raw data, but also preprocessed data and extracted features. The participants' subjective experience on task load, mental effort, emotion and perceived stress was assessed with validated questionnaires as a ground truth. The resulting dataset on working behavior and affect is a valuable contribution to several research fields, such as work psychology, user modeling and context aware systems.

[1]  A. Bakker,et al.  DAILY RECOVERY FROM WORK-RELATED EFFORT DURING NONWORK TIME , 2009 .

[2]  F. Mokhayeri,et al.  Mental stress detection using physiological signals based on soft computing techniques , 2011, 2011 18th Iranian Conference of Biomedical Engineering (ICBME).

[3]  Pietro Cipresso,et al.  Electro-Physiological Data Fusion for Stress Detection , 2012, Annual Review of Cybertherapy and Telemedicine.

[4]  Ashish Kapoor,et al.  Multimodal affect recognition in learning environments , 2005, ACM Multimedia.

[5]  Andrew Sears,et al.  Automated stress detection using keystroke and linguistic features: An exploratory study , 2009, Int. J. Hum. Comput. Stud..

[6]  Wessel Kraaij,et al.  Real-time task recognition based on knowledge workers' computer activities , 2012, ECCE.

[7]  S. Hart,et al.  Development of NASA-TLX (Task Load Index): Results of Empirical and Theoretical Research , 1988 .

[8]  M. Bradley,et al.  Measuring emotion: the Self-Assessment Manikin and the Semantic Differential. , 1994, Journal of behavior therapy and experimental psychiatry.

[9]  J. Ruff,et al.  Information Overload: Causes, Symptoms and Solutions , 2002 .

[10]  P. Duttweiler,et al.  The Internal Control Index: A Newly Developed Measure of Locus of Control , 1984 .

[11]  Dimitris N. Metaxas,et al.  Optical computer recognition of facial expressions associated with stress induced by performance demands. , 2005, Aviation, space, and environmental medicine.

[12]  D. Zapf.  Stress-oriented Analysis of Computerized Office Work , 1993 .

[13]  Wessel Kraaij,et al.  Unobtrusive Monitoring of Knowledge Workers for Stress Self-regulation , 2013, UMAP.

[14]  Wessel Kraaij,et al.  Collecting a dataset of information behaviour in context , 2014, CARR '14.

[15]  Gloria Mark,et al.  The cost of interrupted work: more speed and stress , 2008, CHI.

[16]  A. Bakker,et al.  The job demands-resources model of burnout. , 2001, The Journal of applied psychology.

[17]  Lando L. J. Koppes,et al.  Nationale Enquête Arbeidsomstandigheden 2011. Methodologie en globale resultaten , 2010 .

[18]  Mohammad Soleymani,et al.  A Multimodal Database for Affect Recognition and Implicit Tagging , 2012, IEEE Transactions on Affective Computing.

[19]  Steven Dhondt,et al.  Handleiding NOVA-WEBA : een vragenlijst om arbeidsorganisatorische knelpunten op te sporen : hernieuwde versie , 2000 .

[20]  Saskia Koldijk.  Automatic recognition of context and stress to support knowledge workers , 2012, ECCE.