Search

There is limited infrastructure for providing stress management services to those in need. To address this problem, chatbots are viewed as a scalable solution. However, one limiting factor is having clear definitions and examples of daily stress on which to build models and methods for routing appropriate advice during conversations. We developed a dataset of 6850 SMS-like sentences that can be used to classify input using a scheme of 9 stressor categories derived from: stress management literature, live conversations from a prototype chatbot system, crowdsourcing, and targeted web scraping from an online repository. In addition to releasing this dataset, we show results that are promising for classification purposes. Our contributions include: (i) a categorization of daily stressors, (ii) a dataset of SMS-like sentences, (iii) an analysis of this dataset that demonstrates its potential efficacy, and (iv) a demonstration of its utility for implementation via a simulation of model response times.

We introduce and explore the concept of non-volitional behavior change, a novel category of behavior change interventions, and apply it in the context of promoting healthy behaviors through an automated sit-stand desk. While routine use of sit-stand desks can increase health outcomes, compliance decreases quickly and behavioral nudges tend to be dismissed. To address this issue, we introduce robotic furniture that moves on its own to promote healthy movement. In an in-person preliminary study, we explored users' impressions of an autonomous sit-stand desk prototype that changes position at regular pre-set time intervals while participants complete multiple tasks. While in-the-moment self-reported ratings were similar between the autonomous and manual desks, we observed several bi-modal distributions in user's retrospective comparisons and their qualitative responses. Findings suggest about half were receptive to using an autonomous sit-stand desk, while the remaining preferred to retain some level of control.

This paper focuses on the larger question of when to administer in-car just-in-time stress management interventions. We look at the influence of driving-related stress to find the right time to provide personalized and contextually-aware interventions. We address this challenge with a data driven approach that takes into consideration driving-induced stress, driver (cognitive) availability, and indicators of risky driving behavior such as lane departures and high steering reversal rates. We ran a study with sixteen commuters during morning and evening traffic while applying an in-situ experience sampling. During 45 minutes of driving through various scenarios including city, highway, and neighborhood roads we captured physiological measurements, video of participants and surroundings, and CAN bus driving data. Initial review of the data shows that stress levels changed greatly between 2 and 9 (out of a 0-min to 10-max scale). We conclude with a discussion on how to prepare the data to train supervised algorithms to find the right time to intervene stress while driving.

In this paper, we explore the delivery of fast breathing interventions in a driving context, given the proven effects of high-paced breathing on autonomic arousal. Through in-lab simulator studies, we demonstrate the feasibility of using haptic guidance to increase breathing rate, intensity, and heart rate as well as subjective perceptions of alertness and focus. We also assess usability and user receptivity towards the approach across various simulated driving scenarios (highway, city), times of day (day, night), and traffic levels (low, heavy, fast). In doing so, we outline specific use cases where fast breathing interventions are more or less appropriate and beneficial (e.g., during long, monotonous drives on the highway or at night vs. complex or tense driving scenarios), and we offer fertile future directions for the continued development of breathing systems for health and well-being.

Stress affects the lives of millions of people every day. In-situ sensing could enable just-in-time stress management interventions. We present the first work to detect stress using the movements of a car's existing steering wheel. We extend prior work on PC peripherals and demonstrate that stress, expressed through muscle tension in the limbs, can be measured through the way we drive a car. We collected data in a driving simulator under controlled circumstances to vary the levels of induced stress, within subjects. We analyze angular displacement data to estimate coefficients related to muscle tension using an inverse filtering technique. We prove that the damped frequency of a mass spring damper model representing the arm is significantly higher during stress. Stress can be detected with only a few turns during driving. We validate these measures against a known stressor and calibrate our sensor against known stress measurements.

We introduce Inquire, a tool designed to enable qualitative exploration of utterances in social media and large-scale texts. As opposed to keyword search, Inquire allows the effective use of sentences as queries to quickly explore millions of documents to retrieve semantically-similar sentences. We apply Inquire to LiveJournal.com (LJ) database, which contains millions of personal diaries, and we use semantic embeddings trained in LJ or Google News (GN) datasets. We present the system design through iterative evaluations with qualitative researchers. We show how queries become a part of the inductive process, enabling researchers to try multiple ideas while gaining intuition and discovering less-obvious insights. We discuss the choice of LJ as a rich source of public posts, the preference for GN embeddings which link formal language (e.g. "reminiscence triggers") with colloquial expressions (e.g. "music brings back memories"), the interplay between tool and user, and potential qualitative and social research opportunities.

This demo presents an instance of Inquire, a tool designed to support qualitative researchers in the early stages of research. The tool enables the search over millions of users' records to extract early insights to aid in the formulation of research strategies. The tool presents the work described in the Inquire paper by Paredes, et. al. [12] in this demo we show how queries become a part of the inductive process, enabling researchers to try multiple ideas while gaining intuition and discovering less-obvious insights. We leverage LiveJournal (LJ) as a rich source of public posts, and Google News (GN) embeddings which link formal language (e.g. "reminiscence triggers") with colloquial expressions (e.g. "music brings back memories"). Using our tool, we elicit the interplay between tool and user to enhance qualitative and social research opportunities.

We fuse science and design thinking to create a novel, IoT interactive urban lights system focused on increasing positive affect among pedestrians. Our contributions are three-fold. First, the design, construction, and evaluation of an efficient interactive lighting system focused on well-being, as opposed to systems focused on utility or landscaping. Second, we used scientific methods to discover basic design parameters for affective outcomes. Third, we optimized user experiences for low energy profiles, positive affect, and interactivity. Tested interactions show positive and some unexpected negative responses. Optimal interactive designs cut energy consumption by 75% while maintaining positive affect. Furthermore, card sorting design exercises revealed an inverse relationship between perceived pleasant feelings and interactivity. We conclude by discussing the implications of our research for the design of coherent, attractive, and efficient urban lighting.

Stress causes and exacerbates many physiological and mental health problems. Routine and unobtrusive monitoring of stress would enable a variety of treatments, from break-taking to calming exercises. It may also be a valuable tool for assessing effects (frustration, difficulty) of using interfaces or applications. Custom sensing hardware is a poor option, because of the need to buy/wear/use it continuously, even before stress-related problems are evident. Here we explore stress measurement from common computer mouse operations. We use a simple model of arm-hand dynamics that captures muscle stiffness during mouse movement. We show that the within-subject mouse-derived stress measure is quite strong, even compared to concurrent physiological sensor measurements. While our study used fixed mouse tasks, the stress signal was still strong even when averaged across widely varying task geometries. We argue that mouse sensing "in the wild" may be feasible, by analyzing frequently-performed operations of particular geometries.

This paper describes design explorations for stress mitigation on mobile devices based on three types of interventions: haptic feedback, games and social networks. The paper offers a qualitative assessment of the usability of these three types of interventions together with an initial analysis of their potential efficacy. Social networking and games show great potential for stress relief. Lastly, the paper discusses key findings and considerations for long-term studies of stress mitigation in HCI, as well as a list of aspects to be considered when designing calming interventions.