Dataset Information

Game-Calibrated and User-Tailored Remote Detection of Stress and Boredom in Games.

ABSTRACT: Emotion detection based on computer vision and remote extraction of user signals commonly rely on stimuli where users have a passive role with limited possibilities for interaction or emotional involvement, e.g., images and videos. Predictive models are also trained on a group level, which potentially excludes or dilutes key individualities of users. We present a non-obtrusive, multifactorial, user-tailored emotion detection method based on remotely estimated psychophysiological signals. A neural network learns the emotional profile of a user during the interaction with calibration games, a novel game-based emotion elicitation material designed to induce emotions while accounting for particularities of individuals. We evaluate our method in two experiments ( n = 20 and n = 62 ) with mean classification accuracy of 61.6%, which is statistically significantly better than chance-level classification. Our approach and its evaluation present unique circumstances: our model is trained on one dataset (calibration games) and tested on another (evaluation game), while preserving the natural behavior of subjects and using remote acquisition of signals. Results of this study suggest our method is feasible and an initiative to move away from questionnaires and physical sensors into a non-obtrusive, remote-based solution for detecting emotions in a context involving more naturalistic user behavior and games.

SUBMITTER: Bevilacqua F

PROVIDER: S-EPMC6650833 | biostudies-literature | 2019 Jun

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Game-Calibrated and User-Tailored Remote Detection of Stress and Boredom in Games.

Bevilacqua Fernando F Engström Henrik H Backlund Per P

Sensors (Basel, Switzerland) 20190628 13

Emotion detection based on computer vision and remote extraction of user signals commonly rely on stimuli where users have a passive role with limited possibilities for interaction or emotional involvement, e.g., images and videos. Predictive models are also trained on a group level, which potentially excludes or dilutes key individualities of users. We present a non-obtrusive, multifactorial, user-tailored emotion detection method based on remotely estimated psychophysiological signals. A neura ...[more]

PMID: 31261716

Similar Datasets

Project description:BackgroundHigh quality head-mounted display based virtual reality (HMD-VR) has become widely available, spurring greater development of HMD-VR health games. As a behavior change approach, these applications use HMD-VR and game-based formats to support long-term engagement with therapeutic interventions. While the bulk of research to date has primarily focused on the therapeutic efficacy of particular HMD-VR health games, how developers and researchers incorporate best-practices in game design to achieve engaging experiences remains underexplored. This paper presents the findings of a narrative review exploring the trends and future directions of game design for HMD-VR health games.MethodsWe searched the literature on the intersection between HMD-VR, games, and health in databases including MEDLINE, Embase, CINAHL, PsycINFO, and Compendex. We identified articles describing HMD-VR games designed specifically as health applications from 2015 onwards in English. HMD-VR health games were charted and tabulated according to technology, health context, outcomes, and user engagement in game design.FindingsWe identified 29 HMD-VR health games from 2015 to 2020, with the majority addressing health contexts related to physical exercise, motor rehabilitation, and pain. These games typically involved obstacle-based challenges and extrinsic reward systems to engage clients in interventions related to physical functioning and pain. Less common were games emphasizing narrative experiences and non-physical exercise interventions. However, discourse regarding game design was diverse and often lacked sufficient detail. Game experience was evaluated using primarily ad-hoc questionnaires. User engagement in the development of HMD-VR health games primarily manifested as user studies.ConclusionHMD-VR health games are promising tools for engaging clients in highly immersive experiences designed to address diverse health contexts. However, more in-depth and structured attention to how HMD-VR health games are designed as game experiences is needed. Future development of HMD-VR health games may also benefit from greater involvement of end-users in participatory approaches.

Dataset Information

Game-Calibrated and User-Tailored Remote Detection of Stress and Boredom in Games.

Publications

Game-Calibrated and User-Tailored Remote Detection of Stress and Boredom in Games.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets