Computing and Information Systems - Research Publications
Permanent URI for this collection
Search Results
1 - 10 of 18
-
ItemNo Preview AvailableEmotion trajectories in smartphone use: Towards recognizing emotion regulation in-the-wild(ACADEMIC PRESS LTD- ELSEVIER SCIENCE LTD, 2022-10)
-
Item"Instant Happiness": Smartphones as tools for everyday emotion regulation(Elsevier, 2023-02-01)Smartphone use has become an indispensable aspect of daily life for billions of people. Increasingly, researchers are examining the impact of smartphone use upon psychological well-being. However, little research has investigated how people deliberately use their smartphones to shape affective states; in other words, how smartphones are used as tools to support everyday emotion regulation. In this paper, we report a study that uses quantitative (experience sampling) and qualitative (semi-structured interview) methods to examine when and how people use smartphones to regulate emotions in everyday life, and the associated psychological consequences. Participants report spending a significant amount of time using their smartphones for emotion regulation, in particular to cope with unpleasant feelings such as boredom and stress. They report that smartphone-mediated emotion regulation is effective for attaining desired affective states. However, the perceived emotional benefits of smartphone emotion regulation do not emerge in lagged analyses predicting changes in momentary mood across a few hours, suggesting that emotional benefits may be transient or may reflect self-report biases. Participants discuss their perceptions of smartphone-supported emotion regulation in relation to smartphone addiction. This study provides evidence on how people use their smartphones for emotion regulation, and contributes to better understanding the complex relationship between smartphone use and emotional wellbeing.
-
ItemBenchmarking commercial emotion detection systems using realistic distortions of facial image datasets(Springer Verlag, 2020-01-01)Currently, there are several widely used commercial cloud-based services that attempt to recognize an individual’s emotions based on their facial expressions. Most research into facial emotion recognition has used high-resolution, front-oriented, full-face images. However, when images are collected in naturalistic settings (e.g., using smartphone’s frontal camera), these images are likely to be far from ideal due to camera positioning, lighting conditions, and camera shake. The impact these conditions have on the accuracy of commercial emotion recognition services has not been studied in full detail. To fill this gap, we selected five prominent commercial emotion recognition systems—Amazon Rekognition, Baidu Research, Face++, Microsoft Azure, and Affectiva—and evaluated their performance via two experiments. In Experiment 1, we compared the systems’ accuracy at classifying images drawn from three standardized facial expression databases. In Experiment 2, we first identified several common scenarios (e.g., partially visible face) that can lead to poor-quality pictures during smartphone use, and manipulated the same set of images used in Experiment 1 to simulate these scenarios. We used the manipulated images to again compare the systems’ classification performance, finding that the systems varied in how well they handled manipulated images that simulate realistic image distortion. Based on our findings, we offer recommendations for developers and researchers who would like to use commercial facial emotion recognition technologies in their applications.
-
ItemBehavioral and Physiological Signals-Based Deep Multimodal Approach for Mobile Emotion Recognition(IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC, 2023-04-01)With the rapid development of mobile and wearable devices, it is increasingly possible to access users' affective data in a more unobtrusive manner. On this basis, researchers have proposed various systems to recognize user's emotional states. However, most of these studies rely on traditional machine learning techniques and a limited number of signals, leading to systems that either do not generalize well or would frequently lack sufficient information for emotion detection in realistic scenarios. In this paper, we propose a novel attention-based LSTM system that uses a combination of sensors from a smartphone (front camera, microphone, touch panel) and a wristband (photoplethysmography, electrodermal activity, and infrared thermopile sensor) to accurately determine user's emotional states. We evaluated the proposed system by conducting a user study with 45 participants. Using collected behavioral (facial expression, speech, keystroke) and physiological (blood volume, electrodermal activity, skin temperature) affective responses induced by visual stimuli, our system was able to achieve an average accuracy of 89.2% for binary positive and negative emotion classification under leave-one-participant-out cross-validation. Furthermore, we investigated the effectiveness of different combinations of data signals to cover different scenarios of signal availability.
-
ItemNo Preview Available
-
ItemDesign Considerations for Supporting Mindfulness in Virtual Reality(FRONTIERS MEDIA SA, 2022-01-21)Mindfulness practice involves bringing one’s attention to the present moment and noticing events as they unfold with a non-judgmental attitude of acceptance. Although mindfulness has been shown to reduce stress and improve mental health, it can be challenging to learn mindfulness techniques. Recent years have seen an interest in using virtual reality (VR) to help people learn mindfulness by immersing users in virtual settings that support an external focus of attention and reduce everyday environmental distraction. However, the literature currently lacks an understanding of how VR should be designed to support mindfulness. In this paper we describe the iterative design and evaluation of Place, a VR app that supports mindfulness practice by situating the user in a virtual forest environment. We present findings from our design process in which prospective users trialled Place and provided feedback on the design in focus groups. Our findings draw attention to factors that influenced the user experience and acceptance of VR for mindfulness, and we describe how the design was altered to address these factors. We end by discussing key design choices that designers should consider when creating VR for mindfulness. Our contributions include insight into the importance of following an iterative design process when creating a VR mindfulness app, and a framework that can be used to inform the design of future VR apps for mindfulness practice.
-
ItemModerated online social therapy for depression relapse prevention in young people: pilot study of a "next generation' online intervention(WILEY, 2018-08)AIM: Implementation of targeted e-mental health interventions offers a promising solution to reducing the burden of disease associated with youth depression. A single-group pilot study was conducted to evaluate the acceptability, feasibility, usability and safety of a novel, moderated online social therapy intervention (entitled Rebound) for depression relapse prevention in young people. METHODS: Participants were 42 young people (15-25 years) (50% men; mean age = 18.5 years) in partial or full remission. Participants had access to the Rebound platform for at least 12 weeks, including the social networking, peer and clinical moderator and therapy components. RESULTS: Follow-up data were available for 39 (92.9%) participants. There was high system usage, with 3034 user logins (mean = 72.2 per user) and 2146 posts (mean = 51.1). Almost 70% of users had ≥10 logins over the 12 weeks, with 78.5% logging in over at least 2 months of the pilot. A total of 32 (84%) participants rated the intervention as helpful. There was significant improvement between the number of participants in full remission at baseline (n = 5; none of whom relapsed) relative to n = 19 at 12-week follow-up (P < 0.001). Six (14.3%) participants relapsed to full threshold symptoms at 12 weeks. There was a significant improvement to interviewer-rated depression scores (Montgomery-Asberg Depression Rating Scale (MADRS); P = 0.014, d = 0.45) and a trend for improved strength use (P = 0.088, d = 0.29). The single-group design and 12-week treatment phase preclude a full understanding of the clinical benefits of the Rebound intervention. CONCLUSIONS: The Rebound intervention was shown to be acceptable, feasible, highly usable and safe in young people with major depression.
-
ItemHow psychoactive drugs shape human culture: A multi-disciplinary perspective(PERGAMON-ELSEVIER SCIENCE LTD, 2016-09)Psychoactive drug use occurs in essentially all human societies. A range of disciplines contribute to our understanding of the influence of drugs upon the human world. For example pharmacology and neuroscience analyse biological responses to drugs, sociology examines social influences upon people's decisions to use drugs, and anthropology provides rich accounts of use across a variety of cultural contexts. This article reviews work from multiple disciplines to illustrate that drugs influence aspects of culture from social life to religion, politics to trade, while acting as enablers of cultural change throughout human history. This broad view is valuable at a time when the influence not only of traditional drugs but a growing armoury of novel drugs is felt and debated.
-
ItemModerated Online Social Therapy: A Model for Reducing Stress in Carers of Young People Diagnosed with Mental Health Disorders(FRONTIERS MEDIA SA, 2017-04-03)Family members caring for a young person diagnosed with the onset of mental health problems face heightened stress, depression, and social isolation. Despite evidence for the effectiveness of family based interventions, sustaining access to specialist family interventions is a major challenge. The availability of the Internet provides possibilities to expand and sustain access to evidence-based psychoeducation and personal support for family members. In this paper we describe the therapeutic model and the components of our purpose-built moderated online social therapy (MOST) program for families. We outline the background to its development, beginning with our face-to-face EPISODE II family intervention, which informed our selection of therapeutic content, and the integration of recent developments in positive psychology. Our online interventions for carers integrate online therapy, online social networking, peer and expert support, and online social problem solving which has been designed to reduce stress in carers. The initial version of our application entitled Meridian was shown to be safe, acceptable, and feasible in a feasibility study of carers of youth diagnosed with depression and anxiety. There was a significant reduction in self-reported levels of stress in caregivers and change in stress was significantly correlated with use of the system. We have subsequently launched a cluster RCT for caregivers with a relative diagnosed with first-episode psychosis. Our intervention has the potential to improve access to effective specialist support for families facing the onset of serious mental health problems in their young relative.
-
ItemArtificial Intelligence-Assisted Online Social Therapy for Youth Mental Health(FRONTIERS MEDIA SA, 2017-06-02)Introduction: Benefits from mental health early interventions may not be sustained over time, and longer-term intervention programs may be required to maintain early clinical gains. However, due to the high intensity of face-to-face early intervention treatments, this may not be feasible. Adjunctive internet-based interventions specifically designed for youth may provide a cost-effective and engaging alternative to prevent loss of intervention benefits. However, until now online interventions have relied on human moderators to deliver therapeutic content. More sophisticated models responsive to user data are critical to inform tailored online therapy. Thus, integration of user experience with a sophisticated and cutting-edge technology to deliver content is necessary to redefine online interventions in youth mental health. This paper discusses the development of the moderated online social therapy (MOST) web application, which provides an interactive social media-based platform for recovery in mental health. We provide an overview of the system's main features and discus our current work regarding the incorporation of advanced computational and artificial intelligence methods to enhance user engagement and improve the discovery and delivery of therapy content. Methods: Our case study is the ongoing Horyzons site (5-year randomized controlled trial for youth recovering from early psychosis), which is powered by MOST. We outline the motivation underlying the project and the web application's foundational features and interface. We discuss system innovations, including the incorporation of pertinent usage patterns as well as identifying certain limitations of the system. This leads to our current motivations and focus on using computational and artificial intelligence methods to enhance user engagement, and to further improve the system with novel mechanisms for the delivery of therapy content to users. In particular, we cover our usage of natural language analysis and chatbot technologies as strategies to tailor interventions and scale up the system. Conclusions: To date, the innovative MOST system has demonstrated viability in a series of clinical research trials. Given the data-driven opportunities afforded by the software system, observed usage patterns, and the aim to deploy it on a greater scale, an important next step in its evolution is the incorporation of advanced and automated content delivery mechanisms.