Real-world Usage Data Research Articles

Concept of Chatbot as an Intelligent Dialogue Assistant

The purpose of the study is to compare chatbots, assess their ability to perform tasks, analyze their impact on consumers, and determine the areas of application and risks associated with the use of intelligent dialogue assistants. The research methods used in the study include analysis and systematisation of information, synthesis and generalization of theoretical data based on a review of current research, which made it possible to assess the risks and benefits of using chatbots for businesses and ordinary users. The scientific novelty lies in the analysis of technologies for creating intelligent dialogue assistants and determining the areas of application of chatbots. A study of the areas of application of modern intelligent dialogue systems has shown the high efficiency of using chatbots to solve typical user problems. The article provides statistical data on how satisfied Internet users are with contacts with chatbots and describes recommendations for improving such dialogue systems. An analysis of the role of artificial intelligence in the operation of dialogue systems has shown possible risks from the impact of technology on the minds of users. Conclusions. One of the most obvious trends in chatbots in 2023 is that their use will become more widespread and chatbots themselves will become more sophisticated. Their advantage is free customer service and data collection, which can then be used for marketing research. Over time, chatbots will be used in such areas as marketing, recruitment, education, and medicine. Their ability to perform a wide range of tasks makes chatbots attractive for e-commerce stores, B2B companies, real estate, healthcare, and education. In the future, intelligent dialogue agents will work with huge, dynamic, heterogeneous data streams, providing powerful capabilities for adaptive and flexible interaction. Dialogue systems have become successful and reliable due to the large amount of real-world user data available to their developers. However, these systems still exhibit rather limited communication behaviour modelled on information retrieval tasks. Chatbots are developed for research purposes, but they are often limited to a narrow, manually created domain. The newest trend in conversational agent development involves neural networks and models trained on huge collections of dialogue data without detailed specifications of dialogue states. These models lack tractability and interpretability due to their black-box nature. They also require extensive supervised training data to be competitive.

Modeling user choice behavior under data corruption: Robust learning of the latent decision threshold model

Recent years have witnessed the emergence of many new mobile apps and user-centered systems that interact with users by offering choices with rewards. These applications have been promising to address challenging societal problems such as congestion in transportation and behavior changes for healthier lifestyles. Considerable research efforts have been devoted to model the user behaviors in these new applications. However, as real-world user data is often prone to data corruptions, the success of these models hinges on a robust learning method. Building on the recently proposed Latent Decision Threshold model, this article shows that, among the existing robust learning frameworks, the L 0-norm-based framework can outperform other state-of-the-art methods in terms of prediction accuracy and model estimation. And based on the L 0-norm framework, we further develop a user screening algorithm to identify potential bad actors.

Pilot Investigation of Blood Pressure Control Using a Mobile App (Cardi.Health): Retrospective Chart Review Study.

The high prevalence of hypertension necessitates effective, scalable interventions for blood pressure (BP) control. Self-monitoring has shown improved adherence to medication and better BP management. Mobile apps offer a promising approach with their increasing popularity and potential for large-scale implementation. Studies have demonstrated associations between mobile app interventions and lowered BP, yet real-world data on app effectiveness and engagement remain limited. In this study, we analyzed real-world user data from the Cardi.Health mobile app, which is aimed at helping its users monitor and control their BP. Our goal was to find out whether there is an association between the use of the mobile app and a decrease in BP. Additionally, the study explored how engagement with the app may influence this outcome. This was a retrospective chart review study. The initial study population comprised 4407 Cardi.Health users who began using the app between January 2022 and April 2022. After applying inclusion criteria, the final study cohort comprised 339 users with elevated BP at the baseline. The sample consisted of 108 (31.9%) men and 231 (68.1%) women (P=.04). This retrospective chart review study obtained permission from the Biomedical Research Alliance of New York Institutional Review Board (June 2022, registration ID 22-08-503-939). The study's main findings were that there is a possible relationship between use of the Cardi.Health mobile app and a decrease in systolic BP. Additionally, there was a significant association between active use of the app and systolic BP decrease (χ21=5.311; P=.02). Finally, active users had an almost 2 times greater chance of reducing systolic BP by 5 mm Hg or more over 4 weeks (odds ratio 1.932, 95% CI 1.074-3.528; P=.03). This study shows a possible relationship between Cardi.Health mobile app use and decreased BP. Additionally, engagement with the app may be related to better results-active use was associated with an almost 2-fold increase in the odds of reducing BP by 5 or more mm Hg.

FewShotBP

Deep learning-based methods demonstrate promising results in continuous non-invasive blood pressure measurement, whereas those models trained on large public datasets suffer from severe performance degradation in predicting from real-world user data collected in home settings. Transfer learning has been recently introduced to personalize the pre-trained model with unseen users' data to solve the problem. However, the existing methods based on network fine-tuning for model personalization require a large amount of labeled data, lacking practicality due to labeling using a cuff-based blood pressure monitor is extremely tedious and laborious for home users. In this paper, we propose a novel few-shot transfer learning approach named FewShotBP, which addresses the above-mentioned challenges by introducing a personalization adapter at the personalization stage (i.e., the transfer learning stage), and a multi-modal spectro-temporal neural network at the pre-train stage, to bridge the gap between data-hungry models and limited labeled data in realistic scenarios. To evaluate the approach's significance, we conducted experiments using both a publicly available dataset and a real-world user experiment. The results demonstrated that the proposed approach achieves similar accuracy of blood pressure prediction with 10× less data for personalization compared with the state-of-the-art method in the public dataset and achieves a mean absolute error of 6.68 mmHg (systolic blood pressure) and 3.91 mmHg (diastolic blood pressure) with only 10 personal data samples in the real-world user experiment.

HOME BLOOD PRESSURE MONITORING WITH A DIGITAL BLOOD PRESSURE COACH. A PROSPECTIVE ANALYSIS OF INDIVIDUAL USER DATA

Objective: The influence of baseline BP category and measurement duration on home blood pressure monitoring (HBPM) are still poorly defined, particularly when used in conjunction with a digital application. Design and method: This is a prospective analysis of real-world user data from a digital BP-coach (Manoa app ) in the period from April 2020 (release of the Manoa app) to November 2021 in Germany. The app was freely available in Germany during this period in all major app stores (iOS, Android). We analysed temporal BP changes and performed BP classification tracking in users with self-reported hypertension performing HBPM with a digital and interactive blood pressure coach. Results: Of 3175 users who enrolled in HBPM, 74.1% completed the first measurement period. Overall, mean systolic BP dropped significantly after the first day, but stratification by BP category demonstrated that initial category influenced BP course. BP classification tracking revealed that time to reach final BP category was dependent on baseline category, with users in categories high-normal and grade 1 hypertension requiring more days to decrease BP class volatility and to reach their definitive BP class. This was driven by an intense switching between directly neighbouring categories until the middle phase of the HBPM period, while more distant class switching occurred less often and only early on. Overall, > 90% of users maintained their category by day 5. Omitting the first day from analysis lead to therapeutically relevant reclassification in 3.8% of users. Users who completed at least two HBPM periods (n = 864) showed a mean SBP/DBP decrease of 2.6/1.6 mmHg, which improved hypertension control from 55.6% to 68.1%. Conclusions: With a digital HBPM-protocol, five consecutive measurement days are required for a reliable diagnosis and BP categorization. However, especially at therapeutic thresholds, additional measurement days are often required. Excluding day 1 from the protocol resulted in blood pressure reclassifications in 8.4% of all cases, with therapeutic relevance in 3.8% of cases. The optimal length of HBPM period depends on BP category. HBPM with a digital coach is associated with a reduction in average BP and improvement in BP control.

An Affordable Inkjet-Printed Foot Sole Sensor and Machine Learning for Telehealth Devices

Reduction of cardiovascular disease risk is highly correlated with regularity of exercise, which is not easily observed outside of medical settings, particularly for the elderly. Foot sole monitoring technology is now a saturated market due to its demand for applications in physical therapy, sports, hazardous work, etc. However, the best technology available comes with drawbacks like high prices, bulkiness, discomfort, and low power efficiencies. This work seeks to resolve many of these shortfalls with an inkjet printed foot sole inlay costing $1.85 per sensor, is flexible, runs on nano-watts of power, and can easily be fabricated to personally fit the user's foot. A suite of machine learning algorithms are compared to classify 4 ft movements: sitting, standing, walking, and jogging. Algorithm performance results of the sensor samples show the Support Vector Machine Kernel reaching 83.5% rate of detecting the correct foot movement and classifies 10 times per second. Future work includes embedding the trained algorithm onto a micro-processor, placing it into a shoe sole and performing trials to collect real-world user data such that the technology matures and benefits significantly to those who need a telehealth device for movement monitoring.

The Effects of a Digital Well-being Intervention on Older Adults: Retrospective Analysis of Real-world User Data.

BackgroundDigital interventions have been shown to be effective for a variety of mental health disorders and problems. However, few studies have examined the effects of digital interventions in older adults; therefore, little is known about how older adults engage with or benefit from these interventions. Given that adoption rates for technology among people aged ≥65 years remain substantially lower than in the general population and that approximately 20% of older adults are affected by mental health disorders, research exploring whether older adults will use and benefit from digital interventions is needed.ObjectiveThis study aimed to examine the extent to which older adults engaged with a digital well-being intervention (Happify) and whether engaging with this program led to improvements in both subjective well-being and anxiety symptoms.MethodsIn this retrospective analysis, we analyzed data from 375 real-world Happify users aged ≥65 years who signed up for the platform between January 1, 2019, and December 23, 2021. Changes in well-being and anxiety symptoms across 42 to 182 days were assessed using responses to the in-app assessment, which users were prompted to take every 2 weeks, and were compared among users who engaged with the program at the recommended level (ie, 2 or more activities per week) or below the recommended level.ResultsIn all, 30% (113/375) of the sample engaged with the platform at the recommended level (ie, completed an average of 2 or more activities per week), and overall, users completed an average of 43.35 (SD 87.80) activities, ranging from 1 to 786, between their first and last assessment. Users were also active on the platform for an average of 19.36 (SD 27.16) days, ranging from 1 to 152 days. Moreover, older adults who engaged at the recommended level experienced significantly greater improvements in subjective well-being (P=.002) and anxiety symptoms (P<.001) relative to those who completed fewer activities.ConclusionsThese data provide preliminary evidence that older adults engage with and benefit from digital well-being interventions. We believe that these findings highlight the importance of considering older adult populations in digital health research. More research is needed to understand potential barriers to using digital interventions among older adults and whether digital interventions should be modified to account for this population’s particular needs (eg, ensuring that the intervention is accessible using a variety of devices). However, these results are an important step in demonstrating the feasibility of such interventions in a population that is assumed to be less inclined toward digital approaches.

A digital health program for treatment of urinary incontinence: retrospective review of real-world user data

Introduction and hypothesisTo determine the effectiveness of a prescription digital therapeutic (pDTx) in reducing urinary incontinence (UI) symptoms in real-world users.MethodsThis is a retrospective cohort study of real-world data from users of a pDTx designed to guide pelvic floor muscle training(PFMT) between July 1, 2020–December 31, 2021. The primary outcome was UI symptom change as reported via in-app Urogenital Distress Inventory (UDI-6). Included subjects were female, ≥ 18 years with a diagnosis of stress, urgency, or mixed UI who completed the UDI-6 at baseline and 8 weeks. Demographic, symptom, and adherence data were summarized. Paired t-test and Wilcoxon signed rank test were used to analyze change in outcomes from baseline to 8 weeks across adherence and UI diagnosis groups.ResultsOf 532 women with UI, 265 (50%) met criteria and were included in the analysis. Mean age was 51.2 ± 11.5 years (range 22–84, N = 265). Mean body mass index (BMI) was 27.3 ± 6.2 kg/m2 (range 15.2–46.9, N = 147). Most participants had stress UI (59%) followed by mixed UI (22%), urgency UI/OAB (11%), and unspecified UI (8%). UDI-6 scores improved by 13.90 ± 15.53 (p ≤ 0.001); 62% met or exceeded MCID. Device-reported PFMT adherence was 72% at 4 weeks and 66% at 8 weeks (100% = 14 uses/week). Participants in each diagnosis category reported significant improvement on UDI-6 score from baseline to 8 weeks. No association between UDI-6 score improvement and adherence category, age, BMI, or UI subtype was identified.ConclusionsThis study demonstrates effectiveness of a pDTx in reducing UI symptoms in a real-world setting. Users achieved statistically and clinically significant symptom improvement over an 8-week period.

Using a Digital Approach to Improving Mental Health in Adults With Self-reported Psoriasis: An Analysis of Real-world User Data

Background Visible scales and perceived stigma often lead to feelings of embarrassment, shame, low self-esteem, and self-consciousness among people with psoriasis. Beyond the negative effects of this distress on mental health, some researchers also argue that the inflammatory response caused by psoriasis predisposes patients with psoriasis to mental health conditions like depression. Given that anxiety and depression are linked to higher disease activity and pain in patients with psoriasis, researchers have argued that an important component of any psoriasis management plan should include addressing mental health. However, a shortage of mental health professionals, particularly in low income and rural areas, makes access to mental health care more challenging than many other common referrals—a problem that has been exacerbated in light of the COVID-19 pandemic. Objective This study aims to explore the feasibility of using a digital mental health intervention to help improve subjective well-being and anxiety among adults with self-reported psoriasis. Methods Real-world users who signed up for the digital wellness program, Happify, between January 1, 2017, and June 10, 2021, and who reported having psoriasis during onboarding were included in this analysis. To qualify, users had to complete at least two in-app assessments (which include a proprietary measure of subjective well-being, the Happify Scale, and the Generalized Anxiety Disorder 2 scale to measure anxiety), complete at least 1 Happify activity, complete no more than 3 activities before taking their first assessment, and had to have at least 42 days between their first and last assessment. We examined changes in well-being and anxiety among these participants based on Happify use (recommended vs less than recommended). Results Users who engaged with the program at the recommended level experienced significantly greater improvements in both well-being (P&lt;.001) and anxiety (P=.01). More specifically, users who completed the recommended number of activities improved their well-being scores by 26.8%, whereas users who completed fewer activities improved their well-being scores by only 4.11%. Similarly, users who completed the recommended number of activities improved their anxiety scores by 26.64%, compared to 8.15% among those who engaged below the recommended level. Conclusions These data suggest that a digital mental health intervention can effectively improve both subjective well-being and anxiety among patients with psoriasis when used at the recommended level. Although future research is required to better understand whether this subsequently impacts disease-specific outcomes, such as disease activity and pain, our data suggest that a digital approach may be one method of providing greater access to mental health support for patients with psoriasis, increasing the likelihood that it can be incorporated into their treatment plan. Conflicts of Interest None declared.

Will Apple devices' passive atrial fibrillation detection prevent strokes? Estimating the proportion of high-risk actionable patients with real-world user data.

Utilizing integrated electronic health record (EHR) and consumer-grade wearable device data, we sought to provide real-world estimates for the proportion of wearers that would likely benefit from anticoagulation if an atrial fibrillation (AFib) diagnosis was made based on wearable device data. This study utilized EHR and Apple Watch data from an observational cohort of 1802 patients at Cedars-Sinai Medical Center who linked devices to the EHR between April 25, 2015 and November 16, 2018. Using these data, we estimated the number of high-risk patients who would be actionable for anticoagulation based on (1) medical history, (2) Apple Watch wear patterns, and (3) AFib risk, as determined by an existing validated model. Based on the characteristics of this cohort, a mean of 0.25% (n = 4.58, 95% CI, 2.0-8.0) of patients would be candidates for new anticoagulation based on AFib identified by their Apple Watch. Using EHR data alone, we find that only approximately 36% of the 1802 patients (n = 665.93, 95% CI, 626.0-706.0) would have anticoagulation recommended even after a new AFib diagnosis. These data suggest that there is limited benefit to detect and treat AFib with anticoagulation among this cohort, but that accessing clinical and demographic data from the EHR could help target devices to the patients with the highest potential for benefit. Future research may analyze this relationship at other sites and among other wearable users, including among those who have not linked devices to their EHR.

Emission mitigation potential from coordinated charging schemes for future private electric vehicles

Plug-in electric vehicles (EVs) are expected to synergize with low or even zero-carbon electricity towards a deep mitigation of greenhouse gas (GHG) emission and ultimately carbon neutrality. These benefits are only obtainable when EV charging maximizes the consumption of electricity generated from renewable energy sources. However, the current mismatch between renewable energy output and EV charging demand poses a substantial challenge. Rescheduling charging events, namely charging coordination, has the potential to integrate renewable electricity and tap into higher GHG emission reductions. In this study, with Beijing as the research domain, we develop a charging demand model informed by real-world usage data generated by a massive fleet of private cars, and evaluate the comprehensive impacts of various charging coordination schemes in the future with higher adoption rates of both private EVs and renewable power sources. The research finds that strategies aiming at maximizing renewable power consumption, netload valley filling, and charging cost minimization have similar climate benefits, which can reduce well-to-wheels GHG emissions by approximately 20%, cut charging cost by half, and erase 95% of the need for newly installed generation capacity compared to the benchmark scenario without coordinated charging. On the other hand, conventional charging strategies, such as the simple demand-valley-filling strategy, would increase GHG emissions. The study indicates that substantial benefits can be synergistically achieved between power and transport systems towards improved grid stability, lower fuel cost, and greater emission mitigation by leveraging EV charging flexibility at the end-user side (i.e., charging facility). Furthermore, the potential need for sophisticated charging coordination with multiple optimization objectives is brought to attention.

The Effects of a Digital Mental Health Intervention in Adults With Cardiovascular Disease Risk Factors: Analysis of Real-World User Data.

BackgroundThe American Heart Association has identified poor mental health as a key barrier to healthy behavior change for those with cardiovascular disease (CVD) risk factors such as high blood pressure, high cholesterol, and diabetes. Digital mental health interventions, like those delivered via the internet to computers or smartphones, may provide a scalable solution to improving the mental and physical health of this population. Happify is one such intervention and has demonstrated evidence of efficacy for improving aspects of mental health in both the general population and in users with chronic conditions.ObjectiveThe objectives of this analysis of real-world data from Happify users with self-reported CVD risk factors, including high blood pressure and cholesterol, diabetes, and heart disease, were to examine whether these users would report improvements in subjective well-being and anxiety over time (H1) and use of Happify as recommended would be associated with significantly greater improvement in subjective well-being and anxiety over time compared to less-than-recommended usage (H2).MethodsData were obtained from existing Happify users who reported the aforementioned CVD risk factors. The sample included 1803 users receiving at least 6 weeks’ exposure to Happify (ranging from 42 days to 182 days) who completed at least one activity and two assessments within the app during that time. Subjective well-being was assessed with the Happify Scale, a 9-item measure of positive emotionality and life satisfaction, and anxiety was assessed with the Generalized Anxiety Disorder 2 (GAD-2). To evaluate H1, changes over time in both outcomes were assessed using mixed effects linear regression models, controlling for demographics and usage. For H2, an interaction term was added to the models to assess whether usage as recommended was associated with greater improvement over time.ResultsBoth hypotheses were supported. For both the Happify scale and GAD-2, the initial multivariable model without an interaction demonstrated an effect for time from baseline, and the addition of the interaction term between time and recommended use was significant as well.ConclusionsThis analysis of real-world data provides preliminary evidence that Happify users with self-reported CVD risk factors including high blood pressure or cholesterol, diabetes, and heart disease experienced improved well-being and anxiety over time and that those who used Happify as recommended experienced greater improvements in these aspects of mental health than those who completed fewer activities. These findings extend previous research, which demonstrated that engagement with Happify as recommended was associated with improved well-being among physically healthy users and in those with chronic conditions, to a new population for whom mental health is especially critical: those at risk of developing CVD.

From clinical trials to clinical practice: How long are drugs tested and then used by patients?

ObjectiveEvidence is scarce regarding the safety of long-term drug use, especially for drugs treating chronic diseases. To bridge this knowledge gap, this research investigated the differences in drug exposure between clinical trials and clinical practice.Materials and MethodsWe extracted drug follow-up times from clinical trials in ClinicalTrials.gov and compared the difference between clinical trials and real-world usage data for 914 drugs taken by 96 645 927 patients.ResultsA total of 17.5% of drugs had longer median exposure in practice than in trials, 6% of patients had extended exposure to at least 1 drug, and drugs treating nervous system disorders and cardiovascular diseases were the most common among drugs with high rates of extended exposure.ConclusionsFor most of patients, the drug use length is shorter than the tested length in clinical trials. Still, a remarkable number of patients experienced extended drug exposure, particularly for drugs treating nervous system disorders or cardiovascular disorders.

Multi-Tier CloudVR

The availability of high bandwidth with low-latency communication in 5G mobile networks enables remote rendered real-time virtual reality (VR) applications. Remote rendering of VR graphics in a cloud removes the need for local personal computer for graphics rendering and augments weak graphics processing unit capacity of stand-alone VR headsets. However, to prevent the added network latency of remote rendering from ruining user experience, rendering a locally navigable viewport that is larger than the field of view of the HMD is necessary. The size of the viewport required depends on latency: Longer latency requires rendering a larger viewport and streaming more content. In this article, we aim to utilize multi-access edge computing to assist the backend cloud in such remote rendered interactive VR. Given the dependency between latency and amount and quality of the content streamed, our objective is to jointly optimize the tradeoff between average video quality and delivery latency. Formulating the problem as mixed integer nonlinear programming, we leverage the interpolation between client’s field of view frame size and overall latency to convert the problem to integer nonlinear programming model and then design efficient online algorithms to solve it. The results of our simulations supplemented by real-world user data reveal that enabling a desired balance between video quality and latency, our algorithm particularly achieves the improvements of on average about 22% and 12% in term of video delivery latency and 8% in term of video quality compared to respectively order-of-arrival, threshold-based, and random-location strategies.

Co-Creation Facilitates Translational Research on Upper Limb Prosthetics

People who either use an upper limb prosthesis and/or have used services provided by a prosthetic rehabilitation centre, hereafter called users, are yet to benefit from the fast-paced growth in academic knowledge within the field of upper limb prosthetics. Crucially over the past decade, research has acknowledged the limitations of conducting laboratory-based studies for clinical translation. This has led to an increase, albeit rather small, in trials that gather real-world user data. Multi-stakeholder collaboration is critical within such trials, especially between researchers, users, and clinicians, as well as policy makers, charity representatives, and industry specialists. This paper presents a co-creation model that enables researchers to collaborate with multiple stakeholders, including users, throughout the duration of a study. This approach can lead to a transition in defining the roles of stakeholders, such as users, from participants to co-researchers. This presents a scenario whereby the boundaries between research and participation become blurred and ethical considerations may become complex. However, the time and resources that are required to conduct co-creation within academia can lead to greater impact and benefit the people that the research aims to serve.

Temporal Trends and Interest in Coronary Artery Calcium Scoring Over Time: An Infodemiology Study.

ObjectiveTo evaluate interest in coronary artery calcium (CAC) among the general public during the past 17 years and to compare trends with real-world data on number of CAC procedures performed.MethodsWe used Google Trends, a publicly available database, to access search query data in a systematic and quantitative fashion to search for CAC-related key terms. Search terms included calcium test, heart score, calcium score, coronary calcium, and calcium test score. We accessed Google Trends in January 2021 and analyzed data from 2004 to 2020.ResultsFrom 2004 to December 31, 2020, CAC-related search interest (in relative search volume) increased continually worldwide (+201.9%) and in the United States (+354.8%). Three main events strongly influenced search interest in CAC: reports of a CAC scan of the president of the United States led to a transient 10-fold increase in early January 2018. American College of Cardiology/American Heart Association guideline release led to a sustained increase, and lockdown after the global pandemic due to COVID-19 led to a transient decrease. Real-world data on performed CAC scans showed an increase between 2006 and 2017 (+200.0%); during the same time period, relative search volume for CAC-related search terms increased in a similar pattern (+70.6%-1511.1%). For the search term coronary calcium scan near me, a potential representative of active online search for CAC scanning, we found a +28.8% increase in 2020 compared with 2017.ConclusionGoogle Trends, a valuable tool for assessing public interest in health-related topics, suggests increased overall interest in CAC during the last 17 years that mirrors real-world usage data. Increased interest is seemingly linked to reports of CAC testing in world leaders and endorsement in major guidelines.

An empirical evaluation of different usage pattern between car-sharing battery electric vehicles and private ones

As a non-ownership business mode, a car-sharing service system has received an extensive popularization recently. Many related studies based on the theoretical and questionnaire analyses have confirmed the existence of differences in usage patterns between car-sharing users and private users. Nowadays, usage data provides a new way to analyze and understand the usage pattern of vehicles, which can improve user experience. To study the usage of car-sharing cars and private ones, namely, to study their usage patterns, this paper proposes an evaluation indicator system for usage pattern based on the battery electric vehicle (BEV) data. The evaluation indicator system is based on the state transition approach and describes the usage pattern of BEVs from three dimensions. The travel temporal and travel spatial dimensions describe the time and space characteristics of usage pattern. The decision-making dimension, as a cause of state transition at the micro level, describes the decision-making pattern according to a conceptual psychological model. Finally, an empirical study using the promotion is undertaken to explore differences in the performance of the two BEV types using the real-world usage data. Results show that the evaluation indicator system can identify the differences in usage pattern between car-sharing BEVs and private ones effectively and objectively from different perspectives.

Usability evaluation of an eHealth intervention for family carers of individuals affected by psychosis: A mixed-method study.

BackgroundExisting research suggests that eHealth interventions targeting family carers of individuals with long-term illness offer a promising approach to care delivery. In particular, digital psychoeducational interventions with interactive psychosocial support are well-received with high rates of satisfaction and acceptability. However, development of such interventions for psychosis carers is lacking. We developed a multi-component eHealth intervention specifically for carers of individuals affected by psychosis, called COPe-support (Carers fOr People with Psychosis e-support).ObjectiveUsing mixed methods to evaluate usability, system heuristics and perceived acceptability, we conducted a usability study to establish the suitability of the intervention prototype for the target user group.MethodsTwenty-three carers were recruited to the study and participated in a think-aloud test or a remote online trial of the intervention. Qualitative feedback, post-use System Usability Scale (SUS) scores, and real-world usage data collected from the tests were analysed. These were also supplemented with heuristic evaluation data provided by an independent eLearning technology expert.ResultsParticipants evaluated the intervention content as useful and helpful, and indicated that the system had satisfactory usability with a mean SUS score of 73%, above the usability quality benchmark threshold. Study results identified some minor usability issues, which were corroborated with the eLearning expert’s heuristic evaluation findings. We used these results to refine the COPe-support intervention.ConclusionsThe usability study with end-users and service providers identified real-life usage and usability issues. The study results helped us refine COPe-support and its delivery strategy before its launch as part of a large-scale clinical trial.

Understanding Dynamic Cross-OSN Associations for Cold-Start Recommendation

Online social networks (OSNs) have become an essential part of people's daily life, and an increasing number of users are now using multiple OSNs for different social media services simultaneously. As a result, user's interests and preferences usually distribute in different OSNs. While most of the existing work mainly aggregates the distributed user behaviors or features directly, recently very few efforts have been focused on understanding the cross-OSN association from collective user behaviors. In this paper, we go one step further to consider the dynamic characteristic of user behaviors and propose a dynamic cross-OSN association mining framework. In this framework, dynamic user modeling is first conducted to capture the drift of user interest in each OSN. A session-based factorization method is then proposed to establish the cross-OSN association in a dynamic manner, by incrementally updating the derived association each time a new session of data arrives. Based on the derived dynamic association, we finally design a cold-start YouTube video recommendation application, by only utilizing users' behaviors in Twitter. Experiments are conducted using real-world user data from Twitter and YouTube. The results demonstrate the effectiveness of this proposed framework in capturing the underlying association between different OSNs and achieving superior cold-start recommendation performance.

Analyzing User Interactions with Biomedical Ontologies: A Visual Perspective

Biomedical ontologies are large: Several ontologies in the BioPortal repository contain thousands or even hundreds of thousands of entities. The development and maintenance of such large ontologies is difficult. To support ontology authors and repository developers in their work, it is crucial to improve our understanding of how these ontologies are explored, queried, reused, and used in downstream applications by biomedical researchers. We present an exploratory empirical analysis of user activities in the BioPortal ontology repository by analyzing BioPortal interaction logs across different access modes over several years. We investigate how users of BioPortal query and search for ontologies and their classes, how they explore the ontologies, and how they reuse classes from different ontologies. Additionally, through three real-world scenarios, we not only analyze the usage of ontologies for annotation tasks but also compare it to the browsing and querying behaviors of BioPortal users. For our investigation, we use several different visualization techniques. To inspect large amounts of interaction, reuse, and real-world usage data at a glance, we make use of and extend PolygOnto, a visualization method that has been successfully used to analyze reuse of ontologies in previous work. Our results show that exploration, query, reuse, and actual usage behaviors rarely align, suggesting that different users tend to explore, query and use different parts of an ontology. Finally, we highlight and discuss differences and commonalities among users of BioPortal.