Passively-sensed Behavioral Correlates of Discrimination Events in College Students

Effects of educational intervention based on childbirth scenarios on fear of childbirth in primiparous women

BACKGROUND

Fear of childbirth (FOC) is one of the common reasons for choosing cesarean delivery without medical indications. The present study aimed to assess the effect of childbirth scenario-based educational intervention on FOC in primiparous women.

MATERIALS AND METHODS

This study was conducted on 72 primiparous women attending comprehensive health care centers in Qazvin, Iran, in 2021. Participants were randomly placed in the control group (n = 38) and the intervention group (n = 34). The participants in the intervention group read the booklet of childbirth scenarios once a week for eight weeks. Data were collected using the demographic-fertility questionnaire and the Wijma Delivery Expectancy/Experience Questionnaire (W-DEQ) before the intervention, eight weeks after the intervention, and the first week after delivery. Data analysis was carried out using independent t-test, Chi-square, Fisher's exact, repeated measures analysis of variance (ANOVA), and analysis of covariance (ANCOVA).

RESULTS

By controlling the FOC scores before the intervention, the mean total FOC scores eight weeks after the intervention and in the first week after delivery in the intervention group were significantly 34 units (95% CI: 27.3-40.7) and 22.9 units (95% CI: 14.6-31.1) lower than the control group respectively (P < 0.001).

CONCLUSION

Based on the results, childbirth scenario-based intervention can effectively reduce FOC among primiparous women. Healthcare providers, especially midwives, can benefit from applying childbirth scenario-based intervention in prenatal care to reduce the FOC of pregnant women.

Applying Watson's Theory of Transpersonal Caring to Situate Caregiver Accounts of End-of-Life Experiences Within a Caregiving Context

End-of life-experiences, including profoundly meaningful dreams, visions, and sensations, may be experienced by caregivers at the time of a patient's death, yet few caregivers feel comfortable discussing these experiences with colleagues or other members of the care unit. This article presents findings from a descriptive qualitative study of end-of-life experiences reported by caregivers and frames these experiences within Watson's Theory of Transpersonal Caring, which is a holistic approach to health care that emphasizes the transpersonal caring relationship. Watson's Theory is particularly useful for framing end-of-life experiences in a caregiving context as it avoids debates about the nature of these experiences and emphasizes their therapeutic value in human caring. This article also argues that it is time for open discussions about end-of-life experiences reported by caregivers and what they might teach us about death and dying.

Digital Phenotyping for Stress, Anxiety, and Mild Depression: Systematic Literature Review

BACKGROUND

Unaddressed early-stage mental health issues, including stress, anxiety, and mild depression, can become a burden for individuals in the long term. Digital phenotyping involves capturing continuous behavioral data via digital smartphone devices to monitor human behavior and can potentially identify milder symptoms before they become serious.

OBJECTIVE

This systematic literature review aimed to answer the following questions: (1) what is the evidence of the effectiveness of digital phenotyping using smartphones in identifying behavioral patterns related to stress, anxiety, and mild depression? and (2) in particular, which smartphone sensors are found to be effective, and what are the associated challenges?

METHODS

We used the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) process to identify 36 papers (reporting on 40 studies) to assess the key smartphone sensors related to stress, anxiety, and mild depression. We excluded studies conducted with nonadult participants (eg, teenagers and children) and clinical populations, as well as personality measurement and phobia studies. As we focused on the effectiveness of digital phenotyping using smartphones, results related to wearable devices were excluded.

RESULTS

We categorized the studies into 3 major groups based on the recruited participants: studies with students enrolled in universities, studies with adults who were unaffiliated to any particular organization, and studies with employees employed in an organization. The study length varied from 10 days to 3 years. A range of passive sensors were used in the studies, including GPS, Bluetooth, accelerometer, microphone, illuminance, gyroscope, and Wi-Fi. These were used to assess locations visited; mobility; speech patterns; phone use, such as screen checking; time spent in bed; physical activity; sleep; and aspects of social interactions, such as the number of interactions and response time. Of the 40 included studies, 31 (78%) used machine learning models for prediction; most others (n=8, 20%) used descriptive statistics. Students and adults who experienced stress, anxiety, or depression visited fewer locations, were more sedentary, had irregular sleep, and accrued increased phone use. In contrast to students and adults, less mobility was seen as positive for employees because less mobility in workplaces was associated with higher performance. Overall, travel, physical activity, sleep, social interaction, and phone use were related to stress, anxiety, and mild depression.

CONCLUSIONS

This study focused on understanding whether smartphone sensors can be effectively used to detect behavioral patterns associated with stress, anxiety, and mild depression in nonclinical participants. The reviewed studies provided evidence that smartphone sensors are effective in identifying behavioral patterns associated with stress, anxiety, and mild depression.

Smart Speaker and ICT Use in Relationship With Social Connectedness During the Pandemic: Loneliness and Social Isolation Found in Older Adults in Low-Income Housing

BACKGROUND AND OBJECTIVES

Social well-being of older adults living in low-income housing was disproportionately affected by the coronavirus disease 2019 pandemic. We explored low-income residents' experiences of social isolation and loneliness and strategies to remain socially connected during the pandemic.

RESEARCH DESIGN AND METHODS

As part of a larger, 3-phase user-centered design study, we conducted a qualitative study using focus groups to gain insights into social isolation experiences and the role of information and communication technologies (ICTs), including smart speakers, in social connectedness (N = 25, 76% African American). We also collected survey data to describe social isolation, loneliness, and current ICT use in the sample. Participants included both smart speaker users and nonusers.

RESULTS

Experiences of social isolation and loneliness varied by participants' sociodemographic characteristics and previous experiences with smart speakers. Qualitative analysis showed participants demonstrated coping strategies developed during the pandemic to adapt to new norms of connecting with others, including technology-enabled social interactions. Participants expressed a strong desire to build community together in their facilities and highlighted the potential role of smart speakers in making meaningful social connections, encompassing safety checks to have a means for emergencies, and providing a virtual companion. Access, digital literacy, training, security, and privacy issues were discussed as factors affecting their adoption of new ICT for enhanced social connectedness.

DISCUSSION AND IMPLICATIONS

This study highlights the importance of understanding the unique social isolation experience, demographics, and social determinants of health of low-income residents to develop ICT-based interventions for social connectedness.

Capturing the College Experience: A Four-Year Mobile Sensing Study of Mental Health, Resilience and Behavior of College Students during the Pandemic

Understanding the dynamics of mental health among undergraduate students across the college years is of critical importance, particularly during a global pandemic. In our study, we track two cohorts of first-year students at Dartmouth College for four years, both on and off campus, creating the longest longitudinal mobile sensing study to date. Using passive sensor data, surveys, and interviews, we capture changing behaviors before, during, and after the COVID-19 pandemic subsides. Our findings reveal the pandemic's impact on students' mental health, gender based behavioral differences, impact of changing living conditions and evidence of persistent behavioral patterns as the pandemic subsides. We observe that while some behaviors return to normal, others remain elevated. Tracking over 200 undergraduate students from high school to graduation, our study provides invaluable insights into changing behaviors, resilience and mental health in college life. Conducting a long-term study with frequent phone OS updates poses significant challenges for mobile sensing apps, data completeness and compliance. Our results offer new insights for Human-Computer Interaction researchers, educators and administrators regarding college life pressures. We also detail the public release of the de-identified College Experience Study dataset used in this paper and discuss a number of open research questions that could be studied using the public dataset.

Using the COM-B Model and Theoretical Domains Framework to Understand Workplace Disclosure Experiences, Influencers, and Needs Among Autistic Young Adults

For autistic young adults, deciding whether to disclose their autism at work is complex. Minimal research explores what they need to support disclosure and what influences decisions. To understand disclosure needs and influencers, we explored (i) disclosure decision-making experiences and (ii) perceptions of the disclosure process among autistic young adults. We conducted focus groups using the Capability, Opportunity, Motivation, Behaviour Model and Theoretical Domains Framework (TDF). We analyzed data from 23 participants and mapped onto the TDF to develop five themes: (1) workplace environment, (2) perceptions of disclosure outcomes, (3) personal factors and identity, (4) disclosure-related ambitions and determination, and (5) know-hows of disclosure. Future work should prioritize developing disclosure decision-making supports and investigate employer roles in fostering inclusive workplaces.

ChatGPT: promise and challenges for deployment in low- and middle-income countries

In low- and middle-income countries (LMICs), the fields of medicine and public health grapple with numerous challenges that continue to hinder patients' access to healthcare services. ChatGPT, a publicly accessible chatbot, has emerged as a potential tool in aiding public health efforts in LMICs. This viewpoint details the potential benefits of employing ChatGPT in LMICs to improve medicine and public health encompassing a broad spectrum of domains ranging from health literacy, screening, triaging, remote healthcare support, mental health support, multilingual capabilities, healthcare communication and documentation, medical training and education, and support for healthcare professionals. Additionally, we also share potential concerns and limitations associated with the use of ChatGPT and provide a balanced discussion on the opportunities and challenges of using ChatGPT in LMICs.

Barriers and Facilitators of Artificial Intelligence in Family Medicine: An Empirical Study With Physicians in Saudi Arabia

BACKGROUND

Artificial intelligence (AI) is a novel technology that has been widely acknowledged for its potential to improve the processes' efficiency across industries. However, its barriers and facilitators in healthcare are not completely understood due to its novel nature.

STUDY PURPOSE

The purpose of this study is to explore the intricate landscape of AI use in family medicine, aiming to uncover the factors that either hinder or enable its successful adoption.

METHODS

A cross-sectional survey design is adopted in this study. The questionnaire included 10 factors (performance expectancy, effort expectancy, social influence, facilitating conditions, behavioral intention, trust, perceived privacy risk, personal innovativeness, ethical concerns, and facilitators) affecting the acceptance of AI. A total of 157 family physicians participated in the online survey.

RESULTS

Effort expectancy (μ = 3.85) and facilitating conditions (μ = 3.77) were identified to be strong influence factors. Access to data (μ = 4.33), increased computing power (μ = 3.92), and telemedicine (μ = 3.78) were identified as major facilitators; regulatory support (μ = 2.29) and interoperability standards (μ = 2.71) were identified as barriers along with privacy and ethical concerns. Younger individuals tend to have more positive attitudes and expectations toward AI-enabled assistants compared to older participants (p < .05). Perceived privacy risk is negatively correlated with all factors.

CONCLUSION

Although there are various barriers and concerns regarding the use of AI in healthcare, the preference for AI use in healthcare, especially family medicine, is increasing.

Exposure and Reactions to Cancer Treatment Misinformation and Advice: Survey Study

BACKGROUND

Cancer treatment misinformation, or false claims about alternative cures, often spreads faster and farther than true information on social media. Cancer treatment misinformation can harm the psychosocial and physical health of individuals with cancer and their cancer care networks by causing distress and encouraging people to abandon support, potentially leading to deviations from evidence-based care. There is a pressing need to understand how cancer treatment misinformation is shared and uncover ways to reduce misinformation.

OBJECTIVE

We aimed to better understand exposure and reactions to cancer treatment misinformation, including the willingness of study participants to prosocially intervene and their intentions to share Instagram posts with cancer treatment misinformation.

METHODS

We conducted a survey on cancer treatment misinformation among US adults in December 2021. Participants reported their exposure and reactions to cancer treatment misinformation generally (saw or heard, source, type of advice, and curiosity) and specifically on social media (platform, believability). Participants were then randomly assigned to view 1 of 3 cancer treatment misinformation posts or an information post and asked to report their willingness to prosocially intervene and their intentions to share.

RESULTS

Among US adult participants (N=603; mean age 46, SD 18.83 years), including those with cancer and cancer caregivers, almost 1 in 4 (142/603, 23.5%) received advice about alternative ways to treat or cure cancer. Advice was primarily shared through family (39.4%) and friends (37.3%) for digestive (30.3%) and natural (14.1%) alternative cancer treatments, which generated curiosity among most recipients (106/142, 74.6%). More than half of participants (337/603, 55.9%) saw any cancer treatment misinformation on social media, with significantly higher exposure for those with cancer (53/109, 70.6%) than for those without cancer (89/494, 52.6%; P<.001). Participants saw cancer misinformation on Facebook (39.8%), YouTube (27%), Instagram (22.1%), and TikTok (14.1%), among other platforms. Participants (429/603, 71.1%) thought cancer treatment misinformation was true, at least sometimes, on social media. More than half (357/603, 59.2%) were likely to share any cancer misinformation posts shown. Many participants (412/603, 68.3%) were willing to prosocially intervene for any cancer misinformation posts, including flagging the cancer treatment misinformation posts as false (49.7%-51.4%) or reporting them to the platform (48.1%-51.4%). Among the participants, individuals with cancer and those who identified as Black or Hispanic reported greater willingness to intervene to reduce cancer misinformation but also higher intentions to share misinformation.

CONCLUSIONS

Cancer treatment misinformation reaches US adults through social media, including on widely used platforms for support. Many believe that social media posts about alternative cancer treatment are true at least some of the time. The willingness of US adults, including those with cancer and members of susceptible populations, to prosocially intervene could initiate the necessary community action to reduce cancer treatment misinformation if coupled with strategies to help individuals discern false claims.

A Scoping Review of Physician Advocacy on Twitter

Twitter has been adopted by physicians across most medical specialties; it allows for the wide dissemination of information and calls to action, brings new stakeholders into collations, promotes academic engagement, and fosters collaboration between academia and private practice. In this review of the literature, we briefly outline the state of advocacy in health care and summarize current Twitter-based advocacy efforts in the major specialties of health care, identifying both successful strategies as well as gaps in Twitter advocacy research. Relevant articles were obtained via PubMed and Google Scholar searches using the phrases "Twitter advocacy healthcare," "[specialty name] Twitter" and "[specialty name] Twitter advocacy." Several overarching themes were found to be widely utilized in specialty-specific discussions of Twitter advocacy efforts: organizing under a specific hashtag, fostering dialogue between stakeholders, and tweeting using personalized, action-oriented language. Fields such as pediatrics, heme/onc, ENT, and ophthalmology have most thoroughly embraced the desire to learn how to most effectively advocate on Twitter. Other fields such as OBGYN, cardiology, and surgery have less academic focus on online advocacy. Outside of advocacy efforts, the research and academic benefits of Twitter are well described in nearly every specialty. In conclusion, while clinicians are encouraged to advocate online, only broad strategies for online engagement are currently offered. Additional research into the details of how to successfully create an online profile and Twitter presence is needed to ensure all physicians are able to maximize their advocacy efforts, with clarification of the goals and objectives of this engagement also required.

Distress among undergraduates: Marginality, stressors and resilience resources

Objective: This study addresses mental health concerns among university students, examining cumulative stress exposure as well as resilience resources. Participants: Participants were 253 first- and second-year undergraduate students (age = 18.76; 49.80% male, 69% students of color) enrolled at a large western US university. Methods: Data were obtained from a cross-sectional online survey examining marginalized statuses and multiple stressors alongside coping responses, adaptive self-concept, and social support as predictors of stress, anxiety, and depression. Results: Multivariate regressions demonstrated significant associations between stress exposures and lower levels of resilience resources with each mental health indicator (with substantial R2 of.49-.60). Although stressor exposures accounted for significant increases in mental health concerns, their exploratory power was attenuated by resilience resources (e.g., beta decreases from.25 to.16). Conclusions: Better understanding cumulative adversity/resilience resource profiles, particularly among marginalized students, can help universities in prioritizing institutional support responses toward prevention and mitigating psychological distress.

Visualising data science workflows to support third-party notebook comprehension: an empirical study

Data science is an exploratory and iterative process that often leads to complex and unstructured code. This code is usually poorly documented and, consequently, hard to understand by a third party. In this paper, we first collect empirical evidence for the non-linearity of data science code from real-world Jupyter notebooks, confirming the need for new approaches that aid in data science code interaction and comprehension. Second, we propose a visualisation method that elucidates implicit workflow information in data science code and assists data scientists in navigating the so-called garden of forking paths in non-linear code. The visualisation also provides information such as the rationale and the identification of the data science pipeline step based on cell annotations. We conducted a user experiment with data scientists to evaluate the proposed method, assessing the influence of (i) different workflow visualisations and (ii) cell annotations on code comprehension. Our results show that visualising the exploration helps the users obtain an overview of the notebook, significantly improving code comprehension. Furthermore, our qualitative analysis provides more insights into the difficulties faced during data science code comprehension.

The Severity of Cyberbullying Affects Bystander Intervention Among College Students: The Roles of Feelings of Responsibility and Empathy

Background

Bystander intervention can protect victims from harm in cyberbullying. Previous studies have found that the severity of cyberbullying incidents is one of the important factors affecting decisions to intervene. However, little is known about the mediating and moderating mechanisms underlying this effect.

Purpose

The current study explored the effect of the severity of cyberbullying incidents on bystander intention to intervene on social network sites (SNSs) among college students (Experiment 1), the mediating role of feelings of responsibility (Experiment 2) and the moderating role of empathy (Experiment 3).

Patients and Methods

We presented cyberbullying incidents with different levels of severity through scenarios including fictive Weibo news reports and comments. Participants were exposed to a fictive cyberbullying incident and asked to complete a questionnaire including measures of the variables of interest.

Results

Our results showed that the severity of incidents positively affected bystander intention to intervene through the mediation of feelings of responsibility. Empathy moderated the effect of incident severity on bystander intention to intervene.

Conclusion

The results of the current study help to understand the behavior of bystanders in cyberbullying and they provide a practical reference for intervention in cyberbullying incidents.

Nightly sleep duration predicts grade point average in the first year of college

Academic achievement in the first year of college is critical for setting students on a pathway toward long-term academic and life success, yet little is known about the factors that shape early college academic achievement. Given the important role sleep plays in learning and memory, here we extend this work to evaluate whether nightly sleep duration predicts change in end-of-semester grade point average (GPA). First-year college students from three independent universities provided sleep actigraphy for a month early in their winter/spring academic term across five studies. Findings showed that greater early-term total nightly sleep duration predicted higher end-of-term GPA, an effect that persisted even after controlling for previous-term GPA and daytime sleep. Specifically, every additional hour of average nightly sleep duration early in the semester was associated with an 0.07 increase in end-of-term GPA. Sensitivity analyses using sleep thresholds also indicated that sleeping less than 6 h each night was a period where sleep shifted from helpful to harmful for end-of-term GPA, relative to previous-term GPA. Notably, predictive relationships with GPA were specific to total nightly sleep duration, and not other markers of sleep, such as the midpoint of a student's nightly sleep window or bedtime timing variability. These findings across five studies establish nightly sleep duration as an important factor in academic success and highlight the potential value of testing early academic term total sleep time interventions during the formative first year of college.

One is the loneliest number: Involuntary celibacy (incel), mental health, and loneliness

Incels-a ragtag collection of young males who have rallied around their shared experience of romantic rejection-have slowly emerged as an online group of interest to researchers, no doubt as a result of several high-profile attacks. Much of this work has centered around incels' dating experiences, sexual attitudes, and online forums. However, it is possible that their moniker, short for involuntary celibate, has resulted in an overemphasis on their sexual exclusion and frustration. Recent work has identified social isolation as a key aspect of inceldom, which may help explain why incels have responded negatively to romantic rejection. The present study thus sought to examine the role of social support and loneliness in experiences of rejection in a sample of incel (n = 67) and non-incel (n = 103) men. Results indicated that incels experience more feelings of loneliness and less social supports than non-incel men. Both of these variables were associated with multiple mental and relational health issues that incels also scored more highly on. Further, incels reported using more solitary and problematic coping mechanisms. These results suggest that incels may be missing a key buffer in sheltering them from the adverse effects of romantic rejection. It also extends previous findings highlighting the importance of attachment styles in differentiating incels from non-incels, which may perpetuate feelings of isolation. Implications for how this may relate to incel discourse and clinical interventions are discussed.

Supplementary Information

The online version contains supplementary material available at 10.1007/s12144-023-04275-z.

Digital Phenotyping of Mental Health using multimodal sensing of multiple situations of interest: A Systematic Literature Review

Many studies have used Digital Phenotyping of Mental Health (DPMH) to complement classic methods of mental health assessment and monitoring. This research area proposes innovative methods that perform multimodal sensing of multiple situations of interest (e.g., sleep, physical activity, mobility) to health professionals. In this paper, we present a Systematic Literature Review (SLR) to recognize, characterize and analyze the state of the art on DPMH using multimodal sensing of multiple situations of interest to professionals. We searched for studies in six digital libraries, which resulted in 1865 retrieved published papers. Next, we performed a systematic process of selecting studies based on inclusion and exclusion criteria, which selected 59 studies for the data extraction phase. First, based on the analysis of the extracted data, we describe an overview of this field, then presenting characteristics of the selected studies, the main mental health topics targeted, the physical and virtual sensors used, and the identified situations of interest. Next, we outline answers to research questions, describing the context data sources used to detect situations, the DPMH workflow used for multimodal sensing of situations, and the application of DPMH solutions in the mental health assessment and monitoring process. In addition, we recognize trends presented by DPMH studies, such as the design of solutions for high-level information recognition, association of features with mental states/disorders, classification of mental states/disorders, and prediction of mental states/disorders. We also recognize the main open issues in this research area. Based on the results of this SLR, we conclude that despite the potential and continuous evolution for using these solutions as medical decision support tools, this research area needs more work to overcome technology and methodological rigor issues to adopt proposed solutions in real clinical settings.

Beyond "pains" and "gains": untangling the health consequences of probation

BACKGROUND

Research on the health consequences of criminal legal system contact has increasingly looked beyond imprisonment to understand how more routine forms of surveillance and punishment shape wellbeing. One of these sites is probation, the largest form of supervision in the U.S. Drawing on an interview study with 162 adults on probation in Hennepin County, MN, in 2019, we map how adults on probation understand the consequences of supervision for their health and how these self-reported health changes correlate with individual, social, and structural circumstances.

RESULTS

Roughly half of participants described their health as having improved since starting probation, while the remainder were split between no change and worsened health. Examining both closed-ended survey questions and open-ended interview prompts, we find that the "gains" of supervision were correlated with substance use treatment (often mandated), reduced drug and alcohol use, increased housing and food security, and perceptions of support from their probation officer. However, these potentially health-promoting mechanisms were attenuated for many participants by the significant "pains" of supervision, including the threat of revocation, which sometimes impacted mental health. In addition, participants in the most precarious circumstances were often unable to meet the demands of supervision, resulting in further punishment.

CONCLUSIONS

Moving beyond the "pains" and "gains" framework, we argue that this analysis provides empirical evidence for the importance of moving social services outside of punishing criminal legal system interventions. People with criminal legal contact often come from deeply marginalized socio-economic contexts and are then expected to meet the rigorous demands of supervision with little state aid for redressing structural barriers. Access to essential services, including healthcare, food, and housing, without the threat of further criminal legal sanctions, can better prevent and respond to many of the behaviors that are currently criminalized in the U.S. legal system, including substance use.

The Reintegration Journey Following A Psychiatric Hospitalization: Examining the Role of Social Technologies

For people diagnosed with mental health conditions, psychiatric hospitalization is a major life transition, involving clinical treatment, crisis stabilization and loss of access of social networks and technology. The period after hospitalization involves not only management of the condition and clinical recovery but also re-establishing social connections and getting back to social and vocational roles for successful reintegration - a significant portion of which is mediated by social technology. However, little is known about how people get back to social lives after psychiatric hospitalization and the role social technology plays during the reintegration process. We address this gap through an interview study with 19 individuals who experienced psychiatric hospitalization in the recent past. Our findings shed light on how people's offline and online social lives are deeply intertwined with management of the mental health condition after hospitalization. We find that social technology supports reintegration journeys after hospitalization as well as presents certain obstacles. We discuss the role of social technology in significant life transitions such as reintegration and conclude with implications for social computing research, platform design and clinical care.

"I don't Think These Devices are Very Culturally Sensitive."-Impact of Automated Speech Recognition Errors on African Americans

Automated speech recognition (ASR) converts language into text and is used across a variety of applications to assist us in everyday life, from powering virtual assistants, natural language conversations, to enabling dictation services. While recent work suggests that there are racial disparities in the performance of ASR systems for speakers of African American Vernacular English, little is known about the psychological and experiential effects of these failures paper provides a detailed examination of the behavioral and psychological consequences of ASR voice errors and the difficulty African American users have with getting their intents recognized. The results demonstrate that ASR failures have a negative, detrimental impact on African American users. Specifically, African Americans feel othered when using technology powered by ASR-errors surface thoughts about identity, namely about race and geographic location-leaving them feeling that the technology was not made for them. As a result, African Americans accommodate their speech to have better success with the technology. We incorporate the insights and lessons learned from sociolinguistics in our suggestions for linguistically responsive ways to build more inclusive voice systems that consider African American users' needs, attitudes, and speech patterns. Our findings suggest that the use of a diary study can enable researchers to best understand the experiences and needs of communities who are often misunderstood by ASR. We argue this methodological framework could enable researchers who are concerned with fairness in AI to better capture the needs of all speakers who are traditionally misheard by voice-activated, artificially intelligent (voice-AI) digital systems.

College from home during COVID-19: A mixed-methods study of heterogeneous experiences

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. These findings underline the need for interventions oriented towards problem-focused coping and suggest opportunities for peer role modeling.

Assessing the relationship between routine and schizophrenia symptoms with passively sensed measures of behavioral stability

Increased stability in one's daily routine is associated with well-being in the general population and often a goal of behavioral interventions for people with serious mental illnesses like schizophrenia. Assessing behavioral stability has been limited in clinical research by the use of retrospective scales, which are susceptible to reporting biases and memory inaccuracies. Mobile passive sensors, which are less susceptible to these sources of error, have emerged as tools to assess behavioral patterns in a range of populations. The present study developed and examined a metric of behavioral stability from data generated by a passive sensing system carried by 61 individuals with schizophrenia for one year. This metric-the Stability Index-appeared orthogonal from existing measures drawn from passive sensors and matched the predictive performance of state-of-the-art features. Specifically, greater stability in social activity (e.g., calls and messages) were associated with lower symptoms, and greater stability in physical activity (e.g., being still) appeared associated with elevated symptoms. This study provides additional support for the predictive value of individualized over population-level data in psychiatric populations. The Stability Index offers also a promising tool for generating insights about the impact of behavioral stability in schizophrenia-spectrum disorders.