Search

In this paper, we present a multimodal dataset for affective computing research acquired in a human-computer interaction (HCI) setting. An experimental mobile and interactive scenario was designed and implemented based on a gamified generic paradigm for the induction of dialog-based HCI relevant emotional and cognitive load states. It consists of six experimental sequences, inducing Interest, Overload, Normal, Easy, Underload, and Frustration. Each sequence is followed by subjective feedbacks to validate the induction, a respiration baseline to level off the physiological reactions, and a summary of results. Further, prior to the experiment, three questionnaires related to emotion regulation (ERQ), emotional control (TEIQue-SF), and personality traits (TIPI) were collected from each subject to evaluate the stability of the induction paradigm. Based on this HCI scenario, the University of Ulm Multimodal Affective Corpus (uulmMAC), consisting of two homogenous samples of 60 participants and 100 recording sessions was generated. We recorded 16 sensor modalities including 4 &times, video, 3 &times, audio, and 7 &times, biophysiological, depth, and pose streams. Further, additional labels and annotations were also collected. After recording, all data were post-processed and checked for technical and signal quality, resulting in the final uulmMAC dataset of 57 subjects and 95 recording sessions. The evaluation of the reported subjective feedbacks shows significant differences between the sequences, well consistent with the induced states, and the analysis of the questionnaires shows stable results. In summary, our uulmMAC database is a valuable contribution for the field of affective computing and multimodal data analysis: Acquired in a mobile interactive scenario close to real HCI, it consists of a large number of subjects and allows transtemporal investigations. Validated via subjective feedbacks and checked for quality issues, it can be used for affective computing and machine learning applications.

Background: The working conditions at universities and hospitals are reported to be stressful. Several national and international studies have investigated occupational stress in hospitals. However, scientific studies at colleges and universities addressing psycho-social stress factors and their potential consequences are scarce. In this context, the consequences and correlations of the factor of work���family conflict, in particular, are currently uninvestigated. The aim of our study was to assess data on psychosocial stress in the context of the compatibility of work and family. Methods: Data were gathered through a cross-sectional-study, N = 844 (55% female, 41% male), on university staff (42.3% scientists, 14.3% physicians, 19.4% employees in administration, and 19.3% employees in service). Participants filled out questionnaires to provide their personal data and details of their work and private life conditions. For this purpose, we used the Work���Family and Family���Work Conflict Scales, Effort-Reward Inventory and Overcommitment Scale (ERI, OC), Patient Health Questionnaire (PHQ-4), short-form Maslach Burnout Inventory (MBI), and questions on their subjective health. Statistical analyses were performed using SPSS 22. Results: We found high levels of stress parameters in the total sample: extra work (83%), fixed-term work contracts (53%), overcommitment (OC, 26%), Effort-Reward Imbalance (18%, ERI Ratio > cut-off 0.715), work���family conflict (WFC, 35%), and family���work conflict (FWC, 39%). As hypothesized, we found significant correlations of both WFC and FWC with psychosocial work strain (ERI Ratio) as well as overcommitment (OC). Mental and somatic health parameters also had a significant positive correlation with WFC and FWC. Using a regression analysis (N = 844), we identified WFC as a predictor of burnout, while emotional exhaustion, extra work, and overcommitment could be identified as predictors of WFC and FWC. Discussion: The results of our study point toward deficits in the compatibility of work life and private life in the work fields of science, colleges, and universities. Furthermore, we found indicators that work���family conflicts (interrole conflicts) have an impact on mental and somatic health. These work���family conflicts should be targets for preventions and interventions with the aim of improving the work-life balance and mental and somatic wellbeing of employees., publishedVersion