Passive mobile sensing for the purpose of human state modeling is a fast-growing area. It has been applied to solve a wide range of behavior-related problems, including physical and mental health monitoring, affective computing, activity recognition, routine modeling, etc. However, in spite of the emerging literature that has investigated a wide range of application scenarios, there is little work focusing on the lessons learned by researchers, and on guidance for researchers to this approach. How do researchers conduct these types of research studies? Is there any established common practice when applying mobile sensing across different application areas? What are the pain points and needs that they frequently encounter? Answering these questions is an important step in the maturing of this growing sub-field of ubiquitous computing, and can benefit a wide range of audiences. It can serve to educate researchers who have growing interests in this area but have little to no previous experience. Intermediate researchers may also find the results interesting and helpful for reference to improve their skills. Moreover, it can further shed light on the design guidelines for a future toolkit that could facilitate research processes being used. In this paper, we fill this gap and answer these questions by conducting semi-structured interviews with ten experienced researchers from four countries to understand their practices and pain points when conducting their research. Our results reveal a common pipeline that researchers have adopted, and identify major challenges that do not appear in published work but that researchers often encounter. Based on the results of our interviews, we discuss practical suggestions for novice researchers and high-level design principles for a toolkit that can accelerate passive mobile sensing research.
Mental health of UW students during Spring 2020 varied tremendously: the challenges of online learning during the pandemic were entwined with social isolation, family demands and socioeconomic pressures. In this context, individual differences in coping mechanisms had a big impact. The findings of this paper underline the need for interventions oriented towards problem-focused coping and suggest opportunities for peer role modeling.
Heterogeneity in individuals’ levels of anxiety (reported in ESM). Individual trajectories of anxiety are shown in different line types and colors (dotted versus solid lines represent different participants). Although the mean level of anxiety is 1 on a scale of 0–4, the significant variation in responses invites examination of individuals and subgroups.
This mixed-method study examined the experiences of college students during the COVID-19 pandemic through surveys, experience sampling data collected over two academic quarters (Spring 2019 n1 = 253; Spring 2020 n2 = 147), and semi-structured interviews with 27 undergraduate students.
There were no marked changes in mean levels of depressive symptoms, anxiety, stress, or loneliness between 2019 and 2020, or over the course of the Spring 2020 term. Students in both the 2019 and 2020 cohort who indicated psychosocial vulnerability at the initial assessment showed worse psychosocial functioning throughout the entire Spring term relative to other students. However, rates of distress increased faster in 2020 than in 2019 for these individuals. Across individuals, homogeneity of variance tests and multi-level models revealed significant heterogeneity, suggesting the need to examine not just means but the variations in individuals’ experiences.
Thematic analysis of interviews characterizes these varied experiences, describing the contexts for students’ challenges and strategies. This analysis highlights the interweaving of psychosocial and academic distress: Challenges such as isolation from peers, lack of interactivity with instructors, and difficulty adjusting to family needs had both an emotional and academic toll. Strategies for adjusting to this new context included initiating remote study and hangout sessions with peers, as well as self-learning. In these and other strategies, students used technologies in different ways and for different purposes than they had previously. Supporting qualitative insight about adaptive responses were quantitative findings that students who used more problem-focused forms of coping reported fewer mental health symptoms over the course of the pandemic, even though they perceived their stress as more severe.
Example quotes:
“I like to build things and stuff like that. I like to see it in person and feel it. So the fact that everything was online…. I’m just basically reading all the time. I just couldn’t learn that way”
Insomnia has been pretty hard for me . . . I would spend a lot of time lying in bed not doing anything when I had a lot of homework to do the next day. So then I would become stressed about whether I’ll be able to finish that homework or not.”
“It was challenging … being independent and then being pushed back home. It’s a huge change because now you have more rules again”
“For a few of my classes I feel like actually [I] was self-learning because sometimes it’s hard to sit through hours of lectures and watch it.”
“I would initiate… we have a study group chat and every day I would be like ‘Hey I’m going to be on at this time starting at this time.’ So then I gave them time to all have the room open for Zoom and stuff. Okay and then any time after that they can join and then said I [would] wait like maybe 30 minutes or even an hour…. And then people join and then we work maybe … till midnight, a little bit past midnight”
Megan is a Phd Student at the Human Computer Interaction Institute at Carnegie Mellon Unviversity. She is advised by Prof. Jennifer Mankoff of the University of Washington and and Prof. Scott E. Hudson. She completed her bachelors in Computer Science at Colorado State University in 2017. She is an NSF Fellow, and a Center for Machine Learning and Health Fellow. During her Undergraduate degree Megan’s research was adviced by Dr. Jaime Ruiz and Prof. Amy Hurst.
Her research focuses on creating computer aided design and fabrication tools that expand the digital fabrication process with new materials. She uses participatory observation and participatory design methods to study assistive technology and digital fabrication among many stakeholder (people with disabilities, caregivers, and clinicians).
Visual semantics provide spatial information like size, shape, and position, which are necessary to understand and efficiently use interfaces and documents. Yet little is known about whether blind and low-vision (BLV) technology users want to interact with visual affordances, and, if so, for which task scenarios. In this work, through semi-structured and task-based interviews, we explore preferences, interest levels, and use of visual semantics among BLV technology users across two device platforms (smartphones and laptops), and information seeking and interactions common in apps and web browsing. Findings show that participants could benefit from access to visual semantics for collaboration, navigation, and design. To learn this information, our participants used trial and error, sighted assistance, and features in existing screen reading technology like touch exploration. Finally, we found that missing information and inconsistent screen reader representations of user interfaces hinder learning. We discuss potential applications and future work to equip BLV users with necessary information to engage with visual semantics.
Past research regarding on-body interaction typically requires custom sensors, limiting their scalability and generalizability. We propose EarBuddy, a real-time system that leverages the microphone in commercial wireless earbuds to detect tapping and sliding gestures near the face and ears. We develop a design space to generate 27 valid gestures and conducted a user study (N=16) to select the eight gestures that were optimal for both human preference and microphone detectability. We collected a dataset on those eight gestures (N=20) and trained deep learning models for gesture detection and classification. Our optimized classifier achieved an accuracy of 95.3%. Finally, we conducted a user study (N=12) to evaluate EarBuddy’s usability. Our results show that EarBuddy can facilitate novel interaction and that users feel very positively about the system. EarBuddy provides a new eyes-free, socially acceptable input method that is compatible with commercial wireless earbuds and has the potential for scalability and generalizability
We present HulaMove, a novel interaction technique that leverages the movement of the waist as a new eyes-free and hands-free input method for both the physical world and the virtual world. We first conducted a user study (N=12) to understand users’ ability to control their waist. We found that users could easily discriminate eight shifting directions and two rotating orientations, and quickly confirm actions by returning to the original position (quick return). We developed a design space with eight gestures for waist interaction based on the results and implemented an IMU-based real-time system. Using a hierarchical machine learning model, our system could recognize waist gestures at an accuracy of 97.5%. Finally, we conducted a second user study (N=12) for usability testing in both real-world scenarios and virtual reality settings. Our usability study indicated that HulaMove significantly reduced interaction time by 41.8% compared to a touch screen method, and greatly improved users’ sense of presence in the virtual world. This novel technique provides an additional input method when users’ eyes or hands are busy, accelerates users’ daily operations, and augments their immersive experience in the virtual world.
Knitting is a popular craft that can be used to create customized fabric objects such as household items, clothing and toys. Additionally, many knitters find knitting to be a relaxing and calming exercise. Little is known about how disabled knitters use and benefit from knitting, and what accessibility solutions and challenges they create and encounter. We conducted interviews with 16 experienced, disabled knitters and analyzed 20 threads from six forums that discussed accessible knitting to identify how and why disabled knitters knit, and what accessibility concerns remain. We additionally conducted an iterative design case study developing knitting tools for a knitter who found existing solutions insufficient. Our innovations improved the range of stitches she could produce. We conclude by arguing for the importance of improving tools for both pattern generation and modification as well as adaptations or modifications to existing tools such as looms to make it easier to track progress
Aashaka is a PhD candidate in the UW Paul G. Allen School of Computer Science and Engineering. She is advised by Dr. Jennifer Mankoff and Dr. Richard Ladner. Her research focuses on d/Deaf and hard-of-hearing communication accessibility and explores how can we support all ways of communicating. She explores a range of modalities (speechreading, signing, captioning) as well as languages (multilingualism) in my work. She aims to both document the fluidity of language/communication as well as build technologies that support minoritized communication practices.
Automatic knitting machines are robust, digital fabrication devices that enable rapid and reliable production of attractive, functional objects by combining stitches to produce unique physical properties. However, no existing design tools support optimization for desirable physical and aesthetic knitted properties. We present KnitGIST (Generative Instantiation Synthesis Toolkit for knitting), a program synthesis pipeline and library for generating hand- and machine-knitting patterns by intuitively mapping objectives to tactics for texture design. KnitGIST generates a machine-knittable program in a domain-specific programming language.
The prevalence of mobile phones and wearable devices enables the passive capturing and modeling of human behavior at an unprecedented resolution and scale. Past research has demonstrated the capability of mobile sensing to model aspects of physical health, mental health, education, and work performance, etc. However, most of the algorithms and models proposed in previous work follow a one-size-fits-all (i.e., population modeling) approach that looks for common behaviors amongst all users, disregarding the fact that individuals can behave very differently, resulting in reduced model performance. Further, black-box models are often used that do not allow for interpretability and human behavior understanding. We present a new method to address the problems of personalized behavior classification and interpretability, and apply it to depression detection among college students. Inspired by the idea of collaborative-filtering, our method is a type of memory-based learning algorithm. It leverages the relevance of mobile-sensed behavior features among individuals to calculate personalized relevance weights, which are used to impute missing data and select features according to a specific modeling goal (e.g., whether the student has depressive symptoms) in different time epochs, i.e., times of the day and days of the week. It then compiles features from epochs using majority voting to obtain the final prediction. We apply our algorithm on a depression detection dataset collected from first-year college students with low data-missing rates and show that our method outperforms the state-of-the-art machine learning model by 5.1% in accuracy and 5.5% in F1 score. We further verify the pipeline-level generalizability of our approach by achieving similar results on a second dataset, with an average improvement of 3.4% across performance metrics. Beyond achieving better classification performance, our novel approach is further able to generate personalized interpretations of the models for each individual. These interpretations are supported by existing depression-related literature and can potentially inspire automated and personalized depression intervention design in the future.The prevalence of mobile phones and wearable devices enables the passive capturing and modeling of human behavior at an unprecedented resolution and scale. Past research has demonstrated the capability of mobile sensing to model aspects of physical health, mental health, education, and work performance, etc. However, most of the algorithms and models proposed in previous work follow a one-size-fits-all (i.e., population modeling) approach that looks for common behaviors amongst all users, disregarding the fact that individuals can behave very differently, resulting in reduced model performance. Further, black-box models are often used that do not allow for interpretability and human behavior understanding. We present a new method to address the problems of personalized behavior classification and interpretability, and apply it to depression detection among college students. Inspired by the idea of collaborative-filtering, our method is a type of memory-based learning algorithm. It leverages the relevance of mobile-sensed behavior features among individuals to calculate personalized relevance weights, which are used to impute missing data and select features according to a specific modeling goal (e.g., whether the student has depressive symptoms) in different time epochs, i.e., times of the day and days of the week. It then compiles features from epochs using majority voting to obtain the final prediction. We apply our algorithm on a depression detection dataset collected from first-year college students with low data-missing rates and show that our method outperforms the state-of-the-art machine learning model by 5.1% in accuracy and 5.5% in F1 score. We further verify the pipeline-level generalizability of our approach by achieving similar results on a second dataset, with an average improvement of 3.4% across performance metrics. Beyond achieving better classification performance, our novel approach is further able to generate personalized interpretations of the models for each individual. These interpretations are supported by existing depression-related literature and can potentially inspire automated and personalized depression intervention design in the future.
The rate of depression in college students is rising, which is known to increase suicide risk, lower academic performance and double the likelihood of dropping out. Researchers have used passive mobile sensing technology to assess mental health. Existing work on finding relationships between mobile sensing and depression, as well as identifying depression via sensing features, mainly utilize single data channels or simply concatenate multiple channels. There is an opportunity to identify better features by reasoning about co-occurrence across multiple sensing channels. We present a new method to extract contextually filtered features on passively collected, time-series data from mobile devices via rule mining algorithms. We first employ association rule mining algorithms on two different user groups (e.g., depression vs. non-depression). We then introduce a new metric to select a subset of rules that identifies distinguishing behavior patterns between the two groups. Finally, we consider co-occurrence across the features that comprise the rules in a feature extraction stage to obtain contextually filtered features with which to train classifiers. Our results reveal that the best model with these features significantly outperforms a standard model that uses unimodal features by an average of 9.7% across a variety of metrics. We further verified the generalizability of our approach on a second dataset, and achieved very similar results.
We present a machine learning approach that uses data from smartphones and ftness trackers of 138 college students to identify students that experienced depressive symptoms at the end of the semester and students whose depressive symptoms worsened over the semester. Our novel approach is a feature extraction technique that allows us to select meaningful features indicative of depressive symptoms from longitudinal data. It allows us to detect the presence of post-semester depressive symptoms with an accuracy of 85.7% and change in symptom severity with an accuracy of 85.4%. It also predicts these outcomes with an accuracy of >80%, 11-15 weeks before the end of the semester, allowing ample time for preemptive interventions. Our work has signifcant implications for the detection of health outcomes using longitudinal behavioral data and limited ground truth. By detecting change and predicting symptoms several weeks before their onset, our work also has implications for preventing depression.
Bar chart shows value of baseline, bluetooth, calls, campus map, location, phone usage, sleep and step features on detecting change in depression. the best set leads to 85.4% accuracy; all features except bluetooth and calls improve on baseline accuracy of 65.9%
Megan is a Phd Student at the Human Computer Interaction Institute at Carnegie Mellon Unviversity. She is advised by Prof. Jennifer Mankoff of the University of Washington and and Prof. Scott E. Hudson. She completed her bachelors in Computer Science at Colorado State University in 2017. She is an NSF Fellow, and a Center for Machine Learning and Health Fellow. During her Undergraduate degree Megan’s research was adviced by Dr. Jaime Ruiz and Prof. Amy Hurst.
